ACM Multimedia 2007

Call for Papers (PDF) University of Augsburg Augsburg, Germany September 24 – 29, 2007 http://www.acmmm07.org

ACM Multimedia 2007 invites you to participate in the premier annual multimedia conference, covering all aspects of multimedia computing: from underlying technologies to applications, theory to practice, and servers to networks to devices.

A final version of the conference program is now available.

Registration will be open from 7:30am to 7pm on Monday and 7:30am to 5pm on Tuesday, Wednesday and Thursday On Friday registration is only possible from 7:30am to 1pm.

ACM Business Meeting is schedule for Wednesday 9/26/2007 during Lunch (Mensa). Ramesh Jain and Klara Nahrstedt will talk about the

SIGMM status SIGMM web status Status of other conferences/journals (TOMCCAP/MMSJ/…) sponsored by SIGMM Miscellaneous

Also

Chairs of MM’08 will give their advertisement Call for proposals for MM’09 + contenders will present their pitch Announcement of Euro ACM SIGMM Miscellaneous

Travel information:

How to get to Augsburg How to get to the conference sites (Augsburg public transport) Conference site maps and directions (excerpt from the conference program) Images of Augsburg

The technical program will consist of plenary sessions and talks with topics of interest in:

(a) Multimedia content analysis, processing, and retrieval; (b) Multimedia networking, sensor networks, and systems support; (c) Multimedia tools, end-systems, and applications; and (d) Multimedia interfaces;

Awards will be given to the best paper and the best student paper as well as to best demo, best art program paper, and the best-contributed open-source software.

Panels will consist of discussions on timely and controversial topics.

Short Papers will be presented in poster format and are an opportunity for researchers to present new work and ideas in an interactive setting.

State-of-the-Art Tutorials by leading experts will precede the technical program. The full- and half-day offerings will span a wide variety of topics.

Brave New Topics track is a special sessions track containing papers, which establish foundational sciences and extend the boundaries of multimedia research.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/index.htm[1/28/2010 9:23:42 AM] ACM Multimedia 2007

Technical Demos will include leading edge work in every area of multimedia technology and its application.

Video Demonstrations allow researchers and artists to demonstrate their tool, system or application without having to bring the equipment for a "live" demo.

The Interactive Art Program will include long and short papers describing interactive multimedia art works, tools, applications, and technical approaches for creative uses of multimedia content and technology. It will also include an art exhibition.

Workshops on topics of current interest to members of the multimedia research community will follow the technical program.

Doctoral Symposium is an opportunity for students involved in the preparation of a PhD to interactively discuss their research issues and ideas with senior researchers, receive constructive feedback from members of the research community.

The Open-source Software Competition is a recent addition to the ACM Multimedia program and 2007 will be our forth year in running the competition.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/index.htm[1/28/2010 9:23:42 AM] ACM Multimedia 2007

Call for Papers (PDF) University of Augsburg Augsburg, Germany September 24 – 29, 2007 http://www.acmmm07.org

ACM Multimedia 2007 invites you to participate in the premier annual multimedia conference, covering all aspects of multimedia computing: from underlying technologies to applications, theory to practice, and servers to networks to devices.

A final version of the conference program is now available.

Registration will be open from 7:30am to 7pm on Monday and 7:30am to 5pm on Tuesday, Wednesday and Thursday On Friday registration is only possible from 7:30am to 1pm.

ACM Business Meeting is schedule for Wednesday 9/26/2007 during Lunch (Mensa). Ramesh Jain and Klara Nahrstedt will talk about the

SIGMM status SIGMM web status Status of other conferences/journals (TOMCCAP/MMSJ/…) sponsored by SIGMM Miscellaneous

Also

Chairs of MM’08 will give their advertisement Call for proposals for MM’09 + contenders will present their pitch Announcement of Euro ACM SIGMM Miscellaneous

Travel information:

How to get to Augsburg How to get to the conference sites (Augsburg public transport) Conference site maps and directions (excerpt from the conference program) Images of Augsburg

The technical program will consist of plenary sessions and talks with topics of interest in:

(a) Multimedia content analysis, processing, and retrieval; (b) Multimedia networking, sensor networks, and systems support; (c) Multimedia tools, end-systems, and applications; and (d) Multimedia interfaces;

Awards will be given to the best paper and the best student paper as well as to best demo, best art program paper, and the best-contributed open-source software.

Panels will consist of discussions on timely and controversial topics.

Short Papers will be presented in poster format and are an opportunity for researchers to present new work and ideas in an interactive setting.

State-of-the-Art Tutorials by leading experts will precede the technical program. The full- and half-day offerings will span a wide variety of topics.

Brave New Topics track is a special sessions track containing papers, which establish foundational sciences and extend the boundaries of multimedia research.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/index.html[1/28/2010 9:23:46 AM] ACM Multimedia 2007

Technical Demos will include leading edge work in every area of multimedia technology and its application.

Video Demonstrations allow researchers and artists to demonstrate their tool, system or application without having to bring the equipment for a "live" demo.

The Interactive Art Program will include long and short papers describing interactive multimedia art works, tools, applications, and technical approaches for creative uses of multimedia content and technology. It will also include an art exhibition.

Workshops on topics of current interest to members of the multimedia research community will follow the technical program.

Doctoral Symposium is an opportunity for students involved in the preparation of a PhD to interactively discuss their research issues and ideas with senior researchers, receive constructive feedback from members of the research community.

The Open-source Software Competition is a recent addition to the ACM Multimedia program and 2007 will be our forth year in running the competition.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/index.html[1/28/2010 9:23:46 AM] Important Dates

Important Dates

Feb. 15, 2007 Workshop Proposal Submission Deadline April 2, 2007 Panel Submission Deadline Tutorial Proposal Submission Deadline Brave New Topics Session Proposals April 16, 2007 Research Paper Submission Deadline (EDAS) Interactive Arts Program: Long Paper Submission Deadline May 22, 2007 Interactive Arts Program: Exhibition Submission Deadline June 1, 2007 Short Paper Submission Deadline ( EDAS - Content Track ,EDAS - System and Network Track, EDAS - Applications Track )

Open Source Submission Deadline Doctoral Symposium Submission Deadline Technical Demo Submission Deadline Video Demo Submission Deadline Interactive Arts Program: Short Paper Submission Deadline June 14, 2007 ACM MM 2007 PC Meeting (TU Delft). June 20, 2007 Acceptance Notification

Sep. 23-29, 2007 Main Conference

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/important_dates.html[1/28/2010 9:23:47 AM] Info for Authors

Instructions for preparing camera-ready papers

Click here for detailed camera-ready paper instructions.

Attn.: At least one author of each accepted conference/workshop papers has to register by the advanced registration deadline (August 15, 2007) as a "non-student."

The deadlines for the various tracks are listed below.

Paper Type Max. number of pages Deadline Full papers 10 July 2, 2007 Short papers 4 July 11, 2007 Demo papers 2 July 2, 2007 Panel descriptions 2 July 2, 2007 Art full papers 10 July 2, 2007 Art short papers 4 July 11, 2007 Art exhibit papers 2 July 11, 2007 Brave new topic papers 10 July 2, 2007 Video papers 2 July 11, 2007 Doctoral symposium papers 3 July 11, 2007 Open source contest 4 July 11, 2007 Keynote talks 1 July 2, 2007 Tutorials 2 July 2, 2007 MV workshop 6 July 5, 2007 TVS workshop 10 July 5, 2007 HCM workshop 10 July 11, 2007 MIR workshop 10 July 11, 2007 MS workshop 10 July 11, 2007 EMME workshop 10 July 5, 2007

Please note that the page limits are firm - there is no opportunity to purchase extra pages.

Instructions for Presenters

Posters: Easels will be provided to attach your printed poster to, as well as staples, tape, or an appropriate method of attachment. The easels are large enough to hold the ISO AO size (33" width by 46" height, or 89cm by 118cm). Posters should be set up before the poster session begins. An author should be at the poster at the specified times (see the conference schedule).

You want your poster to be visually appealing and interesting, but most of all, make sure that your poster is easy to read from a distance. Fonts for text should be at a minimum 24 point, without exception. If your text does not fit on the poster at this size, then this is a good indication that you need to reduce the amount of text, not the font size. Use an easy to read font (e.g., Times, Palatino or other serif font) for the text. A good font size for titles is 72 point.

Oral presentations: See here

Demo presentations: Please arrive at least 30 minutes prior to the beginning of your demo session to set up your demo. Each demo station will be provided with two tables (size of a single table W x L x H: 60 cm x 140 cm x 75 cm = 23,6 in x 55,1 in x 29,5 in), and power. There will be wireless Internet connection in the room. There is NO provision to display posters at the demo session.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/info_for_authors.html[1/28/2010 9:23:49 AM] Info for Authors

There is NO provision for a slideshow or talk about your demo. The audience will walk around the room and will interact with you on a one-on-one basis. You are expected to be available at your demo station for the duration of the demo session.

Video presentations: Authors of the video demonstrations are asked to be present for the presentation of their videos. Each video will be followed by a short question and answer session from the audience. The authors should be prepared to answer questions regarding their videos.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/info_for_authors.html[1/28/2010 9:23:49 AM] People

Organizing Committee

General Co-Chairs Local Arrangement

Rainer Lienhart (U. Augsburg ) Gregor van den Boogaart ( U. Augsburg) Anand R. Prasad (DoCoMo Euro-Labs) Jochen Lux ( U. Augsburg) Simon Hoffmann (U. Augsburg) Technical Program Coordinator Susanne Boll (U. Oldenburg)

Chitra Dorai (IBM Watson) Video Program

Program Co-Chairs Thomas Haenselmann (U. Mannheim)

Alan Hanjalic (TU Delft) Demonstration Co-Chairs Sunghyun Choi (Seoul National U.) Brian Bailey (UIUC) Milind Naphade (IBM Watson) Nicu Sebe (U. Amsterdam) Wei-Ying Ma (Microsoft Research Asia)

Short Paper Co-Chairs Doctorial Symposium

Chitra Dorai (IBM Watson) Thomas Plagemann (U. Oslo) Julien Laganier (DoCoMo Euro-Labs) Vera Goebel (U. Oslo) Susanne Boll (U. Oldenburg) Publicity Co-Chairs Tutorial Co-Chairs Wolfgang Effelsberg (U. Mannheim) Benoit Huet (EURECOM) Yong Rui (Microsoft China R&D Group) Malcolm Slaney (Yahoo! Research) Alf Zugenmaier (DoCoMo Euro-Labs)

Workshop Co-Chairs Treasurer

Belle Tseng (NEC USA) Barbara de Vega (U. Augsburg ) Daniel Gatica-Perez (IDIAP) Sponsoring Chair Panel Co-Chairs Arnon Amir (IBM Almaden Research ) Yap-Peng Tan (NTU) Mohan Kankanhalli (NUS) Proceedings Chair

Brave New Topics Co-Chairs Roger Zimmermann (USC)

Edward Chang (Google Research) Registration Co-Chairs Shin'ichi Satoh (NII) Yi Y. Wu (Intel Corporation ) Open Source Competition Marc Emmelmann (TU Berlin) Eva Hörster (U. Augsburg) Apostol Natsev (IBM Watson) Web Co-Chairs Interactive Art Program Simon Hoffmann (U. Augsburg) Alejandro Jaimes (IDIAP Research Institute) Benedikt Gleich (U. Augsburg ) Frank Nack (Université Claude Bernard Lyon 1) Video Production Chair Thomas Rist (FHA) Ina Döhring (U. Augsburg) SIG MM Chair SIG MM Director of Conferrences Ramesh Jain (UCI) Nevenka Dimitrova (Philips)

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/people.html[1/28/2010 9:23:50 AM] Conference Program

Conference Program

General Schedule

Monday, Sep. 24 Tutorials Tueday, Sep. 25 Main conference, arts program, evening reception Wednesday, Sep. 26 Main conference, arts program, conference banquet dinner Thursday, Sep 27 Main conference, arts program Friday, Sep 28 All Workshops Saturday, Sep 29 MIR Workshop

Overview

Final Program

Conference Events

Full Papers Short Papers Workshops Tutorials Demos Doctoral Symposium Video Program Open Source Contest Panel Brave New Topics Interactive Arts Program Papers and Exhibition

Keynote Speakers

Invited Talk: SmartWeb: Multimodal Web Services on the Road Invited Speaker: Prof. Wolfgang Wahlster, DFKI

Tuesday, September 25th, 9:00am

Invited Talk: Insights into Future Mobile Multimedia Applications Invited Speaker: Dr. Minoru Etoh , Research Laboratories, NTT DoCoMo

Thursday, September 26th, 9:00am

Applications Keynote Speakers

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/conference_programm.html[1/28/2010 9:23:52 AM] Conference Program

Invited Talk: Applied Image Science - From Consumers' Digital Files to Tangible Image Products Invited Speaker: Dr. Fageth, CeWe Color

Wednesday, September 26th, 9:15am

Invited Talk: The Workplace of the Future Invited Speaker: Prof. Dr. Lutz Heuser, SAP AG

Wednesday, September 26th, 8:30am

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/conference_programm.html[1/28/2010 9:23:52 AM] Workshops

Workshops

Following the successful events of previous years, ACM Multimedia 2007 has five day-long workshops and one two days-long workshop on topics in new and emerging areas of interest to members of the multimedia research community.

Important Dates

28 September 2007 All Workshops but MIR 28-29 September 2007 MIR Workshop

Accepted Workshops at ACM Multimedia

1. Workshop on Multimedia Information Retrieval (MIR 2007)

Multimedia information retrieval is being transformed into a cross-cutting field. Extending beyond the borders of culture, art, and science, the search for digital information is one of the major challenges of our time. Digital libraries, bio-computing & medical science, the Internet, streaming video, databases, cultural heritage collections and peer-2-peer networks have created a worldwide need for new paradigms and techniques on how to browse, search, and summarize multimedia collections. MIR 2007 is a peer-reviewed meeting for researchers in both academia and the industry, and users to discuss important challenges in multimedia retrieval. We welcome relevant paper submissions from computer and information sciences, computer engineering, electrical engineering, mathematics, statistics, physics, business, humanities, biology, medicine, ...

Following the success of the eight previous MIR workshops held in conjunction with the ACM Multimedia Conferences, the purpose of the 9th ACM SIGMM International Workshop on Multimedia Information Retrieval is to bring together researchers, developers, and practitioners from academia and industry. We are soliciting original papers that address a wide range of issues in multimedia information retrieval.

Important Dates

22 June 2007 MIR’2007 Submission Deadline 9 July 2007 MIR’2007 Acceptance Notification 15 July 2007 Camera-ready papers due

Organizers:

James Z. Wang and Nozha Boujemaa

2. Workshop on Mobile Video (MV 2007)

Mobile video is one of the key technologies pushing the development and usage of current and future wireless networks. With applications as diverse as conversational service, mobile TV and video-on-demand, video gaming, and surveillance, mobile video is a major research and business opportunity with great potential to enrich society and to support the needs of our increasingly mobile daily life.

ACM Mobile Video will be held in conjunction with ACM Multimedia on September 28th at the University of Augsburg, Germany. The technical program of the 1st ACM SIGMM Workshop on Mobile Video will consist of invited talks, oral presentations, and poster sessions. The one-day workshop is single track.

Important Dates

1 June 2007 MV’07 Submission Deadline 1 July 2007 MV’07 Acceptance Notification

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/workshops.html[1/28/2010 9:23:53 AM] Workshops

11 July 2007 Camera-ready papers due

Organizers:

Chang Wen Chen and Eckehard Steinbach

3. TRECVID Video Summarization (TVS 2007)

In 2007 the TREC Video Retrieval Workshop series will run a 1-day workshop on video summarization of unedited BBC video (rushes) as part of the ACM Multimedia Conference 2007, Augsburg, Germany on Friday, 28. September 2007.

PLEASE NOTE: Use of the BBC data and presentations at the ACM workshop (oral, poster, demo) will be limited to groups who are already active participants in TRECVID 2007 and have completed submissions for the TRECVID video summarization task. But attendance at the ACM workshop and participation in discussions will be open to all who sign up for the ACM workshop.

Organizers:

Paul Over and Alan Smeaton

4. Human-Centered Multimedia (HCM 2007)

Human-Centered Computing (HCC) lies at the crossroads of multiple disciplines and research areas that are concerned both with understanding human beings and with the design of computational methods. Researchers and designers of HCC methods and systems include engineers, scholars in psychology, cognitive science, sociology, and graphic designers, among others. Research in HCC deals with understanding humans, both as individuals and in social groups, by focusing on the ways that human beings adopt, adapt, and organize their lives around computational technologies, and on how the development of computational technologies can be informed by human aspects (culture, social setting, human abilities, etc.). Human-Centered Computing addresses problems that the field of Human Computer Interaction (HCI) does not generally address. In HCC the focus is not only on interaction, but also on the design of algorithms and systems with a human focus from start to finish.

Following the success of the previous HCM workshop held in conjunction with the ACM Multimedia 2006 Conference, this year's workshop we will have an entirely different format consisting of very short oral presentations and posters, so the focus will be on group discussions centered around the accepted works and the foundational issues of human-centered multimedia. Workshop attendees will be divided into discussion- focused groups and asked to define frameworks, tasks, or definitions that are relevant to the theme of the workshop. Specific details will be posted in due course, but we expect the new format to allow the presentation of novel technical works as well as the exchange and generation of ideas related to human- centered computing.

Important Dates

22 June 2007 HCM’07 Submission Deadline 9 July 2007 HCM’07 Acceptance Notification 15 July 2007 Camera-ready papers due

Organizers:

Alex Jaimes and Nicu Sebe

5. The Many Faces of Multimedia Semantics (MS 2007)

Information is increasingly becoming ubiquitous and all-pervasive, with the World-Wide Web as its primary repository. The rapid growth of information on the Web creates new challenges for information retrieval. Recently, there has been a growing interest in the investigation and development of the next generation web – the Semantic Web. The Semantic Web enables programs/agents to automatically understand what data is about, and therefore, bridge the, so-called, semantic gap between the ways in which users request web resources and the real needs of those users, ultimately improving the quality of web information retrieval.

Multimedia information has always been part of the Semantic Web paradigm, but, in general, has been discussed very simplistically by the Semantic Web community. We believe that, rather than trying to discover a media object’s hidden meaning, one should formulate ways of managing media objects so as to help people

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/workshops.html[1/28/2010 9:23:53 AM] Workshops

make more intelligent use of them. The relationship between users and media objects should be studied. Media objects should be interpreted relative to the particular goal or point-of-view of a particular user at a particular time.

Content-based descriptors are necessary to this process. Recently, a major European wireless service provider managed to have all its digital media content providers supply metadata in RDF, and saw their revenues increase by 20% in three months. Major search engines are in the process of rolling out A/V search capabilities. At the same time, such descriptions are definitely not sufficient. Context is also important, and should be managed. The area of emergent multimedia semantics has been initiated to study the measured interactions between users and media objects, with the ultimate goal of trying to satisfy the user community by providing them with the media objects they require, based on their individual previous media interactions.

The arrival of Web 2.0 has added new paradigms to the media mix. Such concepts as a folksonomy, a form of emergent semantics, introduces a collaborative, dynamic approach to the generation of ontologies and media object semantics. That such an approach results in a stable semantics, though surprising, has been recently demonstrated.

Important Dates

25 June 2007 MS’07 Submission Deadline 9 July 2007 MS’07 Acceptance Notification 15 July 2007 Camera-ready papers due

Organizers:

William Grosky, Farshad Fotouhi, and Peter Stanchev

6. Educational Multimedia and Multimedia Education (EMME 2007)

Advances in multimedia capture, analysis and delivery, combined with the rapid adoption of broadband communication, have resulted in multimedia teaching systems that have advanced traditional forms of education. Research in these areas has achieved impressive results in the last few years and many actual working systems and commercial products are now routinely used by a growing number of people. However, the various web sites and lecture videos produced as part of the e-learning hype generally do not exploit the full potential of multimedia. The question about how multimedia can really make learning more exploratory and enjoyable is as yet unanswered, and we are just beginning to understand the real contribution of multimedia to education. In addition, new trends in multimedia technology, such as multimedia on handheld devices or advanced approaches for the automatic analysis of multimodal signals, offer novel and exciting opportunities for teaching and learning.

The growing pervasiveness of multimedia on any computing device also increases the relevance of knowledge about multimedia for computer scientists and software engineers. However, the significance of multimedia for the future of computing is generally not reflected in current curricula. For example, few universities offer dedicated courses and multimedia is often only taught as part of other courses such as computer graphics or machine learning. In addition, multimedia is a very active and rapidly changing field. New and emerging technologies can not only influence how we teach but also have an impact on what we should teach.

The goal of this workshop is to identify current and evolving trends, specify open problems, and discover challenges and prospects for new research in the broad topic of multimedia-based education. By bringing together researchers working on educational multimedia with multimedia educators, we want to establish an open discussion on these issues and create a reference for future research in this area.

Important Dates

6 June 2007 EMME’07 Submission Deadline 5 July 2007 EMME’07 Acceptance Notification 11 July 2007 Camera-ready papers due

Organizers:

Gerald Friedland, Wolfgang Hürst, and Lars Knipping

Contacts

If you have any questions regarding the workshops please contact the workshop chairs.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/workshops.html[1/28/2010 9:23:53 AM] Workshops

Belle L. Tseng, Ph.D. NEC Labs America Cupertino, CA, USA Daniel Gatica-Perez, Ph.D. IIDIAP Research Institute Martigny, Switzerland

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/workshops.html[1/28/2010 9:23:53 AM] Tutorials

Tutorials

We've assembled the finest group of tutorials for this year's ACM Multimedia. We have something for everybody, from new students just starting work in multimedia to the most seasoned researcher. Our presenters have worked hard to distill the essence of their topics into a half-day tutorial. Spend the day learning everything you need to think and work in these areas.

The tutorials are grouped into four areas:

Machine Learning - How do we make inferences about our multimedia data?

Bayesian Methods for Multimedia (am) Active Learning for Multimedia (pm)

Emerging Technologies - New ideas for working with multimedia data

Inpainting (am) Large Data Methods for Multimedia (pm)

Standards - How is multimedia delivered?

MPEG (am)

Tools you can use - How do yo make your multimedia ideas real?

Mobile Phone Programming for Multimedia (am) Human-Centered Multimedia Systems (pm)

We hope you will enjoy these tutorials. We think there is something for everyone!

Machine Learning

How do we reason about multimedia data. The most common tools for statistical reasoning are based on statistics. Bayesian methods provide the basic approach and are widely used. When basic statistics are not enough, people are added to the loop so that their opinions can actively improve the system's performance.

Tutorial: Bayesian Methods for Multimedia Signal Processing Presenter: A. Taylan Cemgil

In the last years, there have been a significant growth of multimedia information processing applications that employ ideas from statistical machine learning and probabilistic modeling. In this paradigm, multimedia data (music, audio, video, images, text, ...) is viewed as realizations from highly structured stochastic processes. Once a model is constructed, several interesting problems such as transcription, coding, classification, restoration, tracking, source separation or resynthesis etc. can be formulated as Bayesian inference problems. In this context, graphical models provide a "language" to construct models for quantification of prior knowledge. Unknown parameters in this specification are estimated by probabilistic inference. Often, however, the problem size poses an important challenge and in order to render the approach feasible, specialized inference methods need to be tailored to improve the computational speed and efficiency.

The scope of the proposed tutorial is as follows: First, we will review the fundamentals of probabilistic models, with some focus on music, video and text data. Then, we will discuss the numerical techniques for inference in these models. In particular, we will review exact inference, approximate stochastic inference techniques such as Markov Chain Monte Carlo, Sequential Monte Carlo and deterministic (variational) inference techniques. Our ultimate aim is to provide a basic understanding of probabilistic modeling for multimedia processing, associated computational techniques and a roadmap such that information retrieval researchers new to the Bayesian approach can orient themselves in the relevant literature and understand the current state of the art.

Presenter’s biography: A. Taylan Cemgil received his B.Sc. and M.Sc. in Computer Engineering, Bogazici University, Turkey and his Ph.D. (2004) from Radboud University Nijmegen, the

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/tutorials.html[1/28/2010 9:23:55 AM] Tutorials

Netherlands with a thesis entitled Bayesian music transcription. Between 2003-2005, he worked as a postdoctoral researcher at the University of Amsterdam on vision- based multi-object tracking. He is currently a research associate at the Signal Processing and Communications Lab., University of Cambridge, UK, where he cultivates his interests in machine learning methods, stochastic processes and statistical signal processing. His research is focused towards devoloping computational techniques for audio, music and multimedia processing.

Tutorial: Active learning for multimedia indexing and retrieval. Presenter: Dr. Georges Quénot

Active learning improves the performance of classification or search systems by adding humans to the loop. It is useful for optimizing the annotation of large corpora, those labeled data being useful for efficient supervised learning. The proposed tutorial responds to a strong need for the integration of this technique in multimedia indexing and retrieval systems. It will present the basics of active learning and will give the necessary information for quickly and efficiently integrating it within a project.

Supervised learning consists of training a system from sets of positive and negative examples. The learning system is composed of feature extractors, classifiers and fusion modules. The system's performance depends not only on the implementation choices and but its performance also strongly depends upon the quantity and quality of the training examples. While it is quite easy and cheap to get large amounts of raw data, it is usually very costly to have them annotated because this involves a human intervention for the assessment of the “ground truth”. While the volume of data that can be manually annotated is limited due to the cost of manual intervention, it is useful to select the data samples to be annotated so that their annotations are as useful as possible. Deciding which samples will be the most useful is not trivial. Active learning is an approach in which the system predicts the usefulness of new labeled samples. The whole process is a virtuous circle is operating in which the system gets better and better as new samples are annotated. This approach is a particular case of incremental learning in which a system is trained several times with a growing set of samples.

The tutorial will include two parts. The first part is an introduction describing the principles, the history and the main applications of active learning. Active learning is often used offline, typically in the case of classification based on supervised learning. It can also be used online when a system is dynamically modeling a user’s need via relevance feedback. The second part of the tutorial is a detailed analysis of active learning applied to semantic video indexing. This is a high level feature (concepts) extraction task in the NIST TRECVID evaluation campaign. I will analyze the effect of the following parameters: the active learning strategy, the fraction of the training set that is annotated, the active learning step size, the difficulty or the frequency of the targeted concepts, the total size and the variety of the training set, the precision versus recall compromise, and the combination of strategies. A particular focus will be on the optimal creation of annotations for a training corpus. It will be illustrated with the case of the collaborative annotation of the TRECVID 2007 development set which will be done in the context of an active learning process. A global conclusion will be given. It will summarize the important points and options, it will make a synthesis of the acquired experience in the field and it will indicate the still open questions.

Presenter’s biography: Dr. Georges Quénot is Researcher at CNRS (French National Centre for Scientific Research). He has an engineer diploma of the French Polytechnic School (1983) and a PhD in computer science (1988) from the University of Orsay. He is currently with the Multimedia Information Indexing and Retrieval group (MRIM) of the Laboratoire d'informatique de Grenoble (LIG) where he is responsible for their activities on video indexing and retrieval. His current research activity is about semantic indexing of image and video documents using supervised learning, networks of classifiers and multimodal fusion. He participated since 2001 in the NIST TRECVID evaluations on shot segmentation, story segmentation, concept indexing and search tasks. He is organizing the collaborative annotation for the TRECVID 2007 development data using an active learning approach.

Emerging Technologies

Tutorial: Digital Inpainting Presenter: Timothy K. Shih

Digital inpainting is an interesting new research topic in multimedia computing and image processing since 2000. This tutorial will cover the most recent contributions in image inpainting / image completion, video inpainting, and 3- D surface completion. In the literature, the first intention of image inpainting was to remove damages portions of an aged photo, by completing the area with surrounding or global information. The techniques used include the analysis and usage of pixel properties in spatial and frequency domains. Furthermore, image inpainting techniques were used in object removal (or image completion) in photos. Several strategic algorithms were developed based on

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/tutorials.html[1/28/2010 9:23:55 AM] Tutorials

confidence values and priorities of using patches. The techniques used in still images were then extended to video inpainting, which need to consider temporal properties such as motion vectors. With a reasonable combination of object tracking and image completion, objects in video can be removed and possibly replaced. On the other hand, aged films contain two types of defects: spikes and lone vertical lines. These defects need to be precisely detected and removed to restore the original film. In addition, based on image completion techniques, incompleteness of scanning results of a 3-D scanner due to improper location or other reasons of a scanner can be solved. This tutorial will discuss the above techniques founded in more than 30 top papers. In addition to an overview, the tutorial will be divided into 4 sections: image inpainting, video inpainting, 3-D surface inpainting, and a section to discuss inpainting projects developed by the presenter. Demonstrations will be included. In addition, the tutorial presenter will distribute a DVD ROM for the audience. The DVD ROM will include several interesting computer programs for testing inpainting results. In the past, the tutorial speaker delivered more than 20 keynotes/plenary talks and 16 tutorials (includes those in ACM Multimedia, IEEE ICME, IEEE PCM, MMM, and DMS).

Presenter’s biography: Dr. Shih is a professor of the Department of Computer Science and Information Engineering at Tamkang University, Taiwan and an adjunct professor at National Tsing Hua University, Taiwan. He is a member of ACM. As a senior member of IEEE, Dr. Shih joined the Educational Activities Board of the Computer Society. His current research interests include Multimedia Computing and Distance Learning. He was a faculty of the Computer Engineering Department at Tamkang University in 1986. In 1993 and 1994, he was a part time faculty of the Computer Engineering Department at Santa Clara University. He was also a visiting professor at the University of Aizu, Japan in summer 1999, a visiting researcher at the Academia Sinica, Taiwan in summer 2001, and is a visiting processor at the City University of Hong Kong in summer 2007. Dr. Shih is an adjunct faculty of Xidian University, Huazhong University of Science and Technology, and Beijing Jiaotong University, China. Dr. Shih has edited many books and published over 380 papers and book chapters, as well as participated in many international academic activities, including the organization of more than 50 international conferences and several special issues of international journals. He is the founder and co-editor-in-chief of the International Journal of Distance Education Technologies, published by Idea Group Publishing, USA. Dr. Shih is the associate editor of ACM Transactions on Internet Technology. He was also the associate editor of IEEE Transactions on Multimedia. Dr. Shih has received many research awards, including research awards from National Science Council of Taiwan, IIAS research award from Germany, HSSS award from Greece, Brandon Hall award from USA, and several best paper awards from international conferences. He also received many funded research grants from both domestic and international agencies. Dr. Shih has been invited to give more than 20 keynote speeches and plenary talks in international conferences, tutorials in IEEE ICME 2001/2006 and ACM Multimedia 2002/2007, and talks at international conferences and overseas research organizations. Publications, demonstrations and contact address of Dr. Shih can be retrieved from http://www.mine.tku.edu.tw/chinese/teacher/tshih.htm.

Tutorial: Large data methods for Multimedia Presenters: Michael Casey and Frank Kurth

This tutorial will describe techniques useful for tackling the large databases that are so common on the Internet today. There are more than 2 million songs in the commercial music catalog; Over 300 million images in a photo service like Flickr. How can we find the music, videos or images we want? How can we organize such large collections: find duplicates, create links between similar documents, and extract the semantic structure of complex audiovisual documents? Conventional methods for handling large data sets, such as hashing, get us part of the way to the right answer, but these methods do not extend or scale when used for similarity-based matching and retrieval in large audiovisual document collections. Similarly, elaborate methods from multimedia retrieval are available for semantic document analysis. Again, these methods do not scale for data sets with millions of items. Instead, new classes of algorithms, combining the best of the worlds of large data methods and semantic analysis, are needed to handle large multimedia databases. Innovative methods such as locality sensitive hashing, which are based on randomized probes, are the new workhorses.

This tutorial will cover methods for multimedia retrieval on large document collections. Starting with image and audio retrieval, it will describe both the theory (i.e., randomized algorithms for hashing) and the implementation details (how do you store hash values for 2 million songs?). A special focus will be on how to combine large data methods with semantically meaningful descriptors in order to facilitate efficient similarity-based retrieval. Besides image and audio, the tutorial will cover 3d motion and video retrieval.

Presenters' biographies: Michael Casey (PhD MIT 1998) is a professor at University of London, Goldsmith College. Heconducted his doctoral research at the MIT Media Lab's Music-Mind-Machine group. His research explores new approaches to computing as a creative medium and advanced computational methods for organising large multimedia collections to support digital humanties research. He is an editor of the MPEG-7 International Standard for Multimedia Content

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/tutorials.html[1/28/2010 9:23:55 AM] Tutorials

Description (ISO15938-4 Audio 2002), a standard for automatic organisation of multimedia databases. Michael is also a composer and artist and he has received a number of international awards for his works in digital media.

Frank Kurth studied computer science and mathematics at Bonn University, Germany, where he received both a Master's degree in computer science and the degree of a Doctor of Natural Sciences (Dr. rer. nat.) in 1997 and 1999, respectively. Since his Habilitation (postdoctoral lecture qualification) in computer science in 2004, he holds the title of a Privatdozent and is teaching at Bonn University. Currently, he is with the Communication Systems group at FGAN-FKIE in Wachtberg-Werthhoven, Germany. His research interests include audio signal processing, fast algorithms, multimedia information retrieval, and digital libraries for multimedia documents. Particular fields of interest are music information retrieval, fast content- based retrieval, and bioacoustical pattern matching.

Standards

Tutorial: MPEG Multimedia Standards: Evolution and Future Developments Presenter: Fernando Pereira

Multimedia communications play a growing role in the every day live o modern societies. Until recently, and except for broadcast television and radio, voice was still the sole communication mechanism. However, the diffusion of digital processing algorithms and hardware has brought images, music, and video into everyday life. The availability of open standards (such as JPEG, MPEG-X Audio and Video, H.26X) has had a major impact on this progression, notably due to the easy interoperability. Such standards have made the creation, and communication of (digital) data aimed at our most important senses, sight and hearing, simple, inexpensive and commonplace. With time, multimedia standards have addressed a growing set of fields from coding and metadata to rights management and content adaptation, following the increasing (functional and technical) complexity of multimedia applications.

Since MPEG standards have played a key role in the progress of the multimedia landscape, this tutorial will provide an evolutional overview of MPEG standards, discussing and explaining why certain choices were made, and thus a certain vision of the multimedia world was followed. Moreover this tutorial will specifically address the most recent MPEG standards, notably MPEG-21, MPEG-4 AVC, SVC and MVC, and finally MPEG-A.

Presenter’s biography: Fernando Pereira is currently Professor at the Electrical and Computers Engineering Department of Instituto Superior Técnico. He is responsible for the participation of IST in many national and international research projects. He acts often as project evaluator and auditor for various organizations. He is an Area Editor of the Signal Processing: Image Communication Journal and is or has been an Associate Editor of IEEE Transactions of Circuits and Systems for Video Technology, IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, and IEEE Signal Processing Magazine. He is a Member of the IEEE Signal Processing Society Image and Multiple Dimensional Signal Processing Technical Committee and of the IEEE Signal Processing Society Multimedia Signal Processing Technical Committee. He was an IEEE Distinguished Lecturer in 2005, and member of the Scientific and Program Committees of many international conferences. He has contributed more than 180 papers. He has been participating in the work of ISO/MPEG for many years, notably as the head of the Portuguese delegation, Chairman of the MPEG Requirements Group, and chairing many Ad Hoc Groups related to the MPEG-4 and MPEG-7 standards. His areas of interest are video analysis, processing, coding and description, and interactive multimedia services.

Tutorial: Multimedia Content Protection Presenters: Dulce Ponceleon and Nelly Fazio

This tutorial has been cancelled. We apologize for the inconvenience.

Tools you can use

Tutorial: Mobile Phone Programming for Multimedia Presenter: Jürgen Scheibl

If you are an enthusiastic mobile phone user who has many ideas and new ways of using your phone, this practical hands-on tutorial will show you how to realize your own novel concepts and ideas without spending too much time and effort. It aims to equip you with some practical skills of programming mobile devices for your projects and to bring inspiration for innovation.

Whether you are a novice programmer having some basic programming or scripting knowledge (Flash, Php, ...) or you are an experienced programmer, you will get a quick overview and understanding about programmable phone features especially for multimedia,. But first of all you will gain practical experience on how to write mobile applications with Python for S60 (Nokia) - even within this short tutorial time.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/tutorials.html[1/28/2010 9:23:55 AM] Tutorials

Topics to be covered:

1. Introduction to Python S60 – a trigger for innovation and a toolkit for rapid prototyping 2. Python S60,feature overview and demo examples (capabilities and limitations)

Hands-om session: 3. GUI programming, SMS sending/receiving, 4. Sound recording/playing, Midi, Text to speech 5. Camera, 2D Graphics, 3D Open GL ES, Keyboard key programming, Video playing 6. Bluetooth: phone to phone, phone to computer (e.g. controlling Max/MSP), phone to microcontroller (arduino) 7. Networking: File upload/download, Wifi, client-server applications 8. Location, Contacts and Calendar (Phones will be provided, but bring your own Laptop along: Mac, windows, Linux)

Online tutorial of Python for S60: http://www.mobilenin.com/pys60/menu.htm

The mobile space and the internet are rapidly converging and are turning into a rich source of opportunities. Modern mobile phones offer a large set of features including camera, sound, video, messaging, telephony, location, Bluetooth, Wifi, GPS, Internet access etc. Features that could easily be combined and used for creating new types of applications that kick and bring engaging experiences to users.

The problem: Developing applications on the mobile platform has been time consuming in the past and required a steep learning curve. As a result, people often gave up early or never started to turn their innovative ideas into working solutions. And in research projects we often face the situation that we have lack of time and resources. Additionally we often need to apply a rapid iterative design process for building our applications, but we might lack suitable tools for doing so.

Python for S60 which is introduced in this workshop offers a crucial turning point here. It allows developing mobile applications even by novice programmers, artists and people from the creative communities enabling them to contribute applications and concepts to the mobile space.

Python for S60 is easy to learn It can drastically reduce development time It makes rapid prototyping easy and efficient by wrapping complex low-level technical details behind simple interfaces and above all - it makes programming on the mobile platform fun.

Presenter’s biography: Jürgen Scheible is an Engineer (Telecommunications), a music and media artist. He is a doctoral student at the Media Lab, University of Art and Design, Helsinki where he runs the Mobile Hub, a prototype development environment for mobile client/server applications with a strong focus on artistic approaches and creative design. He spent several months in 2006 as a visiting scientist at MIT, Boston, CSAIL and worked previously for Nokia for 8 years. In 2006 and 2007 Jürgen was recognized as a Forum Nokia Champion for his driving vision to be a bridge builder between art, engineering and research. He is internationally active in teaching innovation workshops on rapid mobile application prototyping in academic but also professional settings e.g. at Stanford University, MIT, NTU Taiwan, Yahoo Research Berkeley, Nokia. In the 2nd half of 2007 his book “Mobile Python” will be published by Symbian Press/Wiley, bringing ‘easy programming’of mobile phones to the creative communities. He was one of the ACM Computers in Entertainment Scholarship Award winners in 2006 and Best Arts Paper Award winner at ACM Multimedia 2005 conference. His research focuses on designing multimodal user interfaces for creating and sharing interactive artistic experiences.

Tutorial: Human-Centered Multimedia Systems Presenters: Alejandro (Alex) Jaimes, IDIAP Research Institute (Switzerland) Nicu Sebe, University of Amsterdam (The Netherlands)

This tutorial will take a holistic view on the research issues and applications of Human-Centered Multimedia Systems focusing on three main areas: (1) multimodal interaction: visual (body, gaze, gesture) and audio (emotion) analysis; (2) image databases, indexing, and retrieval: context modeling, cultural issues, and machine learning for user-centric approaches; (3) multimedia data: conceptual analysis at different levels (feature, cognitive, and affective).

Multimedia plays a fundamental role in many new types of interfaces and application areas (multimodal and attentive interfaces, applications such as surveillance, medicine, art, etc.) in which humans play a central role. This implies that building Multimedia systems (e.g., for human-computer interaction, etc.) lies at the crossroads of many research areas (psychology, artificial intelligence, pattern recognition, computer vision etc.). Although many existing

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/tutorials.html[1/28/2010 9:23:55 AM] Tutorials

multimedia systems were designed with human uses in mind, many of them are far from being user friendly or are rooted on real-world human-needs (few Multimedia systems can be considered "Human-Centered"). What are the current trends in computing and what can the scientific/engineering community do to effect a change for the better? On one hand, the fact that computers are quickly becoming integrated into everyday objects (ubiquitous and pervasive computing) implies that effective natural human-computer interaction is becoming critical (in many applications, users need to be able to interact naturally with computers the way face-to-face human-human interaction takes place). On the other hand, the wide range of applications that use multimedia, and the amount of multimedia content currently available, imply that building successful computer vision and multimedia applications requires a deep understanding of multimedia content. The success of human- centered multimedia systems, therefore, depends highly on two joint aspects: (1) the way humans interact naturally with such systems (using speech and body language) to express emotion, mood, attitude, and attention, and (2) the human factors that pertain to multimedia data (human subjectivity, levels of interpretation).

In this tutorial, we take a holistic approach to developing human- centered multimodal systems. We aim to identify the important research issues, and to ascertain potentially fruitful future research directions in relation to the two aspects above. In particular, we introduce key concepts, discuss technical approaches and open issues in three areas: (1) multimodal interaction: visual (body, gaze, gesture) and audio (emotion) analysis; (2) image databases, indexing, and retrieval: context modeling, cultural issues, and machine learning for user- centric approaches; (3) multimedia data: conceptual analysis at different levels (feature, cognitive, and affective). The focus of the tutorial, therefore, is on technical analysis and interaction techniques formulated from the perspective of key human factors in a user-centered approach to developing Human- Centered Multimedia Systems.

Presenter’s biography: Alejandro Jaimes is Scientific Manager and Senior Researcher at IDIAP Research Institute where he is responsible for managing the research efforts of 12 partners within the EU-funded AMIDA integrated project (Augmented Multiparty Interaction), as well as leading the Human-Machine Interaction unit of IM2 (Interactive Multimodal Information Management), the Swiss National Centre of Competence in Research (NCCR) headed by IDIAP. His technical research focuses on creating new technical approaches for computer-understanding of multimedia content and for human interaction with computers in creative environments, mainly developing computer vision techniques that use machine learning, that involve humans directly, and that are rooted in principles, theories, or techniques from cognitive psychology, the arts, and information sciences, among others. He is a founding member of the IEEE Computer Society Taskforce on Human- Centered Computing, a co-editor of the IEEE Computer Special Issue on Human-Centered Computing (May 2007). Dr. Jaimes received a Ph.D. in Electrical Engineering (2003) and a M.S. in Computer Science from Columbia University (1997) in New York City. His work has led to over 50 technical publications in international conferences and journals, and to numerous contributions to the MPEG-7 standard. He has been granted several patents and serves in the program committee of several international conferences (Creativity and Cognition, ACM Multimedia, ICME, ICIP, CIVR, ICCV and ECCV Workshops on HCI, etc.).

Nicu Sebe is a professor in the Department of Computer Science at the University of Amsterdam, The Netherlands. His research interests include human-computer interaction from a computer vision perspective and multimedia information retrieval. He received a PhD in computer science from Leiden University, The Netherlands.

Contacts

For any questions regarding tutorials please email the tutorial co-chairs:

Benoit Huet (EURECOM) Malcolm Slaney (Yahoo! Research)

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/tutorials.html[1/28/2010 9:23:55 AM] Registration

Registration

Electronic registration is now available. Please review the registration information below before proceeding.

Click here to register on-line. PDF registration is no longer available.

Important Dates

15 August 2007 Advanced Registration Deadline is 11:59pm CET (Central European Time), 15 August 2007.

Attn.: At least one author of each accepted conference/workshop papers has to register by this deadline. 24 August 2007 Deadline for cancellation/refund request Registration deadline for on-line registration. On-site registration will be availabe at the 10 September 2007 conference venue. 12 September 2007 Deadline for check payments

Important Information for Authors

Each main conference accepted paper must have at least one author registered by the advance registration deadline as a non-student, for the paper to be included in the final conference program and the proceedings.

For workshop accepted papers, the same registration policy applies with respect to workshop registration.

Important Information for Students

ACM MM 2007 awards Student Conference Participation Grants. Click here for futher informaiton.

Remember that student registrants need to show proof of student status (e.g., Student ID or a letter from advisor or a letter from the department) when picking up the conference package.

Registration Fees

Advance registrations are encouraged. On-site registration will be available at the conference site.

For registration other than using the electronic registration form (i.e. on-site registration as well as sending the PDF registration form via e-mail, fax, or post) an additional processing fee of US$ 30 will be charged. To avoid this additional fee, please please register on-line (available soon).

There are several registration options, everything from a single half-day tutorial to an "all-inclusive" package deal:Note that

August 15, 2007 is the deadline for "Advance" registration. After this date, the "Late/On-Site" fees apply. The listed fees are applicable if you register on-line. If you choose to register via mail, fax, or e-mail using the PDF registration form, an additional processing fee of US$ 30 will be added.

Non-ACM ACM Student Member Member (USD) (USD) (USD) MAIN CONFERENCE Advance $650 $580 $300 Late/On-Site $720 $650 $350 Half-Day Tutorial Advance $120 $100 $75 Late/On-Site $145 $120 $100 Two Half-Day Tutorial Advance $220 $180 $120

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/registration.html[1/28/2010 9:23:57 AM] Registration

Late/On-Site $260 $215 $150 One-day Workshop Advance $180 $150 $100 Late/On-Site $200 $170 $120 Two-day Workshop Advance $230 $190 $135 Late/On-Site $270 $225 $165 Package A: Conference and one Advance $735 $645 $360 Half-Day Tutorial Late/On-Site not available Package B: Conference and two Advance $830 $725 $400 Half-Day Tutorials Late/On-Site not available Package C: Conference and one Advance $790 $690 $390 One-Day Workshop Late/On-Site not available Package D: Conference and one Advance $830 $720 $420 Two-Day Workshop Late/On-Site not available Package E: Everything (full Advance $880 $765 $450 conference, tutorials, and Late/On-Site not available workshops)

Become an ACM member!

Notes

All conference fees are in US Dollars (USD). Main conference registration includes: Attendance to the following sessions: keynote addresses, full papers, short paper presentation, technical demos, panels, video program, panel, doctoral symposium, and arts exhibition Main conference proceedings (on DVD) Attendance to social programs: receptions, conference banquet, coffee breaks and lunches (Note: student registration does not include the conference banquet.) Free rides with the tram (local public transportation in Augsburg) during the conference with your ACM MM07 badge(e.g., from hotel to conference venue) Extra purchases Extra banquet tickets (Wed. evening) may be purchased for $100 each. Extra reception tickets (Tues. evening) may be purchased for $25. Extra lunch tickets may be purchased for $35 each. Extra DVD proceedings (while available) may be purchased for $25. Payment: We accept payment through Master Card, Visa Card, Amex Card and Check. Check payment will only be available in the on-line registration before 06 September. Checks should be drawn on US Dollars and from a US bank. Checks should be made payable to "ACM/MM07". Please indicate your registration reference number on the check. The check and a copy of the registration invoice should be mailed to: Attn: Yi Wu, 2200 Mission College Blvd, SC12-303, Santa Clara, CA, 95054-1537, USA. Note that checks need to be recieved before 12 September, otherwise the registration will be cancelled.. Note also that checks are not accepted for on-site registration during the conference, only credit cards will be accepted. Registration Refund Policy: Full refunds (minus a $100 handling fee) may be granted before 24 August, 2007. After 24 August, 2007, no refunds will be made. Refund requests must be made in writing (by mail or fax) to the registration chairs. Please fax requests to Attn: Yi Wu, +1-408-653-9677, or mail in the request to: Attn: Yi Wu, 2200 Mission College Blvd, SC12-303, Santa Clara, CA, 95054-1537, USA. Registration receipts will be issued during the conference at the registration desk. Student registrants need to show proof of student status (e.g., Student ID or a letter from advisor or a letter from the department) when picking up the conference package. Also, ACM members need to include their ACM membership number on the registration form. Visa Letters: International registrants should be particularly aware and careful about visa requirements, and should plan travel well in advance. Please note that the Association for Computing Machinery does not issue formal invitation letters for visas. We can however issue a visa support letter.

All visa support inquiries must be handled by ACM HQ. Please send your request for a letter in support of a visa application to Ashley Cozzi ([email protected]); you must supply your name and mailing address as it appears on your passport, the name of the conference you are attending and your registration confirmation number. If you are the author of any papers accepted for the conference, please provide the title. We will also need a fax number in order to fax the support letter.

The web site of the German Federal Foreign office (http://www.auswaertiges-amt.de) includes information regarding the requirements for obtaining a visa as well as links to to the PDF form needed to apply for a visa.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/registration.html[1/28/2010 9:23:57 AM] Registration

Contacts

For queries regarding registration, please contact registration chairs:

Yi Wu (Intel Corporation) Eva Hörster (U. Augsburg) Marc Emmelmann (TU Berlin)

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/registration.html[1/28/2010 9:23:57 AM] Hotel & Travel

Accommodations and Travel

Note to conference members who have not booked a hotel room yet: it is highly recommended to book a hotel room as soon as possible. Most offers for preallocated hotel rooms are only valid until August 17, 2007. Since the conference takes place at the same time as the famous Munich Oktoberfest, a shortage of hotel rooms is to be expected.

Directions on how to get to Augsburg from the airport, as well as a map of the area, are given on the lower half of this page, just below the list of hotels. Click here to go there directly.

For preferred rates and allocations rooms must be reserved before August 17, 2007. Please book your room as early as possible. The famous Oktoberfest is being celebrated at the same time in Munich. This can lead to room shortages in the whole Greater Munich area, which includes Augsburg.

Each hotel listed below has access to the internet except where indicated otherwise.

You can reach the conference site, which is the University of Augsburg, Experimental Physik IV by tram number 3 (“Straßenbahn” 3) in about 10 minutes from the Central Station (“Hauptbahnhof”) or right from the center of Augsburg (Königsplatz).

Members of the Conference will get a badge which allows them to travel with local transport of Augsburg (tram/bus) for free. Main Conference Hotels

Steigenberger Drei Mohren (*****)

Room rates are from 132,00 € - 666,00 €

To make a reservation it is recommended to call +49 (0) 821 50360 Online booking - click “more options” and input “SRMEET04” and “4MR” as corporate ID and access code E-Mail: [email protected] Code: SRMEET04, for preferred rate 4MR

InterCityHotel (***)

Room rates are from 110,00 € - 120,00 €

E-Mail: [email protected] Online booking Click “Member Login” User ID: SRMEET01, password: ACM.MM07 for preferred rates Choose: “InterCityHotel Augsburg (Augsburg DE)” (5th in list) Phone: +49 (0) 821 50390 Fax: +49 (0) 821 5039999

Ibis Hotel Augsburg beim Hauptbahnhof (**)

Room rates are 65,00 €

Please make reservations via e-mail or phone: E-Mail: [email protected] Phone: +49 (0) 821 50160 Fax: 49 (0) 821 5016150 Keyword for preferred rates: ACM MM07 until the 17th of August Additional Hotels

Dorint Novotel Augsburg (****)

Special rate including breakfast: 110,00 €

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/hotel___travel.html[1/28/2010 9:23:59 AM] Hotel & Travel

E-Mail: [email protected] Phone: +49 (0) 821/5974 2966 Fax: ++49 (0) 821/5974 100

Hotel am Rathaus (***)

Special rate including breakfast: 75,00 €

E-Mail: [email protected] Phone: +49 (0) 821 346490 Fax: +49 (0) 821 3464999 Reservation only via phone, fax or email mention ACM Multimedia conference for preferred rates

Hotel Augusta (***1/2)

E-Mail: [email protected] Phone: +49 (0) 821 50140 or +49 (0) 821 5014105 Fax: ++49 (0) 821 5014605 or +49 (0) 821 5014103 Keyword for preferred rates: ACM.MM07

Riegele Privathotel (***)

E-Mail: [email protected] Online booking - input “ACM.MM07” in the field “special requests” Phone: +49 (0) 821 509000 fax +49 (0) 821 517746

Top City Hotel Ost am Kö (***1/2) fully booked

E-Mail: [email protected] Online booking Phone: +49 (0) 821 502040 Fax: ++49 (0) 821 5020444

Ibis Hotel Augsburg beim Königsplatz (**)

Please make reservations via e-mail or phone: E-Mail: [email protected] Phone: +49 (0) 821 50310 Fax: +49 (0) 821 5031300 Keyword for preferred rates: ACM MM07 best before the 16th of June

Hotel Garni im Diako

Online booking 5 minutes to the central station Preferred rates: input “ACM Multimedia 2007” into the field “Sonstiges/Ihr Anliegen”

Romantikhotel Augsburger Hof

Email: [email protected] Online booking Phone: +49 (0) 821 343050 Fax: 49 (0) 821 3430555 Keyword for preferred rates: “ACM MM 07”, until the 17th of August

Hotel Prinz Leopold

Email: [email protected] Online booking Phone: +49 (0) 821 80770 Fax: +49 (0) 821 8077333 Keyword for preferred rates: “ACM MM 07” best before the 31st of July is located south of Augsburg City, but is served by tram line 2

Hotel Zeller

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/hotel___travel.html[1/28/2010 9:23:59 AM] Hotel & Travel

Email: [email protected] Online booking Phone: +49 (0) 8231 9960 Fax: Phone: +49 (0) 8231 996222 Keyword for preferred rates: “ACM”, until the 17th of August (two options available) is located 15 km south of Augsburg in the town of Königsbrunn, which is not connected to the Augsburg tram. You would have to travel to the conference sites e.g. by cab, or bus line 92 (please see bus timetable here and here). Attendees having a car available can quickly reach University campus by the “B 17” highway while completely avoiding the Augsburg downtown traffic.

Hotel Weinberger

Room rates are from 28,00 € - 36,00 €

Email: [email protected] Phone: +49 (0) 8231 243910 Fax: Phone: +49 (0) 8231 438831 No internet access! In the suburb “Stadtbergen”. Connects via tram line 3 directly to the Central Station (< 15 minutes) and to the University campus (25 minutes).

Augsburger Parkhotel

Room rates are about 49,00 €

Email: [email protected] Phone: +49 (0) 8231 243990 Fax: Phone: +49 (0) 8231 2439950 Internet access only in selected rooms! In the suburb “Stadtbergen”. Connects via tram line 3 directly to the Central Station (< 15 minutes) and to the University campus (25 minutes).

Hotel Pension Jakoberhof

Room rates are about 52,00 €

Email: [email protected] Phone: +49 (0) 8231 510030 Fax: Phone: +49 (0) 8231 150844 Near the downtown, next to the famous “Fuggerei”.

Hotel Lochbrunner

Email: [email protected] Phone: +49 (0) 8231 502120 Fax: Phone: +49 (0) 8231 516326 No WLAN, only Modem. Internet cafe nearby (ask at the front desk). Downtown. Travel to Augsburg

Augsburg is located in Bavaria, Germany, about 70 km northwest of Munich. The airport closest to Augsburg is therefore Munich Airport, and flying directly to Munich is recommended. Alternatively, you can reach Augsburg also from Frankfurt Airport (roughly 350 km away).

There are three possibilities to get to Augsburg from the airport: by car, by train, or, in the case of Munich Airport, by airport shuttle/taxi. Airport shuttle services will pick you up at Munich Airport and bring you directly to your hotel in Augsburg. Please find directions for all these means of transportation below.

By car

You can rent a car at the airport and drive to Augsburg. A list of car rentals at Munich Airport is available here (in English). To rent a car at Frankfurt Airport, please follow this link (in English).

Click below for directions from Google Maps.

From Munich Airport to Augsburg Königsplatz From Frankfurt Airport to Augsburg Königsplatz

By train

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/hotel___travel.html[1/28/2010 9:23:59 AM] Hotel & Travel

Please click here for the online travel information of Deutsche Bahn in English. Choose your starting point as either “Munich Airport” or “FRA Frankfurt Airport”, enter “Augsburg” as your destination (this will map to Augsburg Central Train Station automatically) and choose date and time. You can check the prices and book your train tickets directly online. You can easily fetch a taxi directly in front of Augsburg Central Train Station upon arrival which will bring you to your hotel.

By airport shuttle/taxi from/to Munich Airport

Airport shuttle services will pick you up at Munich Airport and bring you directly to your hotel in Augsburg, and can bring you back to the airport after the conference as well. One-way tickets are around 40,00 Euros, round trip tickets around 80,00 Euros depending on the number of people and the exact destination addresses.

Bavaria Flughafen Transfer GmbH

Phone: +49 (0) 821 499001 Fax +49 (0) 821 472140 Email: [email protected]

Flughafentransfer München

Phone: +49 - (0)178 - 3 79 73 32 Fax: +49 - (0)89 - 95 44 60 67 Email: [email protected]

Taxi & Limousinenservice München Tokat

Phone: +49 (0) 89 312 40 23 Email: [email protected]

AirportExpress

Phone: +49 (0) 821 249 86 82 Fax: +49 (0) 821 299 37 18 Email: [email protected]

Flughafentransfer Stefan Kaulke

Phone: +49 (0) 821 5083409 Fax. +49 (0) 821 5083411 Emergency phone code: +49 (0) 171/8104149 Email: [email protected]

Map

The map below shows the conference sites and all of the hotels listed above. (To see the two hotels located south of Augsburg city, Hotel Prinz Leopold and Hotel Zeller, click and drag the visible area, and/or zoom out using the controls on the upper left.) The thick blue line marks a part of tram line 3, which connects Augsburg Central Train Station with the Königsplatz (the city’s main public transporation hub) and the conference sites on the University campus, as well as the Fachhochschule Augsburg where the Arts Program will take place. (Unfortunately, the tram line does not seem to be displayed in some versions of Internet Explorer. We apologize for the inconvenience.)

Public transportation in Augsburg

(This information with accompanying maps is also available in the conference program.)

All tram lines intersect at Königsplatz, the city’s main transportation hub. To change lines, you have to go to Königsplatz first. Also, many conference hotels are within walking distance from Königsplatz.

The most important tram line for the conference members is tram number 3, with the end points ‘Stadtbergen’ and ‘Inninger Str.’, respectively. Line 3 connects the Augsburg central train station with the University of Applied Sciences (called Fachhochschule Augsburg, location of arts exhibitions) and the campus of the University of Augsburg (the main conference site). The end point of the tram line is always being displayed on the front and sides of the tram. It tells you in which direction the tram is currently travelling. Inside the tram, the next stop is always being announced and/or displayed.

To get to either conference site from downtown Augsburg, take line 3 in direction ‘Inninger Str.’. It leaves at Königsplatz platform ‘F’ every 5 to 10 minutes, depending on the current day and time.

The live arts exhibition at the University of Applied Sciences (Fachhochschule Augsburg) is only two stops away from Königsplatz: after getting off the tram at ’Rotes Tor’, it is just a three-minute walk along ‘Rote-Torwall-Staße’” to the Fachhochschule.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/hotel___travel.html[1/28/2010 9:23:59 AM] Hotel & Travel

The University campus is roughly a 10 minute ride from Königsplatz. The stop to get off the tram is called ‘Universität’. There will be signs guiding you from the tram stop to the conference sites nearby.

To get back to downtown from either site, get on any line 3 tram towards Stadtbergen. It will arrive at Königsplatz platform ‘G’. From there, you can either walk back to your hotel (in most cases), or change tram and bus lines, or catch a taxi.

Please enable JavaScript in your browser to display this map.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/hotel___travel.html[1/28/2010 9:23:59 AM] Hotel & Travel

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/hotel___travel.html[1/28/2010 9:23:59 AM] Augsburg & Vicinity

Augsburg

http://www.augsburg.de: The official homepage of Augsburg

http://www.regio-augsburg.de: Homepage of Augsburgs tourist office

Detailed information in English can be found here: http://en.wikipedia.org/wiki/Augsburg

Images of Augsburg

For conference members interested in getting a first impression of Augsburg, there is a Flickr image group containing geotagged images of various city sights available here.

There is also another Flickr group where conference members can upload their own images taken at the conference.

University of Augsburg

http://www.uni-augsburg.de: The University of Augsburg

Bavarian Places of Interest

http://www.bayern.de: The official homepage of the Free State of Bavaria

see also http://en.wikipedia.org/wiki/Bavaria for detailed information

and of course Bavaria is a part of the Federal Republic of Germany: http://www.deutschland.de/

http://www.muenchen.de: The official homepage of Munich

http://www.oktoberfest.de: Information to the famous bavarian Oktoberfest

http://www.oberammergau.de: The official homepage of Oberammergau

http://www.neuschwanstein.de: The official homepage of the Neuschwanstein Castle

http://www.hohenschwangau.de: Tourist information about the castles Neuschwanstein and Hohenschwangau

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/augsburg___vicinity.html[1/28/2010 9:24:01 AM] Local Sights

Sights in Augsburg

Slideshows Augsburg

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/local_sights.html[1/28/2010 9:24:02 AM] Local Sights

Munich

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/local_sights.html[1/28/2010 9:24:02 AM] Sponsors

Sponsor Opportunities and Benefits

The conference organizers warmly invite your support of ACM Multimedia 2007. Corporate support publicizes your organization's interest in and commitment to the multimedia field. An event with international visibility, ACM MM 2007 is the perfect place to inform leaders and students in the field, as well as the interested general public, about your company's activities and products. Regarding the details on how to become an ACM MM 2007 corporate supporter, please read the linked document in the pdf format.

ACM Multimedia 2007 gratefully acknowledges the support of the following benefactors and sponsors:

Benefactors:

Sponsors:

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/sponsors.html[1/28/2010 9:24:04 AM] Sponsors

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/sponsors.html[1/28/2010 9:24:04 AM] Contact Us

This website is edited by

Prof. Dr. Rainer Lienhart Rainer.Lienhart (insert an at) informatik.uni-augsburg (insert a dot) de Lehrstuhl für Multimedia Computing Phone: +49 (821) 598-5703 Fax: +49 (821) 598-4329 Institut für Informatik Universität Augsburg Eichleitnerstr. 30 D-86135 Augsburg Germany

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/contact_us.html[1/28/2010 9:24:05 AM]

Organizing Committee Call for Papers General Co-Chairs University of Augsburg Rainer Lienhart (U. Augsburg ) Augsburg, Germany Anand R. Prasad (DoCoMo Euro-Labs) September 23 – 29, 2007 Program Co-Chairs http://www.acmmm07.org Alan Hanjalic (TU Delft) Sunghyun Choi (Seoul National U.) ACM Multimedia 2007 invites you to participate in the premier annual multimedia Brian Bailey (UIUC) Nicu Sebe (U. Amsterdam) conference, covering all aspects of multimedia computing: from underlying technologies to applications, theory to practice, and servers to networks to devices. Short Paper Co-Chairs Chitra Dorai (IBM Watson) Julien Langanier (DoCoMo Euro-Labs) The technical program will consist of plenary sessions and talks with topics of interest in: Susanne Boll (U. Oldenburg) (a) Multimedia content analysis, processing, and retrieval; Tutorial Co-Chairs (b) Multimedia networking, sensor networks, and systems support; Benoit Huet (EURECOM) Malcolm Slaney (Yahoo! Research) (c) Multimedia tools, end-systems, and applications; and (d) Multimedia interfaces; Workshop Co-Chairs Belle Tseng (NEC USA) Daniel Gatica-Perez (IDIAP) Key Dates March 26, 2007 Research Paper Abstract Deadline Panel Co-Chairs April 2, 2007 Research Paper/Panel/Tutorial/Workshop Submission Deadline Yap-Peng Tan (NTU) June 2, 2007 Short Paper/Open Source/Doctor Program/Demo Deadline Mohan Kankanhalli (NUS) June 20, 2007 Acceptance Notification New Foundational/Application Topics Edward Chang (Google Research) Awards will be given to the best paper and the best student paper as well as to best demo, Shin'ichi Satoh (NII) best art program paper, and the best-contributed open-source software. Open Source Competition Apostol Natsev (IBM Watson) Panels will consist of discussions on timely and controversial topics.

Interactive Art Program Short Papers will be presented in poster format and are an opportunity for researchers to Alejandro Jaimes (Fuji Xerox, Japan) present new work and ideas in an interactive setting. Frank Nack (CWI) State-of-the-Art Tutorials by leading experts will precede the technical program. The full- Video Program Thomas Haenselmann (U. Mannheim) and half-day offerings will span a wide variety of topics.

Demonstration Co-Chairs Brave New Topics track is a special sessions track containing papers, which establish Milind Naphade (IBM Watson) foundational areas and extend the boundaries of multimedia research. Wei-Ying Ma (Microsoft Research Asia) Technical Demos will include leading edge work in every area of multimedia technology Doctorial Symposium and its application. Thomas Plagemann (U. Oslo ) Vera Goebel (U. Oslo ) Video Demonstrations allow researchers and artists to demonstrate their tool, system or

Publicity Co-Chairs application without having to bring the equipment for a "live" demo. Wolfgang Effelsberg (U. Mannheim) Yong Rui (Microsoft China R&D Group) The Interactive Art Program will include long and short papers describing interactive Alf Zugenmaier (DoCoMo Euro-Labs) multimedia art works, tools, applications, and technical approaches for creative uses of multimedia content and technology. It will also include an art exhibition. Proceedings Chair Roger Zimmermann (USC) Workshops on topics of current interest to members of the multimedia research community

SIG MM Chair: Ramesh Jain (UCI) will follow the technical program. SIG MM Director of Conferences: Nevenka Dimitrova (Philips) Doctoral Symposium is an opportunity for students involved in the preparation of a PhD to interactively discuss their research issues and ideas with senior researchers, receive constructive feedback from members of the research community. The Open-source Software Competition is a recent addition to the ACM Multimedia program and 2007 will be our forth year in running the competition.

SPECIAL INTEREST GROUP on MULTIMEDIA

CONTENTS

FOREWORD ...... 3 MAPS ...... 7

AUGSBURG TRAM LINES ...... 7 LIVE ARTS EXHIBITION ...... 8 CONFERENCE SITE MAP ...... 9 FLOOR PLANS ...... 10 1: Keynote and Best Paper Sessions ...... 10 2: Conference Sessions, Workshops, and Tutorials ...... 10 OVERVIEW OF THE FULL CONFERENCE PROGRAM ...... 11

MONDAY, SEPTEMBER 24 ...... 11 TUESDAY, SEPTEMBER 25 ...... 11 WEDNESDAY, SEPTEMBER 26 ...... 12 THURSDAY, SEPTEMBER 27 ...... 12 FRIDAY, SEPTEMBER 28 ...... 13 MIR 2007 - Workshop on Multimedia Information Retrieval ...... 13 MV 2007 - Workshop on Mobile Video ...... 13 TVS 2007 - TRECVID Video Summarization ...... 13 HCM 2007 - Human-Centered Multimedia...... 13 MS 2007 - The Many Faces of Multimedia Semantics ...... 13 EMME 2007 - Educational Multimedia and Multimedia Education...... 13 SATURDAY, SEPTEMBER 29 ...... 13 MIR 2007 Workshop on Multimedia Information Retrieval ...... 13 HALF-DAY TUTORIALS ...... 15

MONDAY, SEPTEMBER 24, 2007 ...... 15 MAIN CONFERENCE FULL PROGRAM ...... 17

TUESDAY, SEPTEMBER 25, 2007 ...... 17 WEDNESDAY, SEPTEMBER 26, 2007...... 25 THURSDAY, SEPTEMBER 27, 2007 ...... 33 WORKSHOPS ...... 39

FRIDAY, SEPTEMBER 28, 2007 ...... 39 MIR 2007 - Workshop on Multimedia Information Retrieval ...... 39 MV 2007- Workshop on Mobile Video 2007 ...... 43 TVS 2007 - TRECVID Video Summarization ...... 47 HCM 2007- Human-Centered Multimedia ...... 49 MS 2007 - The Many Faces of Multimedia Semantics ...... 51 EMME 2007- Educational Multimedia and Multimedia Education ...... 53 SATURDAY, SEPTEMBER 29, 2007...... 57 MIR 2007 - Workshop on Multimedia Information Retrieval ...... 57 CO-SPONSORS ...... 59 SUPPORTERS ...... 59 CONFERENCE ORGANIZATION ...... 61

1

FOREWORD

Welcome to the Fifteenth ACM International Conference on Multimedia (ACM MM 2007), held September 24-29, 2007 at University of Augsburg in the beautiful and historic city of Augsburg, Bavaria, Germany. The city was founded 15 BC in the reign of Roman emperor Augustus.

ACM Multimedia is the premier annual professional meeting for communicating the state-of-the- art in multimedia research, technology, and art. As in previous years, starting with the first ACM Multimedia conference in 1993, the conference seeks to bring together researchers and practitioners in academia, industry, and government who are interested in exploring and exploiting new and multiple media to create new capabilities for human expression, communication, collaboration, and interaction. ACM Multimedia covers all aspects of multimedia computing: from underlying technologies to applications, theory to practice, and servers to networks to devices.

Multimedia is an interdisciplinary endeavor, and the variety of conference events reflects this. The overall conference encompasses three major parts: interesting tutorials on Monday, September 24, an exciting three-day main conference on Tuesday through Thursday, September 25-27, and a set of workshops in hot multimedia areas on Friday and Saturday, September 28-29.

The three-day main conference comprises several different technical program elements, each with separate submissions and reviewing: full papers, short papers, a panel, the doctoral symposium, a Brave New Topics session, technical demonstrations, a video program, an open source contest, and the Interactive Arts Program. We are excited to host two research keynote presentations by Prof. Wolfgang Wahlster of DFKI and the University of Saarland and Dr. Minoru Etoh of NTT DoCoMo, who will give unique perspectives of their research work in academia and industry. In addition two high-profile applications keynotes will be given by Dr. Fageth of CeWe Color, Europe's number one photo services company, and Prof. Lutz Heuser of SAP AG.

The program co-chairs for ACM MM 2007 are Alan Hanjalic, Sunghyun Choi, Brian Bailey, and Nicu Sebe, who were responsible, along with a program committee of 137 members, for selecting the long paper program in the areas of Content, Applications, Systems, and Multimedia Interactions. These tracks received 298 long paper submissions (113 in Content, 90 in Applications, 64 in Systems, and 30 in Multimedia Interactions). Each paper was reviewed by at least three qualified reviewers in a double-blind review process. The program committee met on June 14, 2007 in Delft, Netherlands to discuss the papers and make final selections for papers to be included as oral presentations in the conference program. This rigorous review process resulted in the acceptance of 57 long papers: 19 in the Content track, 18 in the Applications track, 13 in the Systems track, and 7 in the newly introduced Multimedia Interactions track. This represents an acceptance rate of 19 percent. We heartily thank the program co-chairs and the program committee members for their outstanding and dedicated work.

The short paper program received a record number of 255 submissions (a 43% increase over the previous year) and, after a thorough review process, accepted 70 papers resulting in an acceptance rate of 27 percent. These short papers will be presented during poster sessions at the conference. Many thanks to the short paper program co-chairs Chitra Dorai, Julien Laganier, and Susanne Boll for an excellent job.

3 We also wish to acknowledge and thank the co-chairs of the demonstration program, Wei-Ying Ma and Milind Naphade; the chair of the video program, Thomas Haenselmann; the co-chairs of the doctoral symposium, Thomas Plagemann and Vera Goebel; the new foundations co-chairs, Edward Chang and Shin'ichi Satoh; the open source competition chair, Apostol Natsev; and the panel co-chairs, Yap-Peng Tan and Mohan Kankanhalli. These chairs put in an enormous amount of work to bring us a diverse, high quality conference, and their contributions are much appreciated.

The Interactive Arts Program includes long and short papers as well as an exhibition that is housed at the new building site of the school of design at the University of Applied Sciences Augsburg. We are in particular grateful to the school of design, not only because we are the first that are allowed to use the new building but also as the location is nicely situated between the city centre and the conference location.

The exhibition will run throughout the conference, and we encourage all attendees while they are on their way to or from the conference to view these novel works of art utilizing a rich variety of media. The Interactive Arts Program chairs - Frank Nack, Alejandro Jaimes, and Thomas Rist - did a wonderful job, working with their exhibition curators and program committee, to put together a first-rate arts program to complement the technology focus of the main conference. The competition was high and only 16 % of the submissions made it into the exhibition. We thank the co-chairs, but in particular Thomas Rist who took the largest burden as local chair, and all those who helped to organize and run this program.

This year’s conference schedule begins with seven half-day tutorials on a wide range of topics of interest to the multimedia community, from introductory to advanced, from machine learning for multimedia to a programming course for mobile phones, adeptly organized by the tutorial co-chairs Benoit Huet and Malcolm Slaney. After the main conference, six workshops are held on the final two days. Workshop co-chairs Belle Tseng and Daniel Gatica-Perez have done a great job working with the individual workshop chairs to ensure that these run smoothly.

We also wish to acknowledge and thank the publicity co-chairs, Wolfgang Effelsberg, Yong Rui, and Alf Zugenmaier; the registration co-chairs, Yi Wu, Marc Emmelman and Eva Hörster; the treasurer, Barbara de Vega; the technical program coordinator, Chitra Dorai; and the web chairs, Benedikt Gleich and Simon Hoffmann. These colleagues all contributed tremendously to the success of the conference. The proceedings chair, Roger Zimmermann, did an outstanding job putting together these multi-faceted proceedings. Special thanks go to the local arrangements co-chairs Gregor van den Boogaart, Jochen Lux, Simon Hoffmann and Susanne Boll, who worked tirelessly to ensure that the myriad details of the conference venue were addressed, including dealing with the inevitable emergencies and surprises along the way.

Thanks to the ACM and their special interest groups, SIGMM and SIGGRAPH, for co-sponsoring this event, and to Barbara de Vega for being always available to organize and think through the many little thinks that came up during the planning of this conference. We would also like to thank our supporters: CeWe Color, FXPAL, Google, IBM, Microsoft Research, SAP, Yahoo! Research, DoCoMo Comm. Labs Europe, MAN Roland, NEC, Philips Research, Ricoh, and the University of Augsburg for providing us with the nice conference facilities in the large lecture hall building of the physics department. We also thank the University of Applied Sciences Augsburg for hosting the arts program. Their generous support made several key aspects of the conference possible, including the various prizes, student travel, and the Interactive Arts Program. IBM awarded a student travel grant which enabled more students to attend the

4 conference. In this context we would also thank Arnon Amir for his hard work as the sponsoring chairs.

Finally, we wish to thank all of the contributors in every category; the work you do is the reason this conference exists. We invite all attendees to actively participate in the week’s activities: listen, learn, discuss, debate, appreciate, suggest, encourage, enlighten, and be enlightened.

Rainer Lienhart Anand R. Prasad MM’07 General Co-chair MM’07 General Co-chair University of Augsburg, DoCoMo Comm. Labs Europe GmbH, Augsburg Munich

5

MAPS

AUGSBURG TRAM LINES

7 The map on the previous page shows the Augsburg tram lines and how they connect the various conference sites. All tram lines intersect at Königsplatz, the city’s main transportation hub. To change lines, you have to go to Königsplatz first. Also, many conference hotels are within walking distance from Königsplatz.

The most important tram line for the conference members is tram number 3, with the end points ‘Stadtbergen’ and ‘Inninger Str.’, respectively. Line 3 connects the Augsburg central train station with the University of Applied Sciences (called Fachhochschule Augsburg, location of arts exhibitions) and the campus of the University of Augsburg (the main conference site). The end point of the tram line is always being displayed on the front and sides of the tram. It tells you in which direction the tram is currently travelling. Inside the tram, the next stop is always being announced and/or displayed.

To get to either conference site from downtown Augsburg, take line 3 in direction ‘Inninger Str.’. It leaves at Königsplatz platform ‘F’ every 5 to 10 minutes, depending on the current day and time.

The live arts exhibition at the University of Applied Sciences (Fachhochschule Augsburg) is only two stops away from Königsplatz: after getting off the tram at ’Rotes Tor’, it is just a three-minute walk along ‘Rote-Torwall-Staße’” to the Fachhochschule (see separate map below).

The University campus is roughly a 10 minute ride from Königsplatz. The stop to get off the tram is called ‘Universität’. You will find yourself right at the spot marked with an ‘H’ and labeled “Straßenbahnlinie 3 – Haltestelle Universität” as shown on the map on the previous page.

To get back to downtown from either site, get on any line 3 tram towards Stadtbergen. It will arrive at Königsplatz platform ‘G’. From there, you can either walk back to your hotel (in most cases), or change tram and bus lines, or catch a taxi.

LIVE ARTS EXHIBITION (at Fachhochschule Augsburg/University of Applied Sciences, Fakultät für Informatik)

The live arts exhibition takes place in the building marked „KLM“ on the right. The tram stop “Rotes Tor” is shown to the left. Simply follow “Rote-Torwall-Str.” along the ancient city walls.

8 CONFERENCE SITE MAP

9 FLOOR PLANS

1: KEYNOTES, BEST PAPER SESSION Hörsaal 1 (HS1)

2: CONFERENCE SESSIONS, TUTORIALS, WORKSHOPS Institut für Physik – Hörsaalzentrum

1st Floor 2nd Floor

10

OVERVIEW OF THE FULL CONFERENCE PROGRAM

MONDAY, SEPTEMBER 24

Room 1003 2001 2002 2003

Tutorial: Bayesian Tutorial: Mobile Tutorial: MPEG Tutorial: Digital 08:30-10:00am Methods Phone Programming Inpainting

Tea & Coffee Break Tutorial: Bayesian Tutorial: Mobile Tutorial: MPEG Tutorial: Digital 10:30am-noon Methods Phone Programming Inpainting

Lunch Break Tutorial: Active Tutorial: Human Tutorial: Large 1:30-3:00pm Learning Centered Systems Data Methods

Tea & Coffee Break Tutorial: Active Tutorial: Human Tutorial: Large 3:30-5:00pm Learning Centered Systems Data Methods

TUESDAY, SEPTEMBER 25

Room HS1 1001 1002 1004 2001+2002 2003+Hallway other

8:30-9:00am Opening

9:00-10:00am Keynote I

Tea & Coffee Break Best 10:30am- 10:30- Paper 5:30pm: 12:30am Session Keynote I demo Lunch (Hörsaal- zentrum) 2:00-3:30pm Content 1 App. 1 Systems 1 Demos 1

Tea & Coffee Break 4:00-5:30pm Content 2 App. 2 HCI 1 Posters 1 4:00- 10:00pm: Live Arts Exhibition 6:30-7:30pm Welcome - Goldener Saal (Rathaus / City Hall) (University of Applied 7:30-10:00pm Conference Reception & Live Arts Exhibition Sciences)

11

WEDNESDAY, SEPTEMBER 26

Room HS1 1001 1002 1004 2001+2002 2003+Hallway

App. 8:30-10:00am Keynotes

Tea & Coffee Break Content 10:30am-noon App. 3 Arts 1 Demos 2 3

Lunch & ACM Business Meeting

Content Posters 2 1:30-3:00pm BNT 1 HCI 2 4 Arts Posters

Tea & Coffee Break 3:00- 7:00pm BNT 2 Systems Live Arts 3:30-5:00pm Arts 2 Posters 3 Exhibition App. 4 2 (Univ. of Applied Sciences) 7:00 - 11:00pm Conference Banquet (Kurhaus Göggingen)

THURSDAY, SEPTEMBER 27

Room HS1 1001 1002 1003 1004

9:00- 10:00am Keynote II

Tea & Coffee Break 10:30am- noon Content 5 App. 5 Arts 3 Systems 3

Lunch 1:30- Doctorial 3:00pm Content 6 Open Source Symposium Systems 4

Tea & Coffee Break 3:00- 7:00pm 3:30- Live Arts 5:00pm Panel App. 6 Video Session Exhibition

12

FRIDAY, SEPTEMBER 28

MIR 2007 - WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL September 28 - 29, 2007 Location: 1001

MV 2007 - WORKSHOP ON MOBILE VIDEO September 28, 2007 Location: 1002

TVS 2007 - TRECVID VIDEO SUMMARIZATION September 28, 2007 Location: 1004

HCM 2007 - HUMAN-CENTERED MULTIMEDIA September 28, 2007 Location: 1003

MS 2007 - THE MANY FACES OF MULTIMEDIA SEMANTICS September 28, 2007 Location: 2003

EMME 2007 - EDUCATIONAL MULTIMEDIA AND MULTIMEDIA EDUCATION September 28, 2007 Location: 2002

SATURDAY, SEPTEMBER 29

MIR 2007 WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL September 28 - 29, 2007 Location: 1001

13

Monday, September 24, 2007 HALF-DAY TUTORIALS

MONDAY, SEPTEMBER 24, 2007

8:30am - noon – Morning Tutorials

Tutorial: Bayesian Methods for Multimedia Signal Processing Location: 1003 A. Taylan Cemgil

Tutorial: Digital Inpainting Location: 2003 Timothy K. Shih

Tutorial: MPEG Multimedia Standards: Evolution and Future Developments Location: 2002 Fernando Pereira

Tutorial: Mobile Phone Programming for Multimedia Location: 2001 Jürgen Scheible

1:30 - 5:00 pm – Afternoon Tutorials

Tutorial: Active Learning for Multimedia Location: 1003 Georges M. Quénot

Tutorial: Large Data Methods for Multimedia Location: 2003 Michael A. Casey, Frank Kurth

Tutorial: Human-Centered Multimedia Systems Location: 2001 Alejandro Jaimes, Nicu Sebe

15

Tuesday, September 25, 2007 MAIN CONFERENCE FULL PROGRAM

TUESDAY, SEPTEMBER 25, 2007

8:30 - 9:00am – Conference Opening Remarks Location: HS 1 Session Chair: Anand Prasad, Rainer Lienhart

9:00 - 10:00am – Keynote Presentation Location: HS 1 Session Chair: Rainer Lienhart

SmartWeb: Multimodal Web Services on the Road Prof. Wolfgang Wahlster - DFKI

______

10:00 - 10:30am – Tea & Coffee Break (sponsored by Ricoh) Location: Hallway ______

10:30 - 12:30am – Best Paper Session Location: HS 1 Session Chair: Alan Hanjalic

Correlative Multi-Label Video Annotation Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Jinhui Tang, Tao Mei, Hong-Jiang Zhang

Re-Cinematography: Improving the Camera Dynamics of Casual Video Michael L. Gleicher, Feng Liu

Rate Allocation for Multi-User Video Streaming over Heterogeneous Access Networks Xiaoqing Zhu, Piyush Agrawal, Jatinder Pal Singh, Tansu Alpcan, Bernd Girod

Media Adaptation Framework in Biofeedback System for Stroke Patient Rehabilitation Yinpeng Chen, Weiwei Xu, Hari Sundaram, Thanassis Rikakis, Sheng-Min Liu

______

10:30am - 5:30pm – Keynote Demo Location: Outside in front of lecture hall building Session Chair: Gregor van den Boogaart

The team of Prof. Dr. Wolfgang Wahlster is demoing the concepts they he has introduced during his talk on SmartWeb: Multimodal Web Services on the Road

17 Tuesday, September 25, 2007 ______

12:30am - 2:00pm – Conference Lunch (sponsored by FXPAL) Location: Mensa ______

2:00 - 3:30pm – Content 1: Content Analysis Applications Location: 1001 Session Chair: Apostol Natsev

Trajectory Based Event Tactics Analysis in Broadcast Sports Video Guangyu Zhu, Qingming Huang, Changsheng Xu, Yong Rui, Shuqiang Jiang, Wen Gao, Hongxun Yao

A Computation Method for Video Segmentation Utilizing the Pleasure-Arousal-Dominance Emotional Information Sutjipto Arifin, Peter Y. K. Cheung

Can We Trust Digital Image Forensics? Thomas Gloe, Matthias Kirchner, Antje Winkler, Rainer Böhme

______

2:00 - 3:30pm – Applications 1: Enhancing User Experiences Location: 1002 Session Chair: Lloyd Rutledge

The Kindest Cut: Enhancing the User Experience of Mobile TV through Adequate Zooming Hendrik Knoche, Marco Papaleo, M. Angela Sasse, Allesandro Vanelli-Coralli

Multi-Scale Video Cropping Hazem El-Alfy, David Jacobs, Larry Davis

Enriching SMIL with Assertions for Temporal Validation Annalisa Bossi, Ombretta Gaggi

______

2:00 - 3:30pm – Systems 1: Streaming Location: 1004 Session Chair: Ketan Mayer-Patel

Improving VoD Server Efficiency with BitTorrent Yung Ryn Choe, Derek L. Schuff, Jagadeesh M. Dyaberi, Vijay S. Pai

On the Minimum Delay Peer-to-Peer Video Streaming: How Realtime Can It Be? Yong Liu

Playout Scheduling and Loss-Concealments in VoIP for Optimizing Conversational Voice Communication Quality Batu Sat, Benjamin W. Wah

18 Tuesday, September 25, 2007 2:00 - 3:30pm – Demo Session 1 Location: Seminar Rooms 2001 & 2002 Session Chair: Wei-Ying Ma

OLIVE - A Conceptual Web Image Search Engine Adrian Popescu, Pierre Alain Moëllic

Person-Based Search in Videos Bart Kroon, Sabri Boughorbel, Alan Hanjalic

Intelligent Browsing of Concert Videos Suphi Umut Naci, Alan Hanjalic

Atomique: A Photo Repository for Decentralized and Distributed Photo Sharing on the Web Marian Dörk, Andreas Nürnberger, Javier Velasco Martín

An Object Recognition System for Automatic Image Annotation and Browsing of Object Catalogs Michela Lecca, Stefano Messelodi, Claudio Andreatta

Demo SPP: A Demonstrator for a Scalable P2P VoD Infrastructure Piotr Srebrny, Karl-André Skevik, Vera Goebel, Thomas Plagemann

Fast Annotation of Video Objects for Interactive TV Helmut Neuschmied, Remi Trichet, Berard Merialdo

An Image-based Outdoor Place Recognition and Information Retrieval System Hanlin Goh, Yiqun Li, Joo-Hwee Lim mediaWalker: A Video Archive Explorer based on Time-Series Semantic Structure Ichiro Ide, Tomoyoshi Kinoshita, Tomokazu Takahashi, Shin'ichi Satoh, Hiroshi Murase

Statistical Summarization of Content Features for Fast Near-duplicate Video Detection Heng Tao Shen, Xiaofang Zhou, Zi Huang, Jie Shao

Logo Seeker: A System for Detecting and Matching Logos in Natural Images Subhajit Sanyal, Srinivasan H. Sengamedu

______

3:30 - 4:00pm – Tea & Coffee Break (sponsored by DoCoMo Euro-Labs) Location: Hallway ______

4:00 - 5:30pm – Content 2: Video Structuring Location: 1001 Session Chair: Alan Smeaton

Novelty Detection for Cross-Lingual News Stories with Visual Duplicates and Speech Transcripts Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo

Efficient Spatiotemporal-Attention-Driven Shot Matching Shan Li, Moon-Chuen Lee

19 Tuesday, September 25, 2007 Cross-Domain Video Concept Detection Using Adaptive SVMs Jun Yang, Rong Yan, Alexander G. Hauptmann

______

4:00 - 5:30pm – Applications 2: Browsing and Searching Video Location: 1002 Session Chair: Berna Erol

The Use of Topic Evolution to help Users Browse and Find Answers in News Video Corpus Shi-Yong Neo, Yuanyuan Ran, Hai-Kiat Goh, Yan-Tao Zheng, Tat-Seng Chua, Jintao Li

Video Search Re-Ranking via Multi-Graph Propagation Jingjing Liu, Wei Lai, Xian-Sheng Hua, Yalou Huang, Shipeng Li

Practical Elimination of Near-Duplicates from Web Video Search Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo

______

4:00 - 5:30pm – HCI 1: New Media Interaction Location: 1004 Session Chair: Nicu Sebe

Generating Views of the Buzz: Browsing Popular Media and Authoring using Mixed-Initiative Composition Eunyee Koh, Andruid Kerne, Andrew Webb, Sashikanth Damaraju, David Sturdivant

Beyond "Beyond Being There": Towards Multiscale Communication Systems Nicolas Roussel, Sofiane Gueddana

Interactive Video Browsing on Mobile Devices Wolfgang Hürst, Georg Götz, Martina Welte

______

4:00 - 5:30pm – Poster Session 1: Content Analysis Location: Hallway and Seminar Room 2003 Session Chair: Julien Laganier

Reliability-Based 3D Reconstruction in Real Environment Hansung Kim, Ryuuki Sakamoto, Itaru Kitahara, Tomoji Toriyama, Kiyoshi Kogure

Broadcast News Story Segmentation Using Social Network Analysis and Hidden Markov Models Alessandro Vinciarelli, Sarah Favre

Color Conceptualization Xiaodi Hou, Liqing Zhang

Human Behaviour Consistent Relevance Feedback Model for Image Retrieval Jing Liu, Zhiwei Li, Mingjing Li, Hanqing Lu, Songde Ma

20 Tuesday, September 25, 2007 Cross-modal Correlation Learning for Clustering on Image-Audio Dataset Hong Zhang, Yueting Zhuang, Fei Wu

Gradual Transition Detection with Conditional Random Fields Jinhui Yuan, Jianmin Li, Bo Zhang

Image Classification Using Tensor Representation Ziming Zhang, Syin Chan, Liang-Tien Chia

The Importance of Query-Concept-Mapping for Automatic Video Retrieval Dong Wang, Xirong Li, Jianmin Li, Bo Zhang

Mining Repetitive Clips through Finding Continuous Paths Junsong Yuan, Wei Wang, Jingjing Meng, Ying Wu, Dongge Li

Segregated Feedback with Performance-based Adaptive Sampling for Interactive News Video Retrieval Huan-Bo Luan, Shi-Yong Neo, Hai-Kiat Goh, Yong-Dong Zhang, Shou-Xun Lin, Tat-Seng Chua

Typicality Ranking via Semi-Supervised Multiple-Instance Learning Jinhui Tang, Xian-Sheng Hua, Guo-Jun Qi, Xiuqing Wu

Feature Selection Using Principal Feature Analysis Yijuan Lu, Ira Cohen, Xiang Zhou, Qi Tian

Region-Based Visual Attention Analysis with Its Application in Image Browsing on Small Displays Huiying Liu, Shuqiang Jiang, Qingming Huang, Changsheng Xu, Wen Gao

Singing Voice Detection using Perceptually-Motivated Features Tin Lay Nwe, Haizhou Li

Deriving Semantics for Image Clustering from Accumulated User Feedbacks Yanhua Chen, Manjeet Rege, Ming Dong, Farshad Fotouhi

Clustering Web Images with Multi-modal Features Manjeet Rege, Ming Dong, Jing Hua

Image Matting Using Linear Optimization Shifeng Chen, Zhenguo Li, Jianzhuang Liu, Xiaoou Tang

Video Annotation by Graph-Based Learning With Neighborhood Similarity Meng Wang, Tao Mei, Xun Yuan, Yan Song, Li-Rong Dai

Combining Stroke-based and Selection-based Relevance Feedback for Content-based Image Retrieval Jingyu Cui, Changshui Zhang

Temporal Feature Induction for Baseball Highlight Classification Michael Fleischman, Brandon Roy, Deb Roy

A Real-Time Augmented-Reality System for Sports Broadcast Video Enhancement Jungong Han, Dirk Farin, Peter H.N. de With

21 Tuesday, September 25, 2007 Enhancing Image Annotation by Integrating Concept Ontology and Text-based Bayesian Learning Model Rui Shi, Chin-Hui Lee, Tat-Seng Chua

Refining Video Annotation by Exploiting Pairwise Concurrent Relation Zheng-Jun Zha, Tao Mei, Xian-Sheng Hua, Guo-Jun Qi, Zengfu Wang

Multi-layer Multi-Instance Kernel for Video Concept Detection Zhiwei Gu, Tao Mei, Xian-Sheng Hua, Jinhui Tang, Xiuqing Wu

Detecting and Segmenting Humans in Crowded Scenes Mikel D. Rodriguez, Mubarak Shah

A 3-Dimensional SIFT Descriptor and its Application to Action Recognition Paul Scovanner, Saad Ali, Mubarak Shah

Zurfer: Mobile Multimedia Access in Spatial, Social and Topical Context Amy Hwang, Shane Ahern, Simon King, Mor Naaman, Rahul Nair, Jeannie Yang

______

4:00 - 10:00pm – Live Arts Exhibition Location: University of Applied Sciences Augsburg Session Chair: Thomas Rist

Amagatana – the mystical sword Yuichiro Katsumoto, Masa Inakage

The Ball in The Hole – interactive video installation Eleonora Maria Irene Oreggia, Silvano Galliani

Ghost(s) / Fantôme(s) – a participative video-data processing installation Vincent Levy miXer: The Communication Entertainment Content by using "Entrainment Phenomenon" and "Bio-Feedback" Tomohisa Tomida, Anna Ishihara, Ueki Atsuro, Yoshitaka Tomari, Kensuke Fukushima, Masa Inakage

One Million Heartbeats – an interactive art installation that collects one million heartbeats from participants Su-Chu Hsu, Jin-Yao Lin, Carven Chen, Ying-Chung Chen, Jiun-Shian Lin, Keng-Hau Chang

Space of two categories – interactive installation with shadow projection Hanna Haaslahti, Seppo Heikkilä

SpherAleas – a tridimensional interactive / sound / image installation Gregory Lasserre, Anais met den Ancxt

Conversation Piece – a speech-based interactive art installation Alexa Wright, Alf Linney, Mike Lincoln, Alun Evans

22 Tuesday, September 25, 2007 TypeTrace – an interactive application that records all the keyboard strokes you make, similar to spyware Takumi Endo

Will.0.w1sp – an interactive installation exploring our ability to recognise human motion without human form Kirk A. Woolford

______

6:30 - 10:00pm – Conference Reception (sponsored by Microsoft Research)

The conference reception will start at 6:30pm in the Golden Hall of the Town Hall, where wine and brezels will be served and the mayor of Augsburg is giving his welcome. At around 7:30pm we will walk over to the new computer science building of the University of Applied Sciences Augsburg, where the actual reception will take place while everybody can enjoy the highly creative interactive arts exhibition.

6:30 - 7:30pm – Golden Hall at the Town Hall of Augsburg

The Town Hall that was built by Elias Holl between 1615 to 1620. It is the landmark of the city and it is also said to be the most significant secular Renaissance building north of the Alps. The restored Golden Hall is famous for its magnificent, pompous portals, coffered ceiling and mural paintings. The Perlach Tower next to the Town Hall offers a spectacular panoramic view of Augsburg and is open from May to October.

7:30 - 10:00pm –Reception and Arts Exhibition Location: Unversity of Applied Science Augsburg (Fachhochschule Augsburg), Fakultät für Informatik, Friedberger Straße 2 a, 86161 Augsburg

23

Wednesday, September 26, 2007

WEDNESDAY, SEPTEMBER 26, 2007

8:30 - 10:00am – Applications Keynotes Location: HS 1 Session Chair: Arnon Amir

Applied Image Science - From Consumers' Digital Files to Tangible Products Dr. Reiner Fageth - CeWe Color

The Workplace of the Future Prof. Lutz Heuser – SAP AG ______

10:00 - 10:30am – Tea & Coffee break (sponsored by NEC) Location: Hallway ______

10:30 - noon – Content 3: Multimedia Model Learning Location: 1001 Session Chair: Hari Sundaram

Automatic Object Model Acquisition and Object Recognition by Integrating Linguistic and Visual Information Tomohide Shibata, Norio Kato, Sadao Kurohashi

Tagging over Time: Real-world Image Annotation by Lightweight Meta-learning Ritendra Datta, Dhiraj Joshi, Jia Li, James Z. Wang

Spectral Regression: A Unified Subspace Learning Framework for Content-Based Image Retrieval Deng Cai, Xiaofei He, Jiawei Han

______

10:30 - noon – Applications 3: You’re Being Watched Location: 1002 Session Chair: Karrie Karahalios

Distributed Query Processing for Mobile Surveillance Stewart Greenhill, Svetha Venkatesh

DOTS: Support for Effective Video Surveillance Andreas Girgensohn, Don Kimber, Jim Vaughan, Tao Yang, Frank Shipman, Thea Turner, Eleanor Rieffel, Lynn Wilcox, Francine Chen, Tony Dunnigan

Line Cameras for Monitoring and Surveillance Sensor Networks Jiang Yu Zheng, Shivank Sinha

25 Wednesday, September 26, 2007 10:30am - noon – Arts Session 1: Pieces in Art Location: 1004 Session Chair: Frank Nack

Annotation of Paintings with High-level Semantic Concepts using Transductive Inference and Ontology-based Concept Disambiguation Liza Leslie, Tat-Seng Chua, Ramesh Jain

Discussion: How Meta is Digital Art?

______

10:30am - noon – Demo Session 2 Location: Seminar Rooms 2001 & 2002 Session Chair: Milind Naphade

Automated Home Video Editing: a Multi-Core Solution Chengkun Xue, Liqun Li, Feng Yang, Patricia P. Wang, Tao Wang, Yimin Zhang, Yankui Sun vADeo - Video Advertising System Srinivasan H. Sengamedu, Neela Sawant, Smita Wadhwa

Information Dense Summaries for Review of Patient Performance in Biofeedback Rehabilitation Weiwei Xu, Hari Sundaram

High Definition H.264 Decoding on Cell Broadband Engine Yu Yuan, Rong Yan, Huoding Li, Xing Liu, Sheng Xu

Video Collage Xueliang Liu, Tao Mei, Xian-Sheng Hua, Bo Yang, He-Qin Zhou,

VideoSense: A Contextual Video Advertising System Tao Mei, Linjun Yang, Xian-Sheng Hua, Shipeng Li

DJ DreamFactory Jingjing Liu, Yalou Huang, Dong Li, Fanghao Wu, Bin Li

SBIA: Search-based Image Annotation by Leveraging Web-Scale Images Xirong Li, Xin-Jing Wang, Changhu Wang, Lei Zhang

M-MUSICS: Mobile Content-based Music Retrieval System Byeong-jun Han, Eenjun Hwang, Seungmin Rho, Minkoo Kim

Videntifier: Identifying Pirated Videos in Real-Time Kristleifur Dadason, Herwig Lejsek, Fridrik Ásmundsson, Björn Jónsson, Laurent Amsaleg

Unsupervised Content-based Indexing for Sports Video Retrieval Michael Fleischman, Humberto Evans, Deb Roy

Intertainment - Interactive TV Services on Mobile Devices Günther Hölbling, Tilmann Rabl, Harald Kosch

26 Wednesday, September 26, 2007 ______

Noon - 1:30pm – Conference Lunch (sponsored by SAP) Location: Mensa ______

1:30 - 3:00pm – Poster Session 2 (Arts, Content, Applications) Location: Hallway and Seminar Room 2003 Session Chair: Frank Nack

Shadow Casting for Soft and Engaging Immersion in Augmented Virtuality Artworks Christian Jacquemin, Bertrand Planes, Rami Ajaj

Hide & SEEK: Sharing Cultural Knowledge Thierry Giles, Michael Marienek, Katharine S. Willis, Jens Geelhaar

The Body as a Medium: Reassessing the Role of Kinesthetic Awareness in Interactive Applications Aaron M. Levisohn

Generation of Self-Referential Animated Photomosaic Daryl D'Souza, Vic Ciesielski, Marsha Berry, Karen Trist

Performative Surface: Double Sided Interaction Hugues Bruyère, Thierry Giles

Aesthetic Selection of Naked Genes Milos Rankovic

SMSBlogging: Blog-on-the-street Public Art Project Archana Prasad, Sean Olin Blagsvedt, Kentaro Toyama

Arrays of Water Jets as User Interfaces: Detection and Estimation of Flow by Listening to Turbulence Signatures using Hydrophones Ryan E. Janzen, Steve Mann

The Lens of Ludic Engagement: Evaluating Participation in Interactive Art Installations Ann J. Morrison, Peta Mitchell, Margot Brereton

Automatic Classification of Didactic Functions of e-Learning Resources Marek Meyer, Alexander Hannappel, Christoph Rensing, Ralf Steinmetz

Image Inpainting by Global Structure and Texture Propagation Ting Huang, Shifeng Chen, Jianzhuang Liu, Xiaoou Tang

Visual Analysis of Fingering for Pedagogical Violin Transcription Bingjun Zhang, Jia Zhu, Ye Wang, Wee Kheng Leow

Scale Adaptive Visual Attention Detection by Subspace Analysis Yiqun Hu, Deepu Rajan, Liang-Tien Chia

Tracking Multiple Speakers Using CPHD Filter Nam Trung Pham, Weimin Huang, Sim Heng Ong

27 Wednesday, September 26, 2007 Learning the Consensus on Visual Quality for Next-Generation Image Management Ritendra Datta, Jia Li, James Z. Wang

A Refined Rate Allocation Scheme with Adaptive Playback Adjustment for Robust HD Video Stream Transmission Yuanhai Zhang, Wei Huangfu, Kaihui Li, Changqiao Xu

A Web-based Aggregated Platform for User-contributed Interactive Media Broadcasting Jingjing Liu, Yalou Huang, Dong Li, Fanghao Wu, Bin Li

Synchronization of Multi-Camera Video Recordings Based on Audio Prarthana Shrestha, Mauro Barbieri, Hans Weda

Outdoor Place Recognition using Compact Local Descriptors and Multiple Queries with User Verification Yiqun Li, Joo-Hwee Lim

MusicSense: Contextual Music Recommendation using Emotional Allocation Modeling Rui Cai, Chao Zhang, Chong Wang, Lei Zhang, Wei-Ying Ma

Voice Activity Detection by Lip Shape Tracking Using EBGM Masaki Aoki, Ken Masuda, Hiroyoshi Matsuda, Tetsuya Takiguchi, Yasuo Ariki

An Online System for Gathering Image Similarity Judgements Alexei Yavlinsky, Daniel Heesch

Analysis of Usage Patterns in Experiential Multiple Perspective Web Search Rahul Singh, Ya-Wen Hsu

Empirical Study of 3D Video Source Coding for Autostereoscopic Displays Roger Cheng, Klara Nahrstedt

Video Summarization by Redundancy Removing and Content Ranking Tao Wang, Yue Gao, Patricia P. Wang, Eric Li, Wei Hu, Yimin Zhang, Junhai Yong

Improving Gaming Experience in Zonal MMOGs Dewan Ahmed, Shervin Shirmohammadi, Jauvane Oliveira

______

1:30 - 3:00pm – Content 4: Image Annotation Location: 1001 Session Chair: Dongge Li

Bipartite Graph Reinforcement Model for Web Image Annotation Xiaoguang Rui, Mingjing Li, Zhiwei Li,Wei-Ying Ma, Nenghai Yu

Exploiting Spatial Context Constraints for Automatic Image Region Annotation Jinhui Yuan, Jianmin Li, Bo Zhang

Dual Cross-Media Relevance Model for Image Annotation Jing Liu, Bin Wang, Mingjing Li, Zhiwei Li, Weiying Ma, Hanqing Lu, Songde Ma

______

28 Wednesday, September 26, 2007 1:30 - 3:00pm – Brave New Topics Session, Part 1 Location: 1002 Session Chair: Lexing Xie

Contextual Wisdom: Social Relations and Correlations for Multimedia Event Annotation Amit Zunjarwad, Hari Sundaram, Lexing Xie

Systems Challenges of Media Collectives Ketan Mayer-Patel

How Flickr Helps us Make Sense of the World: Context and Content in Community-Contributed Media Collections Lyndon Kennedy, Mor Naaman, Shane Ahern, Rahul Nair, Tye Rattenbury

______

3:30 - 4:00pm – Brave New Topics Session, Part 2

Semantics, Content, and Structure of Many for the Creation of Personal Photo Albums Susanne Boll, Ansgar Scherp, Philipp Sandhaus, Utz Westermann

______

1:30 - 3:00pm – HCI 2: Interfaces to Smart Spaces Location: 1004 Session Chair: Alejandro Jaimes

Madame Bovary on the Holodeck: Immersive Interactive Storytelling Marc Cavazza, Jean-Luc Lugrin, David Pizzi, Fred Charles

Audio-Visual Multi-Person Tracking and Identification for Smart Environments Keni Bernardin, Rainer Stiefelhagen

Privacy and the Access of Information in a Smart House Environment Simon Moncrieff, Svetha Venkatesh, Geoff West

______

3:00 - 7:00pm – Live Arts Exhibition Location: University of Applied Sciences Augsburg Session Chair: Thomas Rist

Please see page 22 for the list of artworks ______

3:00 - 3:30pm – Tea & Coffee break (sponsored by MAN Roland) Location: Hallway ______

29 Wednesday, September 26, 2007 3:30 - 5:00pm – Arts Session 2: Art Pieces Location: 1001 Session Chair: Alejandro Jaimes

The Listening Room: A Speech-based Interactive Art Installation Alexa Wright, Alf Linney, Mike Lincoln, Alun Evans

Particulate Matters: Generating Particle Flows from Human Movement Kirk A. Woolford, Carlos Guedes

Discussion: How Particle is Digital Art?

______

4:00 - 5:00pm –Applications 4: Helping End Users Location: 1002 Session Chair: Brian Bailey

Image Stabilization for 2D Barcode in Handheld Devices Chung-Hua Chu, De-Nian Yang, Ming-Syan Chen

Establishing the Utility of Non-Text Search for News Video Retrieval with Real World Users Michael G. Christel

______

3:30 - 5:00pm – Systems 2: Adaptation & Scalability Location: 1004 Session Chair: Carsten Griwodz

Improving Mobile Ad-hoc Streaming Performance through Adaptive Layer Selection With Scalable Video Coding Min Qin, Roger Zimmermann

Analysis of Waiting-Time Predictability in Scalable Media Streaming Mohammad A. Alsmirat, Musab Al-Hadrusi, Nabil J. Sarhan

An Analytical Model for Progressive Mesh Streaming Wei Cheng, Wei Tsang Ooi, Sebastien Mondet, Romulus Grigoras, Geraldine Morin

______

30 Wednesday, September 26, 2007 3:30 - 5:00pm – Poster Session 3 (Systems & Applications) Location: Hallway and Seminar Room 2003 Session Chair: Susanne Boll

An Efficient Intra Deinterlacing Algorithm with Gradient Detection and Window Matching Wonki Kim, Soonjon Jin, Jechang Jeong

Wavelet-Based Multi-View Video Coding with Full Scalability and Illumination Compensation Jens-Uwe Garbas, Ulrich Fecker, André Kaup

Energy-Aware Data Prefetching for Multi-Speed Disks in Video Servers Minseok Song

Hyperspectral Images Lossless Compression by a Novel Three-dimensional Wavelet Coding Jing Zhang, Guizhong Liu

Hierarchical Collaborative Multicast Francisco A. López-Fuentes, Eckehard Steinbach

Towards Multi-Site Collaboration in Tele-Immersive Environments Wanmin Wu, Zhenyu Yang, Klara Nahrstedt, Gregorij Kurillo, Ruzena Bajcsy

Transparent Protocol Translation for Streaming Håvard Espeland, Carl Henrik Lunde, Håkon Kvale Stensland, Carsten Griwodz, Pål Halvorsen

A Framework for Encoding and Caching Video for Quality Adaptive Progressive Download Siddhartha Chattopadhyay, Lakshmish Ramaswamy, Suchendra M. Bhandarkar

Improving the Delivery of Multimedia Embedded in Web Pages Adam Serbinski, Abdolreza Abhari

A Peer-to-Peer Architecture for Efficient Live Scalable Media Streaming on Internet Xuguang Lan, Nanning Zheng, Jianru Xue, Xiaoguang Wu, Bin Gao

A Compressed Domain Distortion Measure for Fast Video Transcoding Yicheng Huang, Vu An Tran, Ye Wang

Scalable Delivery and Pricing of Streaming Media with Advertisements Musab Al-Hadrusi, Nabil J. Sarhan

Musical Extrapolation of Speech with Auto-DJ Simon Wun, Chern-Han Yong, Ti-Eu Chan

Optimized Cache Management for Scalable Video Streaming Yongfeng Li, Kenneth Ong

Spatial Querying for Retrieval of Human Movement Patterns in Smart Environments Gamhewage C. de Silva, Toshihiko Yamasaki, Kiyoharu Aizawa

Large Head Movement Tracking Using SIFT-based Registration Gangqiang Zhao, Ling Chen, Jie Song, Gencai Chen

Query On Demand Video Browsing Ork de Rooij, Cees Snoek, Marcel Worring

31 Wednesday, September 26, 2007 Adjusting Route Panoramas with Condensed Image Slices Jiang Yu Zheng, Glenn R. Flora

A Modern Day Video Flip-Book: Creating a Printable Representation from Time-Based Media Berna Erol, Jamey Graham, Jonathan J. Hull, Peter E. Hart

Floor-Plan Reconstruction from Panoramic Images Dirk Farin, Wolfgang Effelsberg, Peter H.N. de With

Learning to Gesture: Applying Appropriate Animations to Spoken Text Nathan Nichols, Jiahui Liu, Bryan Pardo, Kristian Hammond, Larry Birnbaum

Introducing TANGerINE: a Tangible Interactive Natural Environment Stefano Baraldi, Alberto Del Bimbo, Lea Landucci, Nicola Torpei, Omar Cafini, Elisabetta Farella, Augusto Pieracci, Luca Benini

Using Audio and Video Features to Classify the Most Dominant Person in a Group Meeting Hayley Hung, Dinesh Jayagopi, Chuohao Yeo, Gerald Friedland, Sileye Ba, Jean-Marc Odobez, Kannan Ramchandran, Nikki Mirghafori, Daniel Gatica-Perez

Emotion-based Impressionism Slideshow with Automatic Music Accompaniment Cheng-Te Li, Man-Kwan Shan

Information Dense Summaries for Review of Patient Performance in Biofeedback Rehabilitation Weiwei Xu, Hari Sundaram

Color-based Clustering for Text Detection and Extraction in Images Jian Yi, Yuxin Peng, Jianguo Xiao

______

7:00 - 11:00pm – Conference Banquet (sponsored by Google and CeWe) Location: Kurhaus Göggingen, Klausenberg 6, 86199 Augsburg

The „Kurhaus“ in Göggingen was built in 1885 by Jean Keller on behalf of Friedrich von Hessing. It is an important monument of German architecture and engineering consisting of plastered brick combined with iron construction and large windows. In 1972 it was severely damaged by fire. It was re-opened in 1996 after extensive renovation. The Kurhaus in Göggingen is regarded as a jewel and unique testimony of late 19th century style. It is now used as a theater and convention facility.

32 Thursday, September 78, 2007 THURSDAY, SEPTEMBER 27, 2007

9:00 - 10:00am – Keynote Presentation II Location: HS 1 Session Chair: Anand Prasad

Insights into Future Mobile Multimedia Applications Dr. Minoru Etoh – NTT DoCoMo

______

10:00 - 10:30 – Tea & Coffee break (sponsored by SAP) Location: Hallway ______

10:30 - noon – Content 5: Video Annotation Location: 1001 Session Chair: Changsheng Xu

Structure-Sensitive Manifold Ranking for Video Concept Detection Jinhui Tang, Xian-Sheng Hua, Guo-Jun Qi, Meng Wang, Tao Mei, Xiuqing Wu

Optimizing Multi-Graph Learning: Towards A Unified Video Annotation Scheme Meng Wang, Xian-Sheng Hua, Xun Yuan, Yan Song, Li-Rong Dai

An Integrated Statistical Model for Multimedia Evidence Combination Sheng Gao, Joo-Hwee Lim, Qibin Sun

______

10:30 - noon – Applications 5: Smart Media Environments Location: 1002 Session Chair: Balakrishnan Prabhakaran

ViewCast: View Dissemination and Management for Multi-party 3D Tele-immersive Environments Zhenyu Yang, Wanmin Wu, Klara Nahrstedt, Gregorij Kurillo, Ruzena Bajcsy

Aging in Place: Fall Detection and Localization in a Distributed Smart Camera Network Adam Williams, Deepak Ganesan, Allen Hanson

Video Personalization in Resourced-Constrained Multimedia Environments Yong Wei, Suchendra M. Bhandarkar, Kang Li

______

33 Thursday, September 27, 2007 10:30 - 12:30am – Arts Session 3: Fluid Art Location: 1003 Session Chair: Frank Nack

Fluid Samplers: Sampling Music Keyboards Having Fluidly Continuous Action and Sound, without Being Electrophones Steve Mann, Ryan E. Janzen

Alternating from 1 to x and Vice Versa - An Interactive Concert-performance Homage to Alighiero Boetti Andrea Valle, Vincenzo Lombardo, Hairi Vogel

Non-Electrophonic Cyborg Instruments: Playing on Everyday Things as if the Whole World Were One Giant Musical Instrument Steve Mann, RyanE. Janzen, Raymond Lo, James Fung

Discussion: How Playful is Digital Art? ______

10:30 - noon – Systems 3: Computing Complexity Location: 1004 Session Chair: Wei Tsang Ooi

Multilevel Parallelization on the Cell/B.E. for a Motion JPEG 2000 Encoding Server Hidemasa Muta, Munehiro Doi , Hiroki Nakano, Yumi Mori

A Workload Prediction Model for Decoding MPEG Video and its Application to Workload- scalable Transcoding Yicheng Huang, An Vu Tran, Ye Wang

Dynamic Complexity Control for Real-Time H.264/AVC Video Encoding Yury Ivanov, Chris J. Bleakley

______

Noon - 1:30pm – Conf. Lunch (sponsored by Yahoo! Research) Location: Mensa ______

1:30 - 3:00pm – Content 6: Video Search Location: 1002 Session Chair: Marcel Worring

Video Search Reranking through Random Walk over Document-Level Context Graph Winston Hsu, Lyndon S. Kennedy, Shih-Fu Chang

Ontology-Enriched Semantic Space for Video Search Xiao-Yong Wei, Chong-Wah Ngo

Semantic Concept-Based Query Expansion and Re-ranking for Multimedia Retrieval Apostol Natsev, Alexander Haubold, Jelena Tesic, Lexing Xie, Rong Yan

______34 Thursday, September 78, 2007 1:30 - 3:00pm – Open Source Software Competition Location: 1002 Session Chair: Apostol Natsev

Best Open Source Software: Programming Web Multimedia Applications with Hop Manual Serrano

Advene: An Open-Source Framework for Integrating and Visualizing Audiovisual Metadata Olivier Aubert, Yannick Prié

GPAC: Open Source Multimedia Framework Jean Le Feuvre, Cyril Concolato, Jean-Claude Moissinac

Xface: Open Source Project and SMIL-Agent Scripting Language for Creating and Animating Embodied Conversational Agents Koray Balci, Elena Not, Massimo Zancanaro, Fabio Pianesi

______

1:30 - 3:00pm – Doctorial Symposium Location: 1003 Session Chair: Thomas Plagemann, Vera Goebel

Large Scale Semantic Structures for Image Retrieval Adrian Popescu

Realizing Multimedia Processes by Combining Intelligent Content and Semantic Web Services Tobias Bürger

Active Reading of Audiovisual Documents Bertrand Richard

______

1:30 - 3:00pm – Systems 4: Coding Support Location: 1004 Session Chair: Klara Nahrstedt

A Utility-Driven Framework for Loss and Encoding Aware Video Adaptation Srinivas Krishnan, Ketan Mayer-Patel

Ligne-Claire Video Encoding for Power Constrained Mobile Environments Siddhartha Chattopadhyay, Suchendra M. Bhandarkar, Kang Li

Display Pre-filtering for Multi-view Video Compression Matthias Zwicker, Sehoon Yea, Anthony Vetro, Clifton Forlines, Wojciech Matusik, Hanspeter Pfister

______

35 Thursday, September 27, 2007 3:00 - 7:00pm – Live Arts Exhibition Location: University of Applied Sciences Augsburg Session Chair: Thomas Rist

Please see page 22 for the list of artworks ______

3:00 - 3:30 – Tea & Coffee break (sponsored by CeWe Color) Location: Hallway ______

3:30 - 5:00pm – Panel Session Location: 1001 Session Chair: Tat-Seng Chua

Towards the Next Plateau – Innovative Multimedia Research beyond TRECVID

Panelists: Alan Hanjalic (Delft University of Technology, The Netherlands) Alan Smeaton (Dublin University, Ireland) John R. Smith (IBM T.J. Watson Research Center, USA) Ramesh Jain (UC Irvine, USA) Svetha Venkatesh (Curtin University, Australia) Wei-Ying Ma (Microsoft Research Asia)

______

3:30 - 5:00pm – Applications 6: Querying and Recommending Media Location: 1002 Session Chair: Vera Goebel

QueST: Querying Music Databases by Acoustic and Textual Features Bin Cui, Ling Liu, Calton Pu, Jialie Shen, Kian-Lee Tan

Scalable Music Recommendation by Search Rui Cai, Chao Zhang, Lei Zhang, Wei-Ying Ma

VideoSense - Towards Effective Online Video Advertising Tao Mei, Xian-Sheng Hua, Linjun Yang, Shipeng Li

______

3:30 - 5:00pm – Video Program Location: 1004 Session Chair: Thomas Haenselmann

New Digital Options in Geographically Distributed Dance Collaborations with TEEVE: Tele- immersive Environments for EVErybody Renata Sheppard, Wanmin Wu, Zhenyu Yang, Klara Nahrstedt, Lisa Wymore, Gregorij Kurillo, Ruzena Bajcsy, Katherine Mezur

36 Thursday, September 78, 2007 Tennis Video 2.0 : A New Framework of Sport Video Applications Jui-Hsin Lai, Shao-Yi Chien

37

Friday, September 28, 2007 WORKSHOPS

FRIDAY, SEPTEMBER 28, 2007

MIR 2007 - 9TH ACM SIGMM INTERNATIONAL WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL

Workshop organizers: James Z. Wang, Nozha Boujemaa

8:30 - 10:00am – Workshop Opening and Keynote Speech Location: 1001

Opening Remarks and Introduction of Speaker. Jia Li

Keynote Speech Michael Lesk – Rutgers University

______

10:00 - 10:20am - Coffee break Location: Hallway ______

10:20am - 12:00pm – Oral Session 1: Image Retrieval and Multimedia Modeling Location: 1001 Chair: Marco Bertini

Regularized Regression on Image Manifold for Retrieval Deng Cai et al.

Clustering Near-duplicate Images in Large Collections Jun Jie Foo

Learning Semantic Categories for 3D Model Retrieval Ryutarou Ohbuchi

Learning User Intention in Relevance Feedback using Optimization Jian Guan

Unsupervised Content-Based Indexing for Sports Video Retrieval Michael Fleischman

39 Friday, September 28, 2007 ______

12:00 - 1:30pm – Lunch break Location: Mensa ______

1:30 - 3:00pm – Poster Session 1: Multimedia Retrieval and Modeling Location: Hallway Chair: Jia Li

Effective Retrieval of Polyphonic Audio with Polyphonic Symbolic Queries Iman Suyoto, Alexandra Uitdenbogerd, Falk Scholer

Visual Language Modeling for Image Classification Lei Wu, Mingjing Li, Zhiwei Li, Wei-Ying Ma, Nenghai Yu

Optimal Decomposition of P2P Networks based on File Exchange Patterns for Multimedia Content Search & Replication Nikolaos Doulamis, Pantelis Karamolegkos, Anastasios D. Doulamis, Ioannis Nikolakopoulos

Music Similarity: Improvements of Edit-based Algorithms by Considering Music Theory Matthias Robine, Pierre Hanna, Pascal Ferraro

Sample-based Creation of Peer Summaries for Efficient Similarity Search in Scalable Peer-to- Peer Networks Soufyane El Allali, Daniel Blank, Wolfgang Müller, Andreas Henrich

Tempo Induction Algorithm in MP3 Compressed Domain Antonello D'Aguanno, Giancarlo Vercellesi

Visual and Textual Fusion for Region Retrieval from Both Bayesian Reasoning and Fuzzy Matching Aspects Rongrong Ji, Yao Hongxun

Stratified Helix Information of Medial-Axis-Points Matching for 3D Model Retrieval Ji Jia, Zheng Qin, Jiang Lu

______

1:30 - 3:00pm – Poster Session 2: Video Retrieval and Annotation Location: Hallway Chair: Jia Li

Exploiting Redundancy in Cross-Channel Video Retrieval Bouke Huurnink, Maarten de Rijke

Adapting Appearance Models of Semantic Concepts to Particular Videos via Transductive Learning Ralph Ewerth, Bernd Freisleben

Evaluating Bag-of-Visual-Words Representations in Scene Classification Jun Yang, Yu-Gang Jiang, Alexander Hauptmann, Chong-Wah Ngo

40 Friday, September 28, 2007 Searching For Repeated Video Sequences Tolga Can, Pinar Duygulu

TV Ad Video Categorization with Probabilistic Latent Concept Learning Jinqiao Wang, Ling-Yu Duan, Lei Xu, Hanqing Lu, Jesse Jin

Building a Comprehensive Ontology To Refine Video Concept Detection Zheng-Jun Zha, Tao Mei, Zengfu Wang, Xian-Sheng Hua

Scene Duplicate Detection from Videos Based on Trajectories of Feature Points Shin'ichi Satoh

______

3:00 - 3:30pm – Coffee break Location: Hallway ______

3:30 - 5:30pm – Special Session 1: Semantic Indexing of Consumer and Web Videos Location: 1001 Chair: Shih-Fu Chang

Kodak Consumer Video Benchmark Data Set: Concept Definition and Annotation Alexander C. Loui, Jiebo Luo, Shih-Fu Chang, Dan Ellis, Wei Jiang, Lyndon Kennedy, Keansub Lee, Akira Yanagawa

Large-Scale Multimodal Semantic Concept Detection for Consumer Video Shih-Fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Alexander C. Loui, Jiebo Luo

Multi-Modal Web Video Categorization Linjun Yang, Jiemin Liu, Tao Mei, Xiaokang Yang, Xian-Sheng Hua

Watch What I Watch: Using Community Activity To Understand Content David A. Shamma, Ryan Shaw, Peter L. Shafton, Yiming Liu

Learning People Annotation from the Web via Consistency Learning Jay Yagnik, Atiq Islam

ITEMS: Intelligent Travel Experience Management System Chih-Chieh Liu, Chun-Hsiang Huang, Wei-Ta Chu, Ja-Ling Wu

41

Friday, September 28, 2007

MV 2007- WORKSHOP ON MOBILE VIDEO 2007

Workshop organizers: Chang Wen Chen, Eckehard Steinbach

8:30 - 9:30am – Invited Plenary Talk 1 Location: 1002

Advances in Wireless Video Delivery Minoru Eto – NTT DoCoMo Research Laboratories, Japan

______

9:30 - 10:30am – Session 1: Industrial Perspectives on Mobile Video Location: 1002 Session Chair: Chang Wen Chen

Mobile Video Applications and Standards Ye-Kui Wang, Imed Bouazizi, Miska Hannuksela, Igor Curcio

On Practical Crosslayer Aspects in 3GPP Video Services Thomas Stockhammer, Günther Liebl

The OMA BCAST Standard for Bearer-Independent Mobile TV Services Frank Hartung, Markus Kampmann, Thomas Rusert

______

10:30 - 10:50am – Coffee Break Location: Hallway ______

10:50 - 11:50am – Invited Plenary Talk 2 Location: 1002

Mobile and Media Experiences and Technologies Susie Wee – HP Labs, USA

______

11:50am - 1:00pm – Lunch Break Location: Mensa ______

1:00 - 1:30pm – Workshop Sponsor Presentation Location: 1002 Christophe Beaugeant – Nokia Siemens Networks, Germany

43 Friday, September 28, 2007 1:30 - 2:50pm – Session 2: Error-Robust Mobile Video Location: 1002 Session Chair: Eckehard Steinbach

Raptor network video coding Nikoloas Thomos, Pascal Frossard

Bit-error Resilient Packetization for Streaming H.264/AVC Video Jari Korhonen, Pascal Frossard

Quality Assessment Metrics vs. PSNR under Packet Loss Scenarios in MANET Wireless Networks Miguel Martínez-Rach, Othoniel López Granado, Pablo Piñol Peral, Manuel Malumbres, Jose Oliver, Carlos Calafate

Multiple Description H.264 Video Coding with Redundant Pictures Ivana Radulovic, Pascal Frossard, Ye-Kui Wang, Stephan Wenger, Antti Hallapuro, Miska Hannuksela

______

2:50 - 3:50pm – Invited Plenary Talk 3 Location: 1002

Mobile Video Transmission Thomas Wiegand – Heinrich-Hertz-Institut, Germany

______

3:50 - 4:10pm – Coffee Break Location: Hallway ______

4:10 - 5:10pm – Session 3: Scalable Video and Rate Adaptation Location: 1002 Session Chair: Susie Wee

Optimized Scalable Video Transmission Based on Conditional Replenishment of JPEG2000 Code- blocks with Motion Compensation Aous Naman, David Taubman

Discardable Data Adaptation in Scalable Video Coding Yi Guo, Ye-Kui Wang, Miska Hannuksela, Houqiang Li

A Smoothed, Minimum Distortion-Variance Rate Control Algorithm for Multiplexed Transcoded Video Sequences Giuseppe Valenzise, Marco Tagliasacchi, Stefano Tubaro

44 Friday, September 28, 2007 5:10 - 5:50pm – Session 4: Applications Location: 1002 Session Chair: Thomas Wiegand

Ball Appearance Improvement in Low-Resolution Soccer Videos Martin Wrulich, Olivia Nemethova, Luca Superiori, Markus Rupp

Mobile Video Surveillance with Low-Bandwidth Low-Latency Video Streaming Giovanni Gualdi, Rita Cucchiara, Andrea Prati

______

5:50 - 6:00pm – Closing Location: 1002

45

Friday, September 28, 2007

TVS 2007 - TRECVID VIDEO SUMMARIZATION

Workshop organizers: Paul Over, Alan F. Smeaton

8:30 - 10:00am Location: 1004

The TRECVID 2007 BBC Rushes Summarization Evaluation Pilot Paul Over, Alan F. Smeaton, Philip Kelly, Richard Wright

Rushes Video Summarization by Object and Event Understanding Feng Wang, Chong-Wah Ngo

Rushes Summarization by Adaptive Acceleration and Stacking of Shots Marcin Detyniecki, Christophe Marsala

______

10:00 – 10:30am – Coffee Break Location: Hallway ______

10:30 – 11:50am Location: 1004

Feature Fusion and Redundancy Pruning for Rush Video Summarization Jim Kleban, Anindya Sarkar, Emily Moxley, Stephen Mangiat, Swapna Joshi, Thomas Kuo, B.S. Manjunath

Video Summarization Preserving Dynamic Content Francine Chen, Matthew Cooper, John Adcock

Generating Comprehensible Summaries of Rushes Sequences based on Robust Feature Matching Ba Tu Truong, Svetha Venkatesh

Skimming Rushes Video Using Retake Detection Werner Bailer, Felix Lee, Georg Thallinger

______

Noon - 1:30pm – Lunch Break Location: Mensa ______

47 Friday, September 28, 2007 1:30 - 2:45pm – Combined Poster & Demo session Location: 2001

Video Summarization at Brno University of Technology Vítězslav Beran, Michal Hradiš, Adam Herout, Stanislav Sumec, Igor Potúček, Pavel Zemčík, Josef Mlích, Aleš Láník, Petr Chmelař

Clever Clustering vs. Simple Speed-Up for Summarizing BBC Rushes Alexander G. Hauptmann, Michael G. Christel, Wei-Hao Lin, Bryan Maher, Jun Yang, Robert V. Baron, Guang Xiang

A User-Centered Approach to Rushes Summarization via Highlight-Detected Keyframes Daragh Byrne, Peter Kehoe, Hyowon Lee, Ciarán O'Connaire, Alan F. Smeaton, Noel E. O'Connor, Gareth J.F. Jones

Split-Screen Dynamically Accelerated Video Summaries Emilie Dumont, Bernard Merialdo

Rushes Summarization with Self-Organizing Maps Markus Koskela, Mats Sjöberg, Jorma Laaksonen

National Institute of Informatics, Japan at TRECVID 2007: BBC Rushes Summarization Duy-Dinh Le, Shin'ichi Satoh

NTU TRECVID-2007 Fast Rushes Summarization System Chen-Ming Pan, Yung-Yu Chuang, Winston H. Hsu

THU-ICRC at Rush Summarisation of TRECVID 2007 Tao Wang, Yue Gao, Jianguo Li, Patricia P. Wang, Xiaofeng Tong, Wei Hu, Yimin Zhang, Jianmin Li

The Hong Kong Polytechnic University at TRECVID 2007 BBC Rushes Summarization Yang Liu, Yan Liu, Yan Zhang

Attention-based Video Summarization in Rushes Collection Reede Ren, P.Punitha, Joemon Jose

On-line Video Skimming Based on Histogram Similarity Víctor Valdés, José M. Martínez

______

2:45 - 3:30pm – Coffee Break Location: Hallway ______

3:30 - 4:30pm – Plenary discussion Location: 1004

Discussion on lessons learned, plans for 2008

48 Friday, September 28, 2007

HCM 2007- HUMAN-CENTERED MULTIMEDIA

Workshop organizers: Alex Jaimes, Nicu Sebe

8:50 - 10:00am – Workshop Opening and Keynote Presentation Location: 1003 ______

10:00 - 10:30am – Coffee Break Location: Hallway ______

10:30 - 12:10pm – Session 1 Location: 1003 Session Chair: Nicu Sebe

Pillows as Adaptive Interfaces in Ambient Environments Frank Nack, Thecla Schiphorst, Zeljko Obrenovic, Michiel KauwATjoe, Simon de Bakker, Lora Aroyo

Music Emotion Recognition: The Role of Individuality Yi-Hsuan Yang, Ya-Fan Su, Yu-Ching Lin, Homer Chen

3D Tracking of Pointing Gesture for Wearable Visual Interfaces Yunde Jia

Affective Multimodal Mirror: Sensing and Eliciting Laughter Willem Melder, Khiet Truong, Mark Neerincx, David Van Leeuwen

______

12:10 - 1:30pm – Lunch Break Location: Mensa ______

1:30 - 3:10pm – Session 2 Location: 1003 Session Chair: Alex Jaimes

Towards Open Source Authoring and Presentation of Multimedia Content Nikitas Sgouros, Alexandros Margaritis

Preattentive Visualization of Information Relevance Matthias Deller, Achim Ebert, Michael Bender, Stefan Agne, Henning Barthel

Local Spatiotemporal Descriptors for Visual Recognition of Spoken Phrases Guoying Zhao, Matti Pietikäinen, Abdenour Hadid

Interconnected Media for Human-Centered Understanding Katja Einsfeld

49 Friday, September 28, 2007 ______

3:10 - 3:40pm – Coffee Break Location: Hallway ______

3:40 - 4:55pm – Session 3 Location: 1003 Session Chair: Daniel Gatica-Perez

Multimedia and human-in-the-loop: Interaction as content enrichment Bruno Emond

Too Close for Comfort? Adapting to the User's Cultural Background Matthias Rehm

Human Support Improvements by Natural Man-Machine Collaboration Motoyuki Ozeki

______

4:55 - 5:45pm – Panel Session Location: 1003

50 Friday, September 28, 2007

MS 2007 - THE MANY FACES OF MULTIMEDIA SEMANTICS

Workshop organizers: William Grosky, Farshad Fotouhi, Peter Stanchev

8:30 - 10:00am – Session 1: The Semantics of Semantics Location: 2003 Session Chair: William I. Grosky

Invited Keynote Talk: Realizing the Relationship Web: Morphing Information Access on the Web from Today’s Document and Entity-Centric Paradigm to a Relationship-Centric Paradigm Amit Sheth – Wright State University, USA

Contributed Talk: Towards an Ecosystem for Semantics Ansgar Scherp, Ramesh Jain

______

10:00 - 10:30 am – Coffee Break Location: Hallway ______

10:30am- 12:00 – Session 2: Annotation Location: 2003 Session Chair: Amit Sheth

An Efficient Manual Image Annotation Approach based on Tagging and Browsing Rong Yan, Apostol Natsev, Murray Campbell

Automatic Metadata Extraction and Indexing for Reusing e-Learning Multimedia Objects Paolo Bolettieri, Fabrizio Falchi, Claudio Gennaro, Fausto Rabitti

The Use of Semantic-based Predicates Implication to Improve Horizontal Multimedia Database Fragmentation Richard Chbeir, Fekade Getahun, Joe Tekli, Solomon Atnafu

______

12:00 - 1:30pm – Lunch break Location: Mensa ______

1:30 - 3:00pm – Session 3: Semantics of Video Location: 2003 Session Chair: Farshad Fotouhi

Learning Ontology for Personalized Video Retrieval Hiranmay Ghosh, P Poornachander, Anupama Mallik, Santanu Chaudhury

51 Friday, September 28, 2007 Dynamic Pictorial Ontologies for Video Digital Libraries Annotation and Retrieval Marco Bertini, Alberto Del Bimbo, Carlo Torniai, Rita Cucchiara, Costantino Grana

Fast Unsupervised Alignment of Video and Text for Indexing/Names and Faces Subhransu Maji, Ruzena Bajcsy

______

3:00 - 3:30pm – Coffee Break Location: Hallway ______

3:30 - 5:00 pm – Session 4: Emerging Applications Location: 2003 Session Chair: Peter Stanchev

Semantic Similarity based Trust Computation in Websites Hicham Ibrahim, Pradeep Atrey, Abdulmotaleb El Saddik

A Digital Rights Aware Similarity Measure for Multimedia Documents Fabrizio Falchi, Nicola Orio, Walter Allasia, Francesco Gallo

A Distributed Data Space for Music-Related Information Yves Raimond, Christopher Sutton, Mark Sandler

52 Friday, September 28, 2007

EMME 2007- EDUCATIONAL MULTIMEDIA AND MULTIMEDIA EDUCATION

Workshop organizers: Gerald Friedland, Wolfgang Hürst, Lars Knipping

8:30 - 10:00am – Opening Session Location: 2002

Opening and welcome address, workshop introduction, and some notes on the past, the present, and the potential future of educational multimedia systems Gerald Friedland, Wolfgang Hürst, Lars Knipping

Effective Use of Multimedia for Computer-Assisted Musical Instrument Tutoring Graham Percival, Ye Wang, George Tzanetakis

______

10:00 - 10:30am – Coffee break Location: Hallway ______

10:30 - 12:30pm –Session “Educational Multimedia”, Part 1 Location: 2002

Categorization of Educational Presentation Systems Georg Turban

An Automatic Cameraman in a Lecture Recording System Fleming Lampi, Stephan Kopf, Manuel Benz, Wolfgang Effelsberg

Towards an Automatic Semantic Annotation for Multimedia Learning Objects Stephan Repp, Serge Linckels, Christoph Meinel

A Web-Based Group Decision Support System for the Selection and Evaluation of Educational Multimedia Mohammed Abdelhakim, Shervin Shirmohammadi

______

12:30 - 1:30pm – Lunch break Location: Mensa ______

53 Friday, September 28, 2007 1:30 - 3:00pm –Session “Educational Multimedia”, Part 2 Location: 2002

Interaction and Reflection via 3D Path Shape Qualities in a Mediated Constructive Learning Environment Kai Tu, Harvey Thornburg, Ellen Campana, David Birchfield, Matthew Fulmer, Andreas Spanias

Adapting Handwriting Recognition for Applications in Algebra Learning Lisa Anthony, Jie Yang, Kenneth Koedinger

Educational Violin Transcription by Fusing Multimedia Streams Ye Wang, Bingjun Zhang, Olaf Schleusing

______

3:00 - 4:00pm – Poster and Demo Session (& coffee break from 3:00 - 3:30pm) Location: hallway (posters) + 2001 (demonstrations)

Posters:

Introducing Wireless Networking Technologies as a Teaching Tool for Foreign Languages: a Multimedia Laboratory Experiment Frank Favier, John Fynn, Michel Misson

Authoring Educational Multimedia Content Using Learning Styles and Story Telling Principles Nalin Sharda

Haptic Multimedia Handwriting Learning System Mohamad Eid, Rosa Iglesias, Mohamed Mansour, Abdulmotaleb El Saddik

Information Extraction from Mathematical Texts by Means of Natural Language Processing Techniques Sabina Jeschke, Nicole Natho, Olivier Pfeiffer, Marc Wilke

A Framework for the Development of Educational Presentation Systems and Its Application Georg Turban, Max Mühlhäuser

Demonstrations:

Active-Smoothing in Digital Ink Environments Khaireel A. Mohamed, Thomas Ottmann

A Low-Cost Mobile Pointing and Drawing Device Kristian Jantz, Gerald Friedland, Lars Knipping, Raul Rojas

Audio-based Methods for Navigation and Browsing Educational Multimedia Documents Tobias Lauer, Wolfgang Hürst

Adapting Handwriting Recognition for Applications in Algebra Learning (Demonstration related to the according presentation in Session 2) Lisa Anthony, Jie Yang, Kenneth Koedinger

54 Friday, September 28, 2007 4:00 - 5:30pm –Session “Multimedia Education” Location: 2002

Creating Innovative New Media Programs: Need, Challenges, and Development Framework Nalin Sharda

Panel Discussion: The Future of Multimedia Education

Panelists: Susanne Boll (University of Oldenburg, Germany) Ramesh Jain (UC Irvine, USA) Max Mühlhäuser (Darmstadt University of Technology, Germany) Timothy K. Shih (Tamkang University, Taiwan)

______

5:30 - 6:00pm – Closing Remarks Location: 2002

55

Saturday, September 29, 2007

SATURDAY, SEPTEMBER 29, 2007

MIR 2007 - 9TH ACM SIGMM INTERNATIONAL WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL

Workshop organizers: James Z. Wang, Nozha Boujemaa

8:30 - 10:00am – Keynote Presentation Location: 1001

Opening remarks and introduction of speaker Alberto del Bimbo

Keynote Speech Arnold Smeulders – University of Amsterdam, The Netherlands

______

10:00 - 10:20am – Coffee break Location: Hallway ______

10:20am - noon – Oral Session 2: Video Retrieval Location: 1001 Chair: Jiebo Luo

Video Diver: Generic Video Indexing with Diverse Features Dong Wang, Xiaobing Liu

Combining Multimodal Preferences for Multimedia Information Retrieval Eric Bruno, Jana Kludas, Stephane Marchand-Maillet

Trademark Matching and Retrieval in Sports Video Databases Andrew Bagdanov, Lamberto Ballan, Marco Bertini, Alberto Del Bimbo

RoleNet: Treat a Movie as a Small Society Chung-Yi Weng, Wei-Ta Chu, Ja-Ling Wu

Semantic-Event Based Analysis and Segmentation of Wedding Ceremony Videos Wen-Huang Cheng, Yung-Yu Chuang, Bing-Yu Chen, Ja-Ling Wu, Shao-Yen Fang, Yin-Tzu Lin, Chi- Chang Hsieh, Chen-Ming Pan, Wei-Ta Chu, Min-Chun Tien

______

Noon - 1:30pm – Lunch Break Location: Hallway ______

57 Saturday,September 29, 2007 1:30 - 3:00pm – Panel Session: New Challenges in Multimedia Research for the Increasingly Connected and Fast Growing Digital Society Location: 1001 Chair: Jia Li

Panelists: Shih-fu Chang (Columbia University, USA) Michael Lesk (Rutgers University, USA) Rainer Lienhart (University of Augsburg, Germany) Jiebo Luo (Eastman Kodak Research, USA) Arnold Smeulders (University of Amsterdam, The Netherlands)

______

3:00 - 3:30pm – Coffee break Location: Hallway ______

3:30 - 5:00pm – Special Session 2: Personalized Multimedia Information Retrieval Location: 1001 Chair: Nicu Sebe

Personalized Multimedia Retrieval: The New Trend? Nicu Sebe, Qi Tian

Browsing Visual Collections Using Graphs Marcel Worring, Ork de Rooij, Ton van Rijn

Personalized Retrieval of Sports Video Yifan Zhang, Xiaoyu Zhang, Changsheng Xu, Hanqing Lu

Evaluating the Implicit Feedback Models for Adaptive Video Retrieval Frank Hopfgartner, Joemon Jose

58

CO-SPONSORS

SUPPORTERS

59

CONFERENCE ORGANIZATION

General Chairs: Anand R. Prasad (DoCoMo Euro-Labs, Germany) Rainer Lienhart (University of Augsburg, Germany)

Technical Program Coordinator: Chitra Dorai (IBM T.J. Watson Research Center, USA)

Program Chairs: Multimedia Content Alan Hanjalic (Delft University of Technology, The Netherlands) Multimedia Systems Sunghyun Choi (Seoul National University, South Korea) Multimedia Applications Brian Bailey (University of Illinois at Urbana-Champaign, USA) Multimedia Interaction Nicu Sebe (University of Amsterdam, The Netherlands)

Short Paper Chairs: Multimedia Content Chitra Dorai (IBM T.J. Watson Research Center, USA) Multimedia Systems Julien Laganier (DoCoMo Euro-Labs, Germany) Multimedia Applications Susanne Boll (University of Oldenburg, Germany)

Workshop Paper Chairs: Belle Tseng (NEC Labs America, USA) Daniel Gatica-Perez (IDIAP Research Institute, Switzerland)

Tutorial Chairs: Benoit Huet (Eurecom, France) Malcolm Slaney (Yahoo! Research, USA)

Publicity Chairs: Wolfgang Effelsberg (University Mannheim, Germany) Yong Rui (Microsoft Research, USA) Alf Zugenmaier (DoCoMo Euro-Labs, Germany)

Demonstration Chairs: Milind Naphade (IBM T.J. Watson Research Center, USA) Wei-Ying Ma (Microsoft Research, Asia, P.R. China)

Doctorial Symposium Chairs: Thomas Plagemann (University of Oslo, Norway) Vera Goebel (University of Oslo, Norway)

Panels Chairs: Yap-Peng Tan (Nanyang Technological University, Singapore) Mohan S Kankanhalli (National University of Singapore, Singapore)

Interactive Art Program Frank Nack (University Claude Bernard Lyon 1, France) Chairs: Thomas Rist (Augsburg University of Applied Sciences, Germany) Alejandro Jaimes (IDIAP Research Institute, Switzerland)

61

Video Program Chair: Thomas Haenselmann (University of Mannheim, Germany)

Brave New Topics Chairs: Edward Chang (Google Research, P.R. China) Shin'ichi Satoh (National Institute of Informatics, Japan)

Open Source Competition Chair: Apostol Natsev (IBM T.J. Watson Research Center, USA)

Proceedings Chair: Roger Zimmermann (National University of Singapore, Singapore)

Registration Chairs: Yi Wu (Intel Research, USA) Marc Emmelmann (Technical University Berlin, Germany) Eva Hörster (University of Augsburg, Germany)

Treasurer: Barbara de Vega (University of Augsburg, Germany)

Sponsoring Chair: Arnon Amir (IBM Almaden Research Center, USA)

Travel Grant Committee: Chair: Chitra Dorai (IBM T.J. Watson Research Center, USA) David Gotz (IBM T.J. Watson Research Center, USA) Zhenghua Fu (IBM T.J. Watson Research Center, USA)

Local Arrangements Chairs: Gregor van den Boogaart (University of Augsburg, Germany) Jochen Lux (University of Augsburg, Germany) Simon Hoffmann (University of Augsburg, Germany) Susanne Boll (University of Oldenburg, Germany)

Web Site Chairs: Simon Hoffmann (University of Augsburg, Germany) Benedikt Gleich (University of Augsburg, Germany)

ACM SIGMM Director of Nevenka Dimitrova (Philips Research, USA) Conferences

ACM SIGMM Chair: Ramesh Jain (University of California, Irvine, USA)

Technical Program Committee Multimedia Content: (Full Papers): Chair: Alan Hanjalic (Delft University of Technology, The Netherlands) Kiyoharu Aizawa (University of Tokyo, Japan) Noboru Babaguchi (Osaka University, Japan) Edward Chang (University of California, Santa Barbara, USA) Liang-Tien Chia (Nanyang Technological University, Singapore) Tat-Seng Chua (National University of Singapore, Singapore) Ajay Divakaran (MERL, USA) Chitra Dorai (IBM T.J. Watson Research Center, USA) Abdulmotaleb El Saddik (University of Ottawa, Canada) Daniel Ellis (Columbia University, USA) Yihong Gong (NEC Labs America, USA) William Grosky (University of Michigan, USA) Alexander Hauptmann (Carnegie Mellon University, USA)

62

Xian-Sheng Hua (Microsoft Research Asia, P.R. China) Horace Ip (City University of Hong Kong, Hong Kong) Mohan S Kankanhalli (National University of Singapore, Singapore) John Kender (Columbia University, USA) Irwin King (The Chinese University of Hong Kong, Hong Kong) Anil Kokaram (Trinity College Dublin, Ireland) Michael Lew (Leiden University, The Netherlands) Dongge Li (Motorola Laboratories, USA) Mark Liao (Academia Sinica, Taiwan) Lie Lu (Microsoft Research Asia, P.R. China) Jiebo Luo (Eastman Kodak Company, USA) Wei-Ying Ma (Microsoft Research Asia, P.R. China) Stephane Marchand-Maillet (University of Geneva, Switzerland) Nasir Memon (Polytechnic University, USA) Bernard Merialdo (Eurecom, France) Apostol Natsev (IBM T.J. Watson Research Center, USA) Chong-Wah Ngo (City University of Hong Kong, Hong Kong) Noel O'Connor (Dublin City University, Ireland) Fernando Pereira (IST-TUL, Portugal) Gopal Pingali (IBM T.J. Watson Research Center, USA) Yong Rui (Microsoft Research, USA) Shin'ichi Satoh (National Institute of Informatics, Japan) Bo Shen (Hewlett-Packard Laboratories, USA) Alan Smeaton (Dublin City University, Ireland) John R. Smith (IBM T.J. Watson Research Center, USA) Hari Sundaram (Arizona State University, USA) Qi Tian (University of Texas at San Antonio, USA) Svetha Venkatesh (Curtin University of Technology, Australia) Lynn Wilcox (FX Palo Alto Laboratory, USA) Marcel Worring (University of Amsterdam, Netherlands) Changsheng Xu (I2R, Singapore) Cha Zhang (Microsoft Research, USA)

Multimedia Systems: Chair: Sunghyun Choi (Seoul National University, South Korea) Kevin Almeroth (University of California, Santa Barbara, USA) Surendar Chandra (University of Notre Dame, USA) Ming-Syan Chen (National Taiwan University, Taiwan) Mark Claypool (Worcester Polytechnic Institute, USA) Pedro Cuenca (University of Castilla-La Mancha, Spain) Alberto Del Bimbo (University of Firenze, Italy) Wu-chang Feng (Portland State University, USA) Wu-chi Feng (Portland State University, USA) David Gotz (IBM T.J. Watson Research Center, USA) Carsten Griwodz (University of Oslo, Norway) Yoshihiro Kawahara (The University of Tokyo, Japan) Jong Won Kim (Gwangju Institute of Science & Technology, Korea) Taekyoung Kwon (Seoul National University, Korea)

63

Baochun Li (University of Toronto, Canada) Laurent Mathy (Lancaster University, UK) Andreas U. Mauthe (Lancaster University, UK) Ketan Mayer-Patel (University of North Carolina at Chapel Hill, USA) Sue Moon (KAIST, Korea) Liam Murphy (University College Dublin, Ireland) Klara Nahrstedt (University of Illinois at Urbana-Champaign, USA) Wei Tsang Ooi (National University of Singapore, Singapore) Balakrishnan Prabhakaran (University of Texas at Dallas, USA) Hayder Radha (Michigan State University, USA) Reza Rejaie (University of Oregon, USA) Keith W. Ross (Brooklyn Polytech, USA) Prashant Shenoy (University of Massachusetts, USA) Shervin Shirmohammadi (University of Ottawa, Canada) Hwangjun Song (Pohang University of Science and Technology, Korea) Michael Vernick (Avaya Labs Research, USA) Michael Zink (University of Massachusetts, USA)

Multimedia Applications: Chair: Brian Bailey (University of Illinois at Urbana-Champaign, USA) Brett Adams (Curtin University of Technology, Australia) John Adcock (FX Palo Alto Laboratory, USA) Elisabeth André (University of Augsburg, Germany) Yasuo Ariki (Kobe University, Japan) Frank Bentley (Motorola Laboratories, USA) Dick Bulterman (CWI, The Netherlands) Andrea Cavallaro (Queen Mary, University of London, UK) Ee-Chien Chang (National University of Singapore, Singapore) Elaine Chew (University of Southern California, USA) Matthew Cooper (FX Palo Alto Laboratory, USA) Berna Erol (Ricoh California Research Center, USA) Jianping Fan (University of North Carolina at Charlotte, USA) Anthony Fang (National University of Singapore, Singapore) Jim Gemmell (Microsoft Research, USA) David Gerhard (University of Regina, Canada) Vera Goebel (University of Oslo, Norway) Forouzan Golshani (Wright State University, USA) Thomas Haenselmann (University of Mannheim, Germany) Karrie Karahalios (University of Illinois at Urbana-Champaign, USA) Wei Lai (Microsoft Research Asia, P.R. China) Peiya Liu (Siemens Corporate Research, USA) Shivajit Mohapatra (Motorola Laboratories, USA) Mor Naaman (Yahoo! Research Berkeley, USA) Balakrishnan Prabhakaran (University of Texas at Dallas, USA) Nicolas Roussel (LRI & INRIA Futurs, France) Lloyd Rutledge (CWI, The Netherlands) Andreas Schrader (University of Luebeck, Germany) Timothy Shih (Tamkang University, Taiwan)

64

Zhen Wen (IBM T. J. Watson Research Center, USA) Andy Wilson (Microsoft Research, USA) Jiang-Yu Zheng (Indiana University, USA) Michelle Zhou (IBM T. J. Watson Research Center, USA)

Multimedia Interaction: Chair: Nicu Sebe (University of Amsterdam, The Netherlands) Antonis Argyros (University of Crete, Greece) Barbara Barry (MIT Media Lab, USA) Erhardt Barth (University of Lübeck, Germany) Paulo Barthelmess (Adapx, USA) Susanne Boll (University of Oldenburg, Germany) Herve Bourlard (IDIAP Research Institute, Switzerland) Ira Cohen (Hewlett-Packard Laboratories, USA) David Demirdjian (MIT, USA) Andreas Dengel (DFKI, Germany) Ahmed Elgammal (Rutgers University, USA) Daniel Gatica-Perez (IDIAP Research Institute, Switzerland) Alejandro Jaimes (IDIAP Research Institute, Switzerland) Ashish Kapoor (Microsoft Research, USA) Andruid Kerne (Texas A&M University, College Station, USA) Michael Lyons (Ritsumeikan University, Japan) Frank Nack (University Claude Bernard Lyon 1, France) Jean-Marc Odobez (IDIAP Research Institute, Switzerland) Kazuhiro Otsuka (NTT, Japan) Maja Pantic (Imperial College, UK) Montse Pardas (Technical University of Catalonia, Spain) Ioannis Patras (Queen Mary, University of London, UK) Vladimir Pavlovic (Rutgers University, USA) Catherine Pelechaud (University of Paris 8, France) Gerasimos Potamianos (IBM T. J. Watson Research Center, USA) Patrick Schmitz (University of California, Berkeley, USA) Rainer Stiefelhagen (University of Karlsruhe, Germany) Matthew Turk (University of California, Santa Barbara, USA) Gerd Westermann (SEraja Technologies, Germany) Jie Yang (Carnegie Mellon University, USA) Ming-Hsuan Yang (Honda Research, USA) Massimo Zancanaro (ITC-irst, Italy)

Additional Reviewers for Full Papers: Golam Ashraf (National University of Singapore, Singapore) Pradeep Atrey (University of Ottawa, Canada) Brian Bailey (University of Illinois, USA) Nikolaos Boulgouris (KCL, UK) Rui Cai (Microsoft Research Asia, P.R. China) David Chatting (British Telecom, UK) Trista Chen (FX Palo Alto Laboratory, USA) Ivan Damnjanovic (Queen Mary, University of London, UK)

65

Christophe De Vleeschouwer (Universite Catholique de Louvain, Belgium) Alexandre François (University of Southern California, USA) Andreas Girgensohn (FX Palo Alto Laboratory, USA) Arthur Goshtasby (Wright State University, USA) Karrie Karahalios (University of Illinois, Urbana Champaign, USA) Jayashree Karlekar (National University of Singapore, Singapore) Thomas Kieninger (DFKI GmbH, Germany) Don Kimber (FX Palo Alto Laboratory, USA) Zhiwei Li (Microsoft Research Asia, P.R. China) Chi Wan Lim (Insitute of High Performance Computing, Singapore) Kok-Lim Low (National University of Singapore, Singapore) Emilio Maggio (Queen Mary University of London, UK) Marta Mrak (Queen Mary University of London, UK) Son Nguyen (National University of Singapore, Singapore) Yong Pei (Wright State University, USA) Guojun Qi (Microsoft Research Asia, P.R. China) Tye Rattenbury (University of California, Berkeley, USA) Ansgar Scherp (Oldenburg R&D Institute for Information Technology Tools and Systems (OFFIS), Germany) David Shamma (Yahoo! Research Berkeley, USA) Olivier Steiger (ABB, Switzerland) Thang Truong (National University of Singapore, Singapore) Changhu Wang (University of Science and Technology of China, P.R. China) Xin-Jing Wang (Microsoft Research Asia, P.R. China) John Winn (Microsoft Research Cambridge, UK) Thomas Wischgoll (Wright State University, USA) Lai Kuan Wong (National University of Singapore, Singapore) Lei Zhang (Microsoft Research Asia, P.R. China) Sheng Zhang (National University of Singapore, Singapore) Yu Zheng (Microsoft Research Asia, P.R. China) Roger Zimmermann (National University of Singapore, Singapore) Lawrence Zitnick (Microsoft Research, USA)

Technical Program Committee Multimedia Content: (Short Papers): Chair: Chitra Dorai (IBM T.J. Watson Research Center, USA) Arnon Amir (IBM Almaden Research Center, USA) Jonathan Connell (IBM Research, USA) Chitra Dorai (IBM T.J. Watson Research Center, USA) Robert Farrell (IBM, USA) Eva Hörster (University of Augsburg, Germany) Giridharan Iyengar (IBM T.J. Watson Research Center, USA) John Kender (Columbia University, USA) Xuelong Li (University of London, UK) Ying Li (IBM T.J. Watson Research Center, USA) Gary Marchionini (University of North Carolina at Chapel Hill, USA)

66

Vincent Oria (NJIT, USA) Gopal Pingali (IBM T.J. Watson Research Center, USA) Srinivasan Sengamedu (Yahoo India, India) Jialie Shen (Singapore Management University, Singapore) Malcolm Slaney (Yahoo! Research, USA) Dacheng Tao (The Hong Kong Polytechnic University, Hong Kong) C. Gregor van den Boogaart (University of Augsburg, Germany) Lexing Xie (IBM Research, USA)

Multimedia Systems: Chair: Julien Laganier (DoCoMo Euro-Labs, Germany) Imad Aad (DoCoMo Euro-Labs, Germany) Marcelo Bagnulo (University of Carlos III de Madrid, Spain) Gonzalo Camarillo (Ericsson, Finland) Lars Eggert (Nokia Research Center, Finland) Ahsan Habib (Siemens TTB, USA) Wassim Haddad (Ericsson Research, Sweden) Hermann Hellwagner (University of Klagenfurt, Austria) Ulas Kozat (DoCoMo USA Labs, USA) Gabriel Montenegro (Microsoft Corporation, USA) R. Venkatesha Prasad (Delft University of Technology, The Netherlands) Christian Timmerer (University of Klagenfurt, Austria) Hannes Tschofenig (Nokia Siemens Networks, Germany) Christian Vogt (Ericsson Research Nomadic Lab, Finland)

Multimedia Applications: Chair: Susanne Boll (University of Oldenburg, Germany) Lalitha Agnihotri (Philips Research, USA) Elisabeth André (University of Augsburg, Germany) Yannis Avrithis (National Technical University of Athens, Greece) Kathrin Berkner (Ricoh Innovations, USA) Andreas Butz (University of Munich, Germany) Wei-Ta Chu (National Taiwan University, Taiwan) Hans Gellersen (Lancaster University, UK) Andreas Girgensohn (FX Palo Alto Laboratory, USA) Lynda Hardman (CWI & TU/e, The Netherlands) Hermann Hellwagner (Klagenfurt University, Austria) Otthein Herzog (University of Bremen, Germany) Wolfgang Hürst (Albert-Ludwigs-University of Freiburg, Germany) Ebroul Izquierdo (Queen Mary, University of London, UK) Christian Kray (University of Newcastle Upon Tyne, UK) Erik Mannens (Ghent University, Belgium) Andreas Mauthe (Lancaster University, UK) Klaus Meyer-Wegener (University of Erlangen and Nuremberg, Germany) Wolfgang Müller (Bamberg University, Germany) Mor Naaman (Yahoo! Research Berkeley, USA)

67

Frank Nack (University Claude Bernard Lyon 1, France) Andreas Nürnberger (Otto-von-Guericke-University of Magdeburg, Germany) Zeljko Obrenovic (CWI, The Netherlands) Dinh Phung (Curtin University of Technology, Australia) Thomas Plagemann (University of Oslo, Norway) Michael Rohs (Deutsche Telekom Laboratories, TU Berlin, Germany) Enrico Rukzio (Lancaster University, UK) Lloyd Rutledge (CWI, The Netherlands) Ansgar Scherp (OFFIS Institute for Information Technology, Germany) Cees Snoek (University of Amsterdam, The Netherlands) Hari Sundaram (Arizona State University, USA) Raphael Troncy (CWI, The Netherlands) Jana Urban (University of Glasgow, UK) Lars Wolf (TU Braunschweig, IBR, Germany)

Additional Reviewers: John Adcock (FX Palo Alto Laboratory, USA) Nadia Baaziz (Universite du Quebec en Outaouais, Canada) Wolf-Tilo Balke (L3S Research Center, Germany) Tat-Seng Chua (National University of Singapore, Singapore) Cyril Concolato (GET-ENST, France) James Fung (University of Toronto, Canada) Daniel Gatica-Perez (IDIAP Research Institute, Switzerland) Amy Gooch (Northwestern University, USA) Carsten Griwodz (Simula Research Laboratory, Norway) Enrico Hauer (Fraunhofer SIT, Germany) Andreas Hein (University of Oldenburg, Germany) Niels Henze (OFFIS Research Institute of Information Technology, Germany) Otmar Hilliges (University of Munich, Germany) Simon Hoffmann (University of Augsburg, Germany) Alejandro Jaimes (IDIAP Research Institute, Switzerland) Ton Kalker (Hewlett Packard Laboratories, USA) Ingo Kofler (Klagenfurt University, Austria) Hyowon Lee (Centre for Digital Video Processing, Dublin City University, Ireland) Karin Leichtenstern (University of Augsburg, Germany) Seong-Whan Lee (Korea University, Korea) Ketan Mayer-Patel (University of North Carolina at Chapel-Hill, USA) Florian Obermeier (TU München, Germany) Martin Pielot (OFFIS Research Institute of Information Technology, Germany) Martin Prangl (Klagenfurt University, Austria) Philipp Sandhaus (OFFIS Institute for Information Technology, Germany) Thomas Schlämer (University of Oldenburg, Germany) Eckehard Steinbach (Munich University of Technology, Germany)

68

Tinne Tuytelaars (Katholieke Universiteit Leuven, Belgium) Jamie Ward (Lancaster University, UK) Roger Zimmermann (National University of Singapore, Singapore) Fredrik Ǻberg (Ericsson Research Nomadic Lab, Finland) Carlos Bernardos (University of Carlos III de Madrid, Spain) Roland Bless (University of Karlsruhe, Germany) Pablo Cancela (University of Republica Oriental del Uruguay, Uruguay) Monica Cortes Sack (University of Carlos III de Madrid, Spain) Pierre Garrigues (University of California at Berkeley, USA) Ladan Gharai (University of Southern California/ISI, USA) Alvaro Gomez (University of Republica Oriental del Uruguay, Uruguay) Stuart Goose (Siemens TTB, USA) Miska Hannuksela (Nokia Research Center, Finland) Mohamed Hefeeda (Simon Fraser University, Canada) Markus Kampmann (Ericsson Research, Germany) Sandeep Kanumuri (DoCoMo USA Labs, USA) Ingo Kofler (University of Klagenfurt, Austria) Miika Komu (Helsinki Institute for Information Technology, Finland) Daniel Kraft (University of Karlsruhe, Germany) Jose Felix Kukielka (University of Carlos III de Madrid, Spain) Robert Kuschnig (University of Klagenfurt, Austria) Ora Lassila (Nokia Research Center, USA) Frederico Lecumberry (University of Republica Oriental del Uruguay, Uruguay) Marco Liebsch (NEC Network Labs, Germany) Arto Mahkonen (Ericsson, Finland) Shahbaz Nazrul (Qualcomm, USA) Antonio de la Oliva (University of Carlos III de Madrid, Spain) Wei Tsang Ooi (National University of Singapore, Singapore) Joerg Ott (Helsinki University of Technology, Finland) Colin Perkins (University of Glasgow, UK) Muralishankar Rangarao (PES Institute of Technology, India) Vijay S. Rao (ESQUBE Communication Solutions, India) Christian Schaefer (DoCoMo Euro-Labs, Germany) Thomas Schreck (Fachhochschule Landshut, Germany) Isaac Seoane (University of Carlos III Madrid, Spain) Wilson So (Siemens TTB, USA) Christoph Sorge (University of Karlsruhe, Germany) Ignacio Soto (University of Carlos III de Madrid, Spain) S. H. Srinivasan (Yahoo!, India) Marius Tico (Nokia Research Center, Finland) Mejdi Trimeche (Nokia Research Center, Finland) Vlasios Tsiatsis (Ericsson, Sweden) Samu Varjonen (Helsinki Institute for Information Technology, Finland) Claudia Villalonga (NEC Network Labs, Germany) Stephan Wenger (Nokia Corporation, USA) Lars Wolf (Technical University of Braunschweig, IBR, Germany) Alf Zugenmaier (DoCoMo Euro-Labs, Germany)

69

Kiyoharu Aizawa (Tokyo University, Japan) Pradeep Kumar (Atrey University of Ottawa, Canada) Noboru Babaguchi (Osaka University, Japan) Kobus Barnard (University of Arizona, USA) Rui Cai (Microsoft Research Asia, P.R. China) Mingyu Chen (Carnegie Mellon University, USA) Tat-Seng Chua (National University of Singapore, Singapore) Antonio De La Oliva (University of Carlos III de Madrid, Spain) Abdulmotaleb El Saddik (University of Ottawa, Canada) Sheng Gao (Institute for Infocomm Research, Singapore) William Grosky (University of Michigan, USA) Ahsan Habib (Siemens TTB, USA) Alan Hanjalic (Delft University of Technology, The Netherlands) Simon Hoffmann (University of Augsburg, Germany) Benoit Huet (Institut Eurecom, France) Alejandro Jaimes (IDIAP Research Institute, Switzerland) Mohan S Kankanhalli (National University of Singapore, Singapore) Yoshihiko Kawai (NHK, Japan) Wei Lai (Microsoft Research Asia, P.R. China) Geetika Lakshmanan (IBM Research, USA) Michael Lew (Leiden University, The Netherlands) Dongge Li (Motorola Laboratories, USA) Mingjing Li (Microsoft Research Asia, P.R. China) Jochen Lux (University of Augsburg, Germany) Bernard Merialdo (Institut Eurecom, France) Alexandre Miège (University of Ottawa, Canada) Shi-Yong Neo (National University of Singapore, Singapore) Naoko Nitta (Osaka University, Japan) Fernando Pereira (IST-TUL, Portugal) Thomas Rist (Augsburg University of Applied Sciences, Germany) Shin'ichi Satoh (National Institute of Informatics, Japan) Nicu Sebe (University of Amsterdam, The Netherlands) Bo Shen (Hewlett Packard Laboratories, USA) Yaxiao Song (University of North Carolina at Chapel Hill, USA) Changhu Wang (University of Science and Technology of China, P.R. China) Wei Wang (Motorola Laboratories, USA) Kevin Wilson (MERL, USA) Jianfeng Xu (Tokyo University, Japan) Rong Yan (IBM T.J. Watson Research Center, USA) Jun Yang (Carnegie Mellon University, USA) Yuan Yuan (Aston University, UK) Cha Zhang (Microsoft Research, USA) Dongqing Zhang (Thomson Research, USA) Lei Zhang (Microsoft Research Asia, P.R. China)

Interactive Art Exhibition Annet Decker (Montevideo, The Netherlands) Curators: Frank Nack (University Claude Bernard Lyon 1, France)

70

Anne Nigten (V2_ Institute for the Unstable Media, The Netherlands) Thomas Rist (Augsburg University of Applied Sciences, Germany) Alejandro Jaimes (IDIAP Research Institute, Switzerland)

Interactive Art Program Xavier Amatriain (Telefonica R&D, Spain) Committee: Peter Andres (Independent, USA) Barbara Barry (MIT Media Lab, USA) Jeffrey Boyd (University of Calgary, CA) Sher Doruff (Waag Society, NL) Jonathan Foote (Independent, USA) Joost Geurts (INRIA, France) Andrew Gordon (University of Southern California, USA) Sabine Himmelsbach (Edith Russ Site for Media Art, Germany) Hayley Hung (IDIAP Research Institute, Switzerland) Andruid Kerne (Texas A&M University, USA) Nisar Keshvani (Leonardo Electronic Almanaca/Queensland University of Technology) Julian Knowles (Queensland University of Technology, Australia) Akihiro Kubota (Tama Art University, Japan) Felipe Londono (University of Caldas, Colombia) Michael Lyons (Ritsumeikan University, Japan) Roger Malina (Leonardo/ISAST, USA) Steve Mann (University of Toronto, Canada) Jose-Carlos Mariategui (ATA, Peru) Aranxta Mendiharat (Leonardo, Spain) Wolfgang Muench (LASALLE, Singapore) Laurence Noel (Mondeca, France) Claudio Pinhanez (IBM Research, USA) Wim van der Plas (University of Utrecht, The Netherlands) Daniela Plewe (National University of Singapore, Singapore) Nicolas Reeves (University of Quebec in Montreal, Canada) Remi Ronfard (Artificial Life, Canada) Andrew Senior (IBM, USA) Patrick Schmitz (University of California at Berkeley, USA) Xin Wei Sha (Concordia University, Canada) David A. Shamma (Yahoo! Research Berkeley, USA) Ryan Shaw (University of California at Berkeley, USA) Yukiko Shikata (NTT InterCommunication Center, Japan) Flavia Sparacino (Sensing Places/MIT, USA) Hari Sundaram (Arizona State University, USA) Atau Tanaka (Sony CSL Paris, France) Nicolas Tsingos (INRIA, France) Ron Wakkary (Simon Fraser University, Canada)

Interactive Art Program Thomas Rist (Augsburg University of Applied Sciences, Germany) Coordinators: Robert Rose (Augsburg University of Applied Sciences, Germany)

71

Open Source Competition Chair: Apostol Natsev (IBM T.J. Watson Research Center, USA) Committee: Ashish Gehani (SRI, USA) Matthew Hill (IBM T. J. Watson Research Center, USA) Rong Yan (IBM T. J. Watson Research Center, USA) Jun Yang (Carnegie Mellon University, USA)

72

CO‐SPONSORS

SUPPORTERS

MAPS

AUGSBURG TRAM LINES

7 The map on the previous page shows the Augsburg tram lines and how they connect the various conference sites. All tram lines intersect at Königsplatz, the city’s main transportation hub. To change lines, you have to go to Königsplatz first. Also, many conference hotels are within walking distance from Königsplatz.

The most important tram line for the conference members is tram number 3, with the end points ‘Stadtbergen’ and ‘Inninger Str.’, respectively. Line 3 connects the Augsburg central train station with the University of Applied Sciences (called Fachhochschule Augsburg, location of arts exhibitions) and the campus of the University of Augsburg (the main conference site). The end point of the tram line is always being displayed on the front and sides of the tram. It tells you in which direction the tram is currently travelling. Inside the tram, the next stop is always being announced and/or displayed.

To get to either conference site from downtown Augsburg, take line 3 in direction ‘Inninger Str.’. It leaves at Königsplatz platform ‘F’ every 5 to 10 minutes, depending on the current day and time.

The live arts exhibition at the University of Applied Sciences (Fachhochschule Augsburg) is only two stops away from Königsplatz: after getting off the tram at ’Rotes Tor’, it is just a three-minute walk along ‘Rote-Torwall-Staße’” to the Fachhochschule (see separate map below).

The University campus is roughly a 10 minute ride from Königsplatz. The stop to get off the tram is called ‘Universität’. You will find yourself right at the spot marked with an ‘H’ and labeled “Straßenbahnlinie 3 – Haltestelle Universität” as shown on the map on the previous page.

To get back to downtown from either site, get on any line 3 tram towards Stadtbergen. It will arrive at Königsplatz platform ‘G’. From there, you can either walk back to your hotel (in most cases), or change tram and bus lines, or catch a taxi.

LIVE ARTS EXHIBITION (at Fachhochschule Augsburg/University of Applied Sciences, Fakultät für Informatik)

The live arts exhibition takes place in the building marked „KLM“ on the right. The tram stop “Rotes Tor” is shown to the left. Simply follow “Rote-Torwall-Str.” along the ancient city walls.

8 CONFERENCE SITE MAP

9 FLOOR PLANS

1: KEYNOTES, BEST PAPER SESSION Hörsaal 1 (HS1)

2: CONFERENCE SESSIONS, TUTORIALS, WORKSHOPS Institut für Physik – Hörsaalzentrum

1st Floor 2nd Floor

10 Brave New Topics

Call for Brave New Topics Session Proposals

ACM Multimedia 2007 is seeking to extend the boundaries of multimedia research presented at the conference through the introduction of its Brave New Topics Sessions. We solicit proposals for special sessions dealing either with topics not usually covered at ACM Multimedia or which introduce entirely new research areas. We also encourage proposals addressing to define foundations of multimedia as a science.

Example topics include but are not limited to: Web2.0, biomedical applications, multimodal biometrics, multimedia use experience, sensor- based systems, gaming, and pervasive computing.

Each Brave New Topics session is expected to consist of a coordinated set of papers managed by the session organizer. An initial proposal is expected that outlines the scope of the session and the expected participants. Session organizers, together with the Brave New Topics chairs, work together on organizing a final session.

The Brave New Topics session is being handled as a separate track at this year's conference. We expect to accommodate up to two Brave New Topics sessions, and each session will be allotted 90 minutes. Since acceptance is likely to be highly selective, we encourage you to submit a short session proposal well in advance of the final submission dates. We can provide feedback on your proposal or help bring groups together in expanded sessions.

Important Dates

2 April 2007 Deadline for submission of Proposal 30 Apr 2005 Notice of acceptance TBD Session Proposal Acceptance Notification 2 July 2007 Camera-ready papers

Submission Instructions

What to submit:

Session proposals should include a title, a one-page abstract describing the scope of the session, names and biographies of the organizers, names of the participants, and abstracts for each of the proposed papers.

Where to submit:

Please submit your proposal by sending email with the abstract and other supporting materials as attachments to the Brave new topic co-chair.Shin'ichi Satoh [[email protected]] and Edward Chang [[email protected]]

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/brave_new_topics_.html[1/28/2010 9:24:20 AM] Technical Demonstrations

Call for Technical Demonstrations Submissions

This year's Technical Demonstrations will showcase leading edge work and work in progress in every area of multimedia, including:

Multimedia analysis, processing, and retrieval Multimedia networking and system support Multimedia tools, end-systems, and applications

Submissions are particularly encouraged in the areas of haptics, smell, sensors, novel interface design, immersive technologies, wireless multimedia applications, multimedia-based security applications, digital rights management, multimedia databases, content analysis, content-based retrieval, multimedia storage, multimedia networking, media processing, entertainment, compression, hypermedia authoring, multimedia social networking and innovative applications.

All submissions will be peer-reviewed to ensure quality. An award will be given for the best technical demonstration, as judged by an evaluation panel. Demonstrators will be provided with space and access to a local (wired) network. Participants will be required to provide their own computing equipment and any additional network, display, haptic, sensor, etc., hardware needed for the demonstration.

Important Dates

1 June 2007 Technical demonstrations submission deadline 20 June 2007 Technical demo acceptance notification 11 July 2007 Camera-ready papers

Submission Instructions

What to submit:

A short paper (two page maximum) describing your technical demo. Please use the standard ACM format (see http://www.acm.org/sigs/pubs/proceed/template.html ) In addition to the two page short paper, you may optionally submit one or more of the following multimedia documents that describe or illustrate the demonstration:

a Microsoft Powerpoint presentation a Macromedia Flash presentation, or an MPEG video clip (not more than 3 minutes long)

Where to submit:

Please submit your demonstration proposal by sending email with the short paper and other supporting materials as attachments to Milind Naphade or Wei-Ying Ma

([email protected] and [email protected])

Questions?

Please direct any questions regarding the technical demonstrations or submissions to the technical demo chairs:

Milind Naphade, IBM Wei-Ying Ma, Microsoft

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/technical_demonstrations.html[1/28/2010 9:24:21 AM] Call for VideoDemos

Call for Video Demos

The 15th Annual ACM International Conference on Multimedia (ACM MM 2007) will be held in Augsburg, September 23-29, 2007. ACM Multimedia is the premier technical multimedia conference attended by an international community of researchers from both academia and industry.

Most of the ideas we get to know at the ACM MM deal with analyzing and using domains and documents consisting of different kinds of media and modalities. Yet, we present most of them in paper-form. So let's practice what we preach and consider presenting your idea as a self-made video of up to 8 minutes in MPEG format. The video must be in the following format:

MPEG-2, yuv420p, 720x480, about 4000 kb/s, 29.97 fps with audio in MP2, 48 kHz, stereo, 384 kb/s

We encourage authors to submit videos

showing creative applications or MM-arts in new contexts merging augmented reality and real world entities showing the use of multiple cameras, camera-arrays or video-sensor networks

At the presentation, the principal author should introduce the audience shortly to the presented idea. The actual display of the videos will be prepared by the committee.

The author is encouraged to submit her contribution digitally. Therefore, please make the submission available for download under a stable URL. In order not to run into technical difficulties we strongly recommend to submit 1-2 days prior to the actual deadline. Sending a storage medium via traditional mail is another option. The date of the postmark will count as date of submission.

The accompanying paper using the same style-sheet as regular papers of the ACM MM should be sent to

Thomas Haenselmann [email protected]

or in case of snail mail to the

University of Mannheim Dr. Thomas Haenselmann LS PI IV A5, 6 68159 Mannheim Germany

Prepare an informal cover sheet with title, authors (indicate principal author), affiliations, address, and primary contact or include this information in your e-mail when submitting digitally. Authors of accepted submissions will be required to sign copyright to ACM. Do not attach a video-file to your mail but provide an URL for download.

Important Dates

1 June 2007 Deadline for Submission 20 June 2007 Notification of acceptance 11 July 2007 Camera-ready papers

Contacts?

For any questions regarding the video demos please email

Thomas Haenselmann [email protected]

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/call_for_videodemos.html[1/28/2010 9:24:22 AM] Source Competition

Call for Open Source Software Competition

The open-source software competition is a relatively recent and highly successful addition to the ACM Multimedia program. 2007 will be our fourth year in running the competition.

The competition celebrates the invaluable contribution of researchers who advance the field by providing the community with implementations of codecs, middleware, frameworks, toolkits, libraries, and other multimedia software.

To qualify, software must be provided with source code and licensed in such a manner that it can be used free of charge in academic and research settings. For the competition, the software will be built from the sources. Submissions should be made in the form of a compressed zip or tar archive file and must include the following:

A text file named README.txt which summarizes the purpose of the software and its overall design and use. A text file named INSTALL.txt which includes any and all instructions on building and installing the software and any system requirements. The judging committee will make a reasonable effort to build any submitted software. However, if we are unable to make the software run given a reasonable effort, we must unfortunately exclude it from the competition. Therefore, complete and clear build and install instructions are a crucial component of any submission.

Additionally, authors are highly encouraged to provide as much documentation as possible, including examples of how the provided software might be used. Entries may be made available to the research community via the ACM Multimedia SIG website and the judging committee may employ feedback from the community at large to help determine the winning entry. In order to encourage participation, non-winning entries are encouraged to submit again in the future. Student-led efforts are particularly encouraged. Authors of the winning entry will be recognized formally at ACM Multimedia 2007, awarded a prize (to be announced), and invited to demonstrate their software as part of the conference demonstration program.

All short Open Source Software submissions must be submitted through EDAS. Follow the link, create either a new user account or use your existing EDAS account and submit your code and description.

Important Dates

1 June 2007 Open Software Competition submission deadline (EDAS) 20 June 2007 Notification of acceptance 11 July 2007 Camera-ready papers

Submission Instructions

People interested in submitting an entry to the open source software competition should submit 1-2 pages containing the following information via the online submission system.

Title of submission Names and affiliations of authors (indicate students) Brief overview of submission (i.e., purpose, intended audience, main features, etc.) Public URL for project page where software, documentation, and license can be found Compressed tar or zip archive file with all source code, documentation, and licenses

Please note: If the archive file is more than 5MB in size, please place the file in a web accessible location and send a URL for that location instead.

If you have questions about what can or should be submitted, please feel free to address these questions to the competition chair Apostol (Paul) Natsev. We are excited to be organizing this innovative and creative addition to the ACM Multimedia program. Please help us make this venture a continuing success by submitting your entry to the competition. We look forward to your participation.

Questions?

For any questions regarding the open source competition please email the chair:

Apostol (Paul) Natsev (IBM Research)

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/source_competition.html[1/28/2010 9:24:24 AM] Call for Panel Proposals

Call for Panel Proposals

The 15th Annual ACM International Conference on Multimedia (ACM MM 2007) will be held in Augsburg, September 23-29, 2007. ACM Multimedia is the premier technical multimedia conference attended by an international community of researchers from both academia and industry.

The panels at Multimedia 2007 will provide a forum for bold position statements and insightful debates on controversial, unresolved, or emerging issues related to all aspects of multimedia. With the panels we would specifically like to stimulate discussions on challenges and research trends. The conference will host two panels, one each on the first and the second day of the conference.

Potential Topics

We solicit proposals in, but not at all limited to, the following topics:

Is the semantic gap the main obstacle to pervasive multimedia content access? Multimedia context is much more than just time and location. Personalization challenges for multimedia usage, delivery and recommendation systems The impact of a multi-sensory world on multimedia research Content analysis versus social network analysis Opportunities in the convergence of cyberspace and real space Why can't we still build a really usable multimedia content authoring system?

Submission Instructions

The panel proposal (2-3 pages) should include:

Panel title Panelists (name, position, affiliation, country) Panel topic (motivation, issues to be discussed) Panel structure (time needed, schedule of presentations and discussions) Proposers of the panel (name, position, affiliation, country)

Please e-mail your panel proposal in PDF to the panel co-chairs. Best panel proposals will be selected by the panel co-chairs supported by a Panel Selection Board comprised of members from the ACM MM 2007 Program Committee.

Important Dates

2 April 2007 Deadline for Submission 20 June 2007 Notification of acceptance

Contacts?

For any questions regarding panels please email the panel co-chairs:

Mohan Kankanhalli (NUS, Singapore) Yap-Peng Tan (NTU, Singapore)

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/call_for_panel_proposals.html[1/28/2010 9:24:25 AM] Technical Program

Call for Long Papers

The 15th Annual ACM International Conference on Multimedia (ACM MM 2007) will be held in Augsburg, Germany, September 23-28, 2007. ACM Multimedia is the premier technical multimedia conference attended by an international community of researchers, practitioners, and designers from both academia and industry.

ACM MM 2007 invites your participation in the premier annual multimedia conference, covering all aspects of multimedia computing: from underlying technologies to applications, theoretical foundations to experimental systems, and servers to networks to devices. MM 2007 seeks high-quality, original papers that will set the standard in the field and stimulate the trends for years to come. We especially encourage introduction of novel media such as haptic, olfactory, multiple sensors, etc. and multimodal, generic, on-line adaptable and human-centered approaches.

Technical Program

The technical program will consist of plenary sessions and talks with topics of interest in:

Multimedia content access, including multimedia semantics, aesthetics, modeling, assimilation/fusion, audio/video/multi-modal processing, multi-sensor processing, multimedia content description and indexing, multimedia digital rights management, content- based retrieval with emphasis on multiple and novel media, combined local and distributed (networked) content indexing. Papers on theoretical foundations of content access methodologies, as well as on generic and on-line adaptable content analysis and indexing approaches are encouraged.

(Technical Program Committee for Content Track)

Multimedia tools, applications, and end user systems, including new UI metaphors, authoring and design tools, experiential systems, sociable media, collaborative systems, multi-modal interaction, virtual environments, and multimedia in education, entertainment, and security. Empirical studies and new theories related to these topics are encouraged.

(Technical Program Committee for Applications Track)

Multimedia networking and systems, including context-aware multimedia communications, Internet telephony, peer-to-peer streaming, audio/video streaming, multimedia content distribution, wireless multimedia, multimedia over mesh/sensor networks, adaptive support for scalable media, Internet protocols, multimedia servers, operating systems, middleware and QoS.

(Technical Program Committee for Systems Track)

Multimedia interaction, including multimodal human-computer-interaction, experiential and affective issues in multimedia, user, context, and task modeling in multimedia systems, multimedia ubiquitous computing, human interaction modeling from multimedia, multimodal social network analysis, cultural and social issues in multimedia modeling, multimedia collaboration, interactive storytelling, social dynamics modeling and socially aware systems, ethnocomputing.

(Technical Program Committee for Interaction Track)

The above list is not exhaustive. We particularly encourage submissions in new and emerging areas.

Submission Instructions

Prepare a paper (not more than 10 pages) using the ACM template for the conference -- Portable Document Format (PDF) or PostScript (version 2 or later), formatted in two-column conference style. Submissions should present original reports of substantive new work. Papers should properly place the work within the field, cite related work, and clearly indicate the innovative aspects of the work and its contribution to the field. We will not accept any paper which, at the time of submission, is under review for or has already been published or accepted for publication in a journal or another conference. Please see the ACM proceedings template available at http://www.acm.org/sigs/pubs/proceed/template.html. All submitted papers will undergo a double-blind review process.

Please note that the formatting template given above refers to final format of accepted papers. For the purpose of double blind review, please remove names of authors and affiliations from the paper heading, and all references to (your own) papers or systems that may reveal your identity. In place of names of authors and affiliations in the heading, please replace it by the paper id as "Paper xxx". For some references to your own papers, you may want to leave the reference id but remove the details of references by stating: "reference removed for the purpose of anonymous review.

All papers must be submitted through EDAS. Follow the link, create either a new user account or use your existing EDAS account and submit your paper under one of the four tracks. Every paper must be assigned to one of the four tracks!

Important Dates

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/technical_program.html[1/28/2010 9:24:26 AM] Technical Program

5 March 2007 Paper submission site open; submit through EDAS 16 April 2007 Submission deadline for full length, 10-page technical papers at 5 PM PDT 20 June 2007 Notification of acceptance 2 July 2007 Camera-ready papers

Contacts

For any questions regarding full papers, please email to the PC co-chairs:

Alan Hanjalic (Delft University of Technology, Netherlands) - Content ([email protected]) Sunghyun Choi (Seoul National University, Korea) - Systems ([email protected]) Brian Bailey (UIUC, USA) - Applications ([email protected]) Nicu Sebe (University of Amsterdam, Netherlands) – Interaction ([email protected])

Program Committee

Multimedia Content Access

Kiyoharu Aizawa, University of Tokyo Noboru Babaguchi, Osaka University Edward Chang, University of California Liang-Tien Chia, Nanyang Technological University Tat-Seng Chua, National University of Singapore Ajay Divakaran, MERL Chitra Dorai, IBM T.J. Watson Research Center Abdulmotaleb El Saddik, University of Ottawa Daniel Ellis, Columbia University Yihong Gong, NEC Labs American William Grosky, U of Michigan Alexander Hauptmann, Carnegie Mellon University Xian-Sheng Hua, Microsoft Research Asia Horace Ip, City University of Hong Kong Mohan Kankanhalli, National University of Singapore John Kender, Columbia U Irwin King, The Chinese University of Hong Kong Anil Kokaram, Trinity College Dublin Michael Lew, Leiden University Dongge Li, Motorola Labs Mark Liao, Academia Sinica Lie Lu, Microsoft Research Asia Jiebo Luo, Eastman Kodak Company Wei-Ying Ma, Microsoft Research, China Stephane Marchand-Maillet, University of Geneva Nasir Memon, Polytech University Bernard Merialdo, Institut Eurecom Apostol Natsev, IBM T. J. Watson Research Center Chong-Wah Ngo, City University of Hong Kong Noel O'Connor, Dublin City University Fernando Pereira ,IST-TUL Gopal Pingali, IBM TJ Watson Research Center Yong Rui, Microsoft Research Shin'ichi Satoh, National Institute of Informatics Bo Shen, HP Labs Alan Smeaton, Dublin City University John Smith, IBM T.J. Watson Research Center Hari Sundaram, Arizona State University Qi Tian, University of Texas at San Antonio Svetha Venkatesh, Curtin University of Technology Lynn Wilcox, FXPAL Marcel Worring, University of Amsterdam Changsheng Xu, Institute for Infocomm Research Cha Zhang, Microsoft Research

Multimedia Tools, Applications, and End-user Systems

Brett Adams, Curtin University of Technology John Adcock, FX Palo Alto Laboratory Elisabeth André, University of Augsburg Yasuo Ariki, Kobe University Frank Bentley, Motorola Labs Dick Bulterman, CWI

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/technical_program.html[1/28/2010 9:24:26 AM] Technical Program

Andrea Cavallaro, Queen Mary, University of London Ee-Chien Chang, National University of Singapore Elaine Chew, University of Southern California Matthew Cooper, FX Palo Alto Laboratory Berna Erol, Ricoh California Research Center Jianping Fan, University of North Carolina at Charlotte Anthony Fang, National University of Singapore Jim Gemmell, Microsoft Research David Gerhard, University of Regina Vera Goebel, University of Oslo Forouzan Golshani, Wright State University Thomas Haenselmann, University of Mannheim Karrie Karahalios, University of Illinois - Urbana Wei Lai, Microsoft Research Asia Peiya Liu, Siemens Corporate Research Shivajit Mohapatra, Motorola Labs Mor Naaman, Yahoo! Research Berkeley Balakrishnan Prabhakaran, University of Texas at Dallas Nicolas Roussel, LRI & INRIA Futurs Lloyd Rutledge, CWI, Amsterdam Andreas Schrader, University of Lubeck Timothy Shih, Tamkang University Zhen Wen, University of Illinois - Urbana Andy Wilson, Microsoft Research Jiang-Yu, Zheng Indiana University Michelle Zhou, IBM T. J. Watson

Multimedia Interaction

Antonis Argyros, University of Crete, Greece Barbara Barry, MIT Media Lab, USA Erhardt Barth, Univ. of Luebeck, Germany Paulo Barthelmess, Adapx, USA Susanne Boll, University of Oldenburg, Fermany Herve Bourlard, IDIAP, Switzerland Kevin Brooks, Motorola, USA Ira Cohen, HP Laboratories, USA David Demirdjian, MIT, USA Andreas Dengel, DFKI, Germany Ahmed Elgammal, Rutgers University, USA Daniel Gatica-Perez, IDIAP, Switzerland Alejandro Jaimes, IDIAP, Switzerland Ashish Kapoor, Microsoft Research, USA Andruid Kerne, Texas A&M Univ., USA Michael Lyons, Ritsumeikan University, Japan Frank Nack, Univ. Lyon, France Jean-Marc Odobez, IDIAP, Switzerland Kazuhiro Otsuka, NTT, Japan Maja Pantic, Imperial College, UK Montse Pardas, Technical University of Catalonia, Spain Ioannis Patras, Queen Mary, University of London, UK Vladimir Pavlovic, Rutgers University, USA Catherine Pelechaud, Univ. Paris 8, France Gerasimos Potamianos, IBM, USA Patrick Schmitz, UC Berkeley, USA Rainer Stiefelhagen, Universität Karlsruhe, Germany Matthew Turk, University of California, Santa Barbara, USA Gerd Westermann, SEraja Technologies, Germany Jie Yang, Carnegie Mellon University, USA Ming-Hsuan Yang, Honda Research, USA Massimo Zancanaro, ITC-irst, Italy

Multimedia Networking and Systems

Kevin Almeroth, University of California at Santa Barbara, USA Surendar Chandra, University of Notre Dame, USA Ming-Syan Chen, National Taiwan University, Taiwan Mark Claypool, Worcester Polytechnic Institute, USA Pedro Cuenca, Universidad Castilla La Mancha, Spain Alberto Del Bimbo, University of Firenze, Italy Wu-chang Feng, Portland State University, USA Wu-chi Feng, Portland State University, USA David Gotz, IBM Research, USA Carsten Griwodz, Simula Research Laboratory, Norway Yoshihiro Kawahara, The University of Tokyo, Japan

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/technical_program.html[1/28/2010 9:24:26 AM] Technical Program

JongWon Kim, GIST (Gwangju Institute of Science & Technology), Korea Taekyoung Kwon, Seoul National University, Korea Baochun Li, University of Toronto, Canada Laurent Mathy, Lancaster University, UK Andreas Mauthe, Lancaster University, UK Ketan Mayer-Patel, University of North Carolina, USA Sue Moon, KAIST, Korea Liam Murphy, University College Dublin, Ireland Klara Nahrstedt, University of Illinois at Urbana-Champaign, USA Wei Tsang Ooi, National University of Singapore, Singapolre Balakrishnan Prabhakaran, University of Texas at Dallas, USA Hayder Radha, Michigan State University, USA Reza Rejaie, University of Oregon, USA Keith W. Ross, Brooklyn Polytech, USA Prashant Shenoy, University of Massachusetts at Amherst, USA Shervin Shirmohammadi, University of Ottawa, Canada Hwangjun Song, Pohang University of Science and Technology, Korea Michael Vernick, Avaya Labs, USA Michael Zink, University of Massachusetts Amherst, USA

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/technical_program.html[1/28/2010 9:24:26 AM] Short Papers CFP

Call for Short Papers

The 15th Annual ACM International Conference on Multimedia (MM 2007) will be held in Augsburg, Germany, September 23 – 29, 2007. ACM Multimedia is the premier technical multimedia conference attended by an international community of researchers from both academia and industry.

For this conference, we are seeking outstanding short paper submissions that will be presented in an interactive poster format at the conference.

Short papers should present interesting recent results or novel thought-provoking ideas that are not quite ready for a regular full-length paper. We are looking for original and bold papers in all areas of multimedia technology, its application, and use Submissions are encouraged in areas including multimedia databases, content analysis, media processing, compression, multimedia storage, networking, copyright protection, multimedia and hypermedia authoring, multimedia user interfaces, innovative applications and in emerging topics of social media and collaborative tagging. Submissions will be peer-reviewed to ensure quality. Accepted short papers will be presented in an interactive poster presentation at the conference.

Areas of interest include, but not restricted to:

(a) Multimedia content analysis, processing, and retrieval; (b) Multimedia networking, sensor networks, and systems support; (c) Multimedia tools, interfaces, end-to-end-systems, and applications.

Submission Instructions

Prepare a 4-page paper using the ACM template for the conference—Portable Document Format (PDF) or PostScript (version 2 or later), formatted in two-column conference style. Please see the ACM proceedings template available at http://www.acm.org/sigs/pubs/proceed/template.html.

All submitted papers will undergo a double-blind review process. Please note that the formatting template given above refers to final format of accepted papers. For the purpose of double blind review, please remove names of authors and affiliations from the paper heading, and all references to (your own) papers or systems that may reveal your identity. In place of names of authors and affiliations in the heading, please replace it by the paper id as “Paper xxx”. For some references to your own papers, you may want to leave the reference id but remove the details of references by stating: “reference removed for the purpose of anonymous review.”

All short papers must be submitted through EDAS. Follow the link, create either a new user account or use your existing EDAS account and submit your paper under one of the three tracks. Every paper must be assigned to one of the three tracks!

Important Dates

1 June 2007 Short Paper Submission deadline ( EDAS - Content Track ,EDAS - System and Network Track, EDAS - Applications Track ) 5 July 2007 Notification of acceptance 11 July 2007 Camera-ready papers

Contacts

For any questions regarding short papers please email the co-chairs:

Chitra Dorai (IBM Watson Research) [[email protected]] Julien Laganier (DoCoMo Euro-Labs) [[email protected]] Susanne Boll (U. Oldenburg) [[email protected]]

Technical Program Committee

Imad Aad, DoCoMo Euro-Labs Arnon Amir, IBM Almaden Research Center, USA Marcelo Bagnulo, University Carlos III of Madrid, Spain Kathrin Berkner, Ricoh Innovations, USA Julien Bournelle, France Telecom R&D, France

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/short_papers_cfp.html[1/28/2010 9:24:28 AM] Short Papers CFP

Andreas Butz, Ludwig-Maximilians-Universität München, Germany Doree Duncan Seligman, Avaya Labs, USA Lars Eggert, Nokia Research Center, Finland Lynda Hardman, CWI, The Netherlands Hermann Hellwagner, Alpen-Adria-Universität Klagenfurt, Austria Otthein Herzog, Universität Bremen, TZI and MRC, Germany Ebroul Izquierdo, Queen Mary University London, UK Erik Mannens, Ghent University – IBBT, Belgium Klaus Meyer-Wegener, Universität Erlangen-Nürnberg, Germany Andreas Nürnberger, Otto-von-Guericke-University Magdeburg Thomas Plagemann, University of Oslo, Norway Ansgar Scherp, OFFIS, Germany / Visiting Scholar at UCI, USA Klaus Tochtermann, Know Center Graz, Austria Lars Wolf, Technische Universität Braunschweig, Germany Christian Vogt, Ericsson Research NomadicLab, Finland Wassim-Michel Haddad, Ericsson Research, Sweden Ahsan Habib, Siemens Technology-To-Business Center Giridharan Iyengar, IBM Research Ying Li, IBM Research Xuelong Li, University of London, UK Gabriel Montenegro, Microsoft Corporation Vincent Oria, NJIT, USA Malcolm Slaney, Yahoo! Research, USA S H Srinivasan, Yahoo!, India Ba Tu Truong, Curtin University, Australia Raphael Troncy, CWI, The Netherlands Hannes Tschofenig, Nokia Siemens Networks, Germany Jana Urban, University of Glasgow, UK Wolfgang Müller, University of Bamberg, Germany

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/short_papers_cfp.html[1/28/2010 9:24:28 AM] Doctoral Symposium

Call for Submissions to the Doctoral Symposium

The 15th Annual ACM International Conference on Multimedia (MM 2007) will be held in Augsburg, Germany, September 23 – 29, 2007. ACM Multimedia is the premier technical multimedia conference attended by an international community of researchers from both academia and industry.

The Doctoral Symposium is an opportunity for students involved in the preparation of a PhD in any area of Multimedia to interactively discuss their research issues and ideas with senior researchers, receive constructive feedback from members of the research community and expose themselves as up and coming multimedia researchers.

During the Doctoral Symposium, selected students will present their thesis topic, the work they have performed so far and the results that they have obtained. They will also reveal the difficulties, problems and questions that they encounter in the continuation of their work and can ask for comments from the audience.

Submission Instructions

Interested students should submit 2-3 page abstracts describing their research using the standard paper submission template for the conference - Portable Document Format (PDF) - formatted in two-column conference style. Please see the ACM proceedings template available at http://www.acm.org/sigs/pubs/proceed/template.html. Please email your proposal abstract to the Doctoral Symposium Chairs.

Important Dates

1 June 2007 Doctoral Symposium Submission Deadline 1 July 2007 Notification of acceptance 11 July 2007 Camera-ready papers

Contacts

For any questions regarding short papers please email the co-chairs:

Thomas Plagemann (U. Oslo) [[email protected]] Vera Göbel (U. Oslo) [[email protected]]

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/doctoral_symposium.html[1/28/2010 9:24:30 AM] Camera Ready Papers

Detailed instructions for preparing camera-ready papers

[Note: Each accepted paper must have at least one author registered for the conference at the regular full rate (not the student rate) by the advance registration date (August 15) for the paper to remain part of the ACM MM conference and proceedings. If all of the paper's authors are students, then a student registration suffices for that paper.]

The website for submitting the final version of the accepted papers is now open. Please go to the relevant links below to access the copyright form and submission web site:

The instructions are organized as follows:

Overview of deadlines and maximum number of pages Camera ready copy and the copyright form Formatting instructions and uploading camera ready copy The ACM computing classification The Shepherding process (full papers only) Printed proceedings and ACM digital library Contact the proceedings coordinator, Lisa M. Tolles at Sheridan Printing Contact the MM07 Proceedings Chair, Roger Zimmermann

Overview of the page limits and deadlines

Note: These deadlines must be met - no extensions!

Paper Type Max. number of pages Deadline Full papers 10 July 2, 2007 Short papers 4 July 11, 2007 Demo papers 2 July 2, 2007 Panel descriptions 2 July 2, 2007 Art full papers 10 July 2, 2007 Art short papers 4 July 11, 2007 Art exhibit papers 2 July 11, 2007 Brave new topic papers 10 July 2, 2007 Video papers 2 July 11, 2007 Doctoral symposium papers 3 July 11, 2007 Open source contest 4 July 11, 2007 Keynote talks 1 July 2, 2007 Tutorials 2 July 2, 2007 MV workshop 6 July 5, 2007 TVS workshop 10 July 5, 2007 HCM workshop 10 July 11, 2007 MIR workshop 10 July 11, 2007 MS workshop 10 July 11, 2007 EMME workshop 10 July 5, 2007

Camera ready copy and copyright form

Authors of accepted full papers/short papers/demos/videos/art exhibit/doctoral symposium for the ACM MM 2007 conference will receive an email from Lisa M. Tolles from Sheridan Printing, the publisher that will produce the

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/camera_ready_papers.html[1/28/2010 9:24:31 AM] Camera Ready Papers

conference proceedings. The email contains all the details for submitting the camera ready copy and copyright form.

Formatting instructions and uploading camera ready copy

The camera ready copy of each submission must strictly adhere to the Sheridan Printing Instructions for the ACM MM 2006 Proceedings.

We kindly ask you to read carefully through the instructions from Sheridan and start preparing the camera ready copy as early as possible to avoid any delays due to formatting problems, paper length, or lacking a copyright form. For an appealing print of your contribution in the conference proceedings please do NOT change the given paper style, e.g., by increasing text width and height or reducing line spacing in order to get more space for your paper.

The Sheridan web page also contains information on the files and their required naming for the submission as well as the URL where to upload the files of the final version.

If you have any questions left regarding the preparation of the camera ready copy, please contact the proceedings coordinator Lisa M. Tolles at Sheridan printing. For questions regarding the shepherding process and further general questions, please contact the proceedings chair Roger Zimmermann.

The ACM computing classification

Please note that each paper must provide a classification of it's content and general terms according to the ACM computing classification. If you are not familiar with this classification please make sure that you read carefully through the guide "How to classify works using the ACM's computing classification system" to select the most suitable categories and general terms for your paper and add some additional keywords to it. Do NOT omit classification, general terms or keywords in your camera ready copy, e.g., in order to save space!

The shepherding process (for Full Papers only)

As was started in ACM 2003, the inclusion of the reviewers' comments in the final version of the paper is guided by a "Shepherd" - a member of the program committee - to help the authors in the process of reflecting the reviewers' comments in the final version. The shepherd will ensure that all review comments are addressed properly in the final version. This process contributes to the high quality of the conference and also honors the reviewers' effort in writing reviews. Your shepherd should already be in touch with you; please negotiate a time schedule with your shepherd.

The proceedings chair must get a confirmation from the shepherds that all review comments are appropriately considered in your final camera-ready version. Please do not hesitate to ask your shepherd if you have any questions. In order to facilitate the task of the shepherd, we ask you to establish a document that lists all review comments and discusses how you have taken them into account in your final paper.

Email this document to the proceedings chair Roger Zimmermann before July 2, 2007. Please include [ACM MM07] in the subject of the e-mail. This information, acknowledged by your shepherds as complete, is important for being included in the conference proceedings.

Note: Only some papers are shepherded. You will be informed by your track chair if this is the case for your paper.

Printed proceedings and ACM digital library

Printed conference proceedings will be produced by Sheridan Printing; the proceedings will also be entered in the ACM Digital Library.

Contact the publisher

Lisa Tolles Email: [email protected] Phone +1-908-213-8988 Fax +1-908-454-2554

Address Sheridan Printing Co. Attn: Lisa M. Tolles 1425 Third Ave. Alpha, NJ 08865 (USA)

Contact proceedings chair

In case you have any questions left after having carefully read the instructions provided by Sheridan Printing, please contact the proceedings chair:

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/camera_ready_papers.html[1/28/2010 9:24:31 AM] Camera Ready Papers

Roger Zimmermann, University of Southern California Email: [email protected] Phone +1-213-740-7654 Fax +1-213-740-5807

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/camera_ready_papers.html[1/28/2010 9:24:31 AM] Oral Presentations

Oral Presentations

The oral presentations at ACM MM 2007 will be scheduled to start on the half-hour (at 8:30am, 9:00am, 9:30am, etc.) so that the audience may freely move between parallel sessions and see complete talks. Session chairs should enforce this, and thus make sure talks do not go overtime or start too soon. Since there will be 30 minutes for everything - the talk, questions and answers, and changing to the next speaker - the talk should run 22-24 minutes (no longer) to leave adequate time for questions and changeover. Session chairs will give speakers 5-minute and 1-minute notices, and they will feel free to stop the talk at the 24 minute mark.

For all oral presentations, a video projector (for PC or Mac laptop) and audio will be provided. Bring your own laptop, and have it ready to go when you step up to give your presentation (that is not the time to boot the computer, look for the file, etc.!).

Presenters, please find the session chair and introduce yourself to him or her before the session begins. You may want to tell the session chair how to pronounce your name, and ask how he/she will give the 5-minute and 1-minute warnings.

Session chairs, please be at the session early to check on A/V and to meet the speakers. Find out who is giving the talk for each paper, and how to pronounce the speaker's name. Make sure they understand about the 5-minute and 1-minute warnings, and how you will deliver these.

Presentation Guidelines: Do’s and Don’ts

This information is reprinted in part from the ACM CHI and IUI conference series.

1. Checking Content Appropriateness

DON'T give a presentation that will be comprehensible and interesting only to people who work in the same area as you. Please be aware that MM is a multidisciplinary conference, with researchers and practitioners in attendance.

DO ensure that even people who have little familiarity with your subarea of MM can understand at least the main points:

what questions you addressed, why they're important, what methods you used (not necessarily the details), what your main results were, and why they are interesting.

In fact, even the experts in your area don't need to understand more than these points; for the rest, they can read the paper.

DON'T try to squeeze in so much material as to leave hardly any time for questions.

DO aim to be finished in your allotted time:

Your audience will love and admire you for it, and you will be rewarded with a relatively deep discussion. (If the discussion flags, the Session Chair or the program chairs will ask a question to get it going again.) Note that any speaker who exceeds 24 minutes will be interrupted mercilessly by the Session Chair, and time for questions will be reduced accordingly.

DON'T subject your audience to an "ordeal by bulleted list”. Bulleted lists - especially those with large amounts of text - should be used only in exceptional cases. They are generally boring, abstract, unconvincing, and hard to read while the speaker is talking.

DO present a series of "exhibits": images, videos, system demos, diagrams, graphs, or tables. You can explain and elaborate on these exhibits while people are looking at them, but in general you don't need to write what you say on the slides. Anyone who wants to see the points you made in black and white can read your paper. Carefully preparing an exhibit can take at least 10 times as long as dashing off a bulleted list, but your audience -- and your research, case study, or discussion -- deserve nothing less.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/oral_presentations.html[1/28/2010 9:24:32 AM] Oral Presentations

DON’T use text smaller than a 28-point font. Your audience will not be able to read your slides otherwise.

DO use text sparingly: Keep your points in short, concise, outline form. This will inform the viewer about the topic, and will also help you remember your key points for discussion. There is no real need to write in full sentences, as this will unnecessarily clutter your slides. If you have that much text on the screen, break part of it out to another slide.

2. Polishing the Details

DON'T put material on a slide that only the people in the front rows can read.

DO pay special attention to types of material that often turn out to be illegible: screen shots and complex graphics. If an exhibit like this can't be shown legibly as a whole, find a way to zoom in on individual parts of it as they are discussed.

DON'T clutter each slide with distracting logos and superfluous information such as the title of the talk or the name and date of the conference.

DO present only material that helps you to convey your points effectively. If you must include your institution's logo on each slide, make sure that it is not the most conspicuous and interesting element on any slide.

3. Giving the Presentation

DON'T risk fumbling desperately with the laptop at the beginning of your talk.

DO arrive 20 minutes before your session to test the compatibility of your laptop with the projector. If you bring your presentation on a CD or memory stick to present on someone else's laptop, do everything possible to maximize its portability, and test the presentation at the earliest opportunity, leaving plenty of time to fix any problems (e.g., replacing missing fonts).

DON'T talk in such a way that only a fraction of the listeners can understand you.

DO keep in mind the people in the back row who are not especially experienced in listening to English- language presentations. Native speakers of English need to avoid speaking too fast or colloquially; non- native speakers should enunciate especially clearly so that any foreign accent does not impair comprehension.

DO use your microphone, even if there are not many attendees in your session. Session rooms are still enormous, and you will be on a stage. Remember that the use of a microphone does not in itself guarantee that people in the back can hear you easily: Speak up in a lively manner!

DON’T ignore your Session Chair’s time warnings.

DO pay attention to the Session Chair’s countdown cards. You will receive warnings at five minutes prior, one minute prior, and when time is up. If you do not stop when time is called, your Session Chair will come to the stage to start the Q&A session.

DON’T rush to cover your remaining content if you are running out of time.

DO rehearse your presentation before attending MM, and if you find yourself with a lot more content to cover at the 5-minute mark, resist the temptation to speak faster to finish. Your audience will not remember that much material!

4. Answering Questions

DON'T end your presentation with a slide that contains only an uninformative text like "Any questions?"

DO conclude with a slide summarizing your main contributions, leaving it on the screen except when a question requires you to switch to another slide. (This is one of those rare cases where a bulleted list may be appropriate.) This slide will help people to think of important questions to ask - and also to be impressed by your achievements.

DON'T use a question from the audience as a springboard to leap into the five minutes of your talk that you had to leave out because of the time limit.

DO answer each question directly and concisely, without digressing into related topics. Give others a chance to ask their questions as well.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/oral_presentations.html[1/28/2010 9:24:32 AM] Oral Presentations

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/oral_presentations.html[1/28/2010 9:24:32 AM] Keynote Speakers

Keynote Speakers

SmartWeb: Multimodal Web Services on the Road

Prof. Wolfgang Wahlster, DFKI

Abstract:

SmartWeb provides a context-aware user interface to web services, so that it can support the mobile user in different roles, e.g. as a car driver, a motorbiker, or a pedestrian. It provides a symmetric multimodal dialogue system [2] combining speech, gesture, haptic and video input with speech, haptic, video and acoustic output. It goes beyond traditional keyword search engines like Google by delivering higher quality results that are adapted to the mobile user’s current task and situation. In mobile situations, users don’t want to deal with hypertext lists of retrieved web pages, but simply want an answer to their query. If a desperate driver with a crying and acutely ill child on the backseat asks SmartWeb “Who is the closest paediatrician?” he needs just the name and address of the doctor. Based on SmartWeb’s ability to combine various web services, the driver can then ask SmartWeb a follow-up question about route guidance to the doctor’s practice. One of the innovative features of SmartWeb is that the user can specify whether he wants a textual or pictorial answer, a video clip or a sound file as a query result.

SmartWeb [1] provides not only an open-domain question answering machine but a multimodal web service interface for coherent dialogue, where questions and commands are interpreted according to the context of the previous conversation. For example, if the driver of our Mercedes-Benz R-Class test car asks SmartWeb “Where is the closest Italian restaurant”, it will access a web service to find an appropriate restaurant and show its location on a digital map presented on the large dashboard display. The user may continue his dialog with a command like “Please guide me there with a refueling stop at the lowest price gas station.” In this case, SmartWeb combines a navigation service with a special web service that finds low gas prices. SmartWeb includes plan-based composition methods for semantic web services, so that complex tasks can be carried out for the mobile user.

One version of SmartWeb has been deployed on a BMW motor-bike R1200RT, using a swivel with force feedback integrated in the handle bar. Similar to the control knob known from the iDrive interface of BMW automobiles, the biker can rotate the swivel or push it right or left in order to browse through menus or select items displayed by SmartWeb on the large high-resolution screen in the middle of the cockpit. In combination with these pointing actions, the biker can use speech input over the microphone integrated in a Bluetooth helmet to interact with SmartWeb. The multimodal dialogue system combines visual displays with speech and earcons over the speakers integrated in the helmet and haptic force feedback for output generation. For example, the biker can ask for weather forecasts along his planned route. SmartWeb accesses location-based web services via the bike’s 3G wireless connection to retrieve the relevant weather forecasts. In addition, SmartWeb exploits ad-hoc Wifi connections for vehicle-to-vehicle communication based on a local danger warning ontology so that the motorbike driver can be informed of a danger ahead by a car in front of him. For example, a car detecting a large wedge of water under its wheels will pass the information wirelessly to the bike following it and SmartWeb will generate the warning “Attention! Risk of aquaplaning 100 meters ahead” using the GPS coordinates of both vehicles to compute the distance to the upcoming dangerous area. Another distinguishing feature of SmartWeb is the generation of adaptive multimodal presentations taking into account the predicted cognitive load of the biker depending on the driving speed and other factors.

This keynote presents the anatomy of SmartWeb, its ontology-based information extraction and web service composition technology and explains the distinguishing features of its multimodal dialogue and answer engine.

1. Sonntag, D., Engel, R., Herzog, G., Pfalzgraf, A., Pfleger, N. , Romanelli, M., Reithinger, N.: SmartWeb Handheld: Multimodal Interaction with Ontological Knowledge Bases and Semantic Web Services. In Huang, Th., Nijholt, A., Pantic, M., Pentland, A. (eds.): Artificial Intelligence for Human Computing. Springer, Heidelberg, 2007, 272 – 295 2. Wahlster, W. (ed.): SmartKom: Foundations of Multimodal Dialogue Systems. Springer, Heidelberg, 2006

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/keynote_speakers.html[1/28/2010 9:24:34 AM] Keynote Speakers

Bio:

Dr. Wolfgang Wahlster is the Director and CEO of DFKI, the German Research Center for Artificial Intelligence and a Professor of Computer Science and Computational Linguistics at Saarland University (Saarbrücken, Germany). Founded in 1988, DFKI today is the world’s largest contract research institute with in the field of innovative software technology based on Artificial Intelligence (AI) methods with more than 400 researchers working for DFKI’s industrial shareholders BWM, DaimlerChrysler, EADS, SAP, Microsoft, Deutsche Telekom and Bertelsmann.

Professor Wahlster received his diploma and doctoral degree (1981) in Computer Science from the University of Hamburg, Germany. He has published more than 180 technical papers and 8 books on intelligent multimodal user interfaces. His current research includes multimodal and tangible user interfaces, mobile multimedia interfaces for Car2X systems, user modeling, ambient intelligence, embodied conversational agents, and mobile access to semantic web services.

Wahlster has received numerous honors and awards for his research contributions. He is an AAAI Fellow (elected in 1993), an ECCAI Fellow (since 1999), and a GI Fellow (since 2004). In 2001, the President of the Federal Republic of Germany presented the German Future Prize to Professor Wahlster for his work on language technology and intelligent user interfaces. He was the first computer scientist to receive Germany's highest scientific prize that is awarded each year for outstanding innovations in technology, engineering, or the natural sciences. He was the first German computer scientist elected Foreign Member of the Royal Swedish Nobel Prize Academy of Sciences, Stockholm in 2003. Currently, he is serving as the chief scientific advisor of the German government for IT in the framework of the national high-tech funding strategy.

Insights into Future Mobile Multimedia Applications

Dr. Minoru Etoh , Research Laboratories, NTT DoCoMo

Abstract:

TBD

Bio:

Minoru Etoh is Deputy Managing Director of Research Laboratories at NTT DoCoMo, Japan.

In the 90's, he was leading an image communication research team in Matsushita Electric and participated in MPEG-4 standardization as one of major video CODEC architects. He joined Multimedia Laboratories of NTT DoCoMo in 2000, where he contributed to launching DoCoMo’s 3G mobile multimedia services including video phones and audio-visual content download applications. He was also appointed at Managing Director of DoCoMo USA Labs in 2002 and Multimedia Labs in 2005 respectively. His expertise covers a wide range of mobile multimedia: network architecture, terminal software, coding technologies, media delivery over mobile networks, and MPEG / ITU-T / 3GPP / W3C/ IETF standardization activities. Minoru Etoh received his B.E. and M.S.E.E. from Hiroshima University, Ph.D. degree from Osaka University, in 1983, 1985 and 1993 respectively.

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/keynote_speakers.html[1/28/2010 9:24:34 AM] App Keynote Speakers

Applications Keynote Speakers

Applied Image Science - From Consumers' Digital Files to Tangible Image Product

Dr. Fageth, CeWe Color

Abstract:

The market for picture capturing devices is booming and as a result, household penetration is increasing rapidly. In the traditional analogue market, prints from processed film were the only, albeit a very convenient, way of sharing and archiving memories in albums or in the famous shoebox. Nowadays innovative developments have given rise to new ways to view, share and archive images.

Image taking habits are also changing. People are afraid of not “capturing the moment” and nowadays pressing the shutter is not directly linked to cost as was the case with silver halide photography. This behavior seems to be convenient but can result in a dilemma for the consumer. This paper presents tools designed to help the consumer overcome the time-consuming image selection process while turning the chore of selecting the images for prints, or of placing them automatically into a photo book, into a fun experience.

The digital files processed by these tools originate from various sources. These files are transferred into a production process either in a modified or in their original state. The device origin might be a high resolution SLR camera or a low resolution mobile phone camera. The customer expects all of these images, regardless of source, to be printed in the perfect quality he/she is accustomed to from analog film processing. Customers often expect an even higher standard of quality due to the elevated retail price of DSCs. Digital photo services also offer the customer the option of a simple order process, enabling them to order a variety of image formats which cannot be printed on a single machine. Therefore, color management and the enhancement tools used on different types of machines play a very important role, especially with regard to online photo services which also offer products which do not necessarily have to be printed on light-sensitive photo paper, e.g. calendars, greeting cards, etc. These products are printed using different technologies, e.g. digital printers such as the hp Indigo or Xerox machines. The customer expects to receive both prints and personalized photo creations in exactly the same quality.

This paper will also describe how non-virtual products from pictures taken by digital devices can be implemented in the wholesale industry, regardless of image resolution and source, in order to fulfill the consumers’ requirements (delivery time and quality). The goal when selling these products is convenience and quality of the whole industrially finished product.

Bio:

Reiner Fageth studied electronic engineering at the Fachhochschule Heilbronn, Germany. He received a Ph.D. from the University of Northumbria at Newcastle, UK in split research with Telefunken Microelectronic and the Steinbeis Transferzentrum Image Processing in 1994. The major research topics there and also for the following years were industrial image processing systems based on classification using fuzzy logic and neural networks.

In 1998 he joined CeWe Color with the change to drive the analogue photo business into digital. First he was responsible for R&D and the production of consumers digital files on silver halide paper. CeWe Color is Europe largest wholesale photofinisher producing more than 3 billion prints a year.

Applications to transfer these files via the Internet, kiosk systems in retail shops and mobile applications have been developed and introduced successfully into the market. Recently digital services have been extended to more complex products such as photo books printed on digital presses. January 2007 he was appointed CTO of the company.

He is a member of the German DIN Normenausschuss Bild und Film NA 049-00-04 AA and has published over 30

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/app_keynote_speakers.html[1/28/2010 9:24:35 AM] App Keynote Speakers

technical papers.

The Workplace of the Future

Prof. Dr. Lutz Heuser (SAP AG)

Abstract:

The workplace of the future will support the user to cope with a flexible change of multiple processes and tasks. The actual work context is observed by the system and this will be utilized to support the user with relevant information as well as recommendations to proceed in his work. Interaction channelsand presentation means are chosen adaptively; needed knowledge and information is provided pro-actively and in direct context of the work performed. The user will have tightly integrated direct access to different services by mesh up techniques. He will ollaborate via informal social networks provided by various Web 2.0 services (e.g., forums, weblogs, wikis, and Xing). Domain experts will be identified automatically through an expert finder which is driven by social mining and advanced machine learning technologies. The user will be able to change the system by the use of end-user development facilities to adapt his working environment to his actual needs and specific environments. These methodologies and technologies have been investigated in a varying depth in the research community. However, only a proper combination will lead to the desired user experience. Knowing about the (business) processes the user is involved in supports this and will form the workplace of the future significantly. Business processes are not necessarily IT- based or IT-supported.

Bio:

Professor Lutz Heuser, Vice President SAP Research and Chief Development Architect at SAP AG, is responsible for the overall research portfolio management and the corporate venturing organization. His areas of expertise include collaborative business processes; ubiquitous computing and its integration into business applications; blended learning as part of corporate and non-corporate training; as well as security in corporate applications.

Professor Heuser joined SAP AG in 1999. Prior to his appointment at SAP AG, he was director of the European Research Organization at Digital Equipment Corporation and member of the extended executive board of the German subsidiary of Digital Equipment.

Professor Heuser serves on the advisory boards of imedia, Providence, FhG-Fokus, Berlin, and the D-Grid initiative.

Professor Heuser is a Visiting Professor at the National University of Paraguay and an Adjunct Professor of the Queensland University of Technology in Brisbane. In 2004, he was awarded an Honorary Professorship at the Technical University Darmstadt and in 2006 he became a member of acatech: the “Council for Engineering Sciences at the Union of the German Academies of Science and Humanities."

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/app_keynote_speakers.html[1/28/2010 9:24:35 AM] Student Grants

Student Conference Participation Grant

The ACM Multimedia conference is the main annual conference of the ACM SIGMM. It provides a great opportunity for researchers to present their work, get acquainted with the work of others, and discuss with colleagues both junior and senior. To promote this form of cooperation, the SIG and its sponsors make conference participation grants available for several students.

A grant is meant to support personal attendance of one student at the main conference by paying the advance registration fee for students as well as a ticket for the conference banquet. The grant will not cover fees for workshops or tutorials. Individual grants may cover additional expenses subject to conditions of individual sponsors. Students will have to make their own arrangements for travel and accommodation.

All students can apply, but regional and institutional diversity will be considered in the selection process. Additionally, students being the primary author of an accepted paper will be given preference in the selection process.

To apply for a grant, a faculty member of the student's host institution must send an email to Chitra Dorai ([email protected]) with the subject "ACM MM Student Conference Participation Grant."

Students are encouraged to have the application sent as soon as possible. The application must be sent in ASCII in the email body no later than July 13, 2007. Applications arriving after the deadline will not be considered. The notification date is July 25, 2007. Decisions made are final.

Please include the following information in an application:

1. the student's full name and email address 2. the name and nationality of the institution 3. the student's academic status and expected year of graduation 4. whether the student is (co-)author of a paper that was accepted for the main conference or if the student contributes to any other part of the conference 5. if the student is a (co-)author, the paper title, author list, the student's contribution to the paper, and whether the student will present the paper 6. the reason for applying for the grant, including the expected benefits that the students will have from attending the conference and including the funding status of the student 7. a brief statement by the student about his or her current research interests and research accomplishments to date

We look forward to receiving your applications!

file:///C|/Documents%20and%20Settings/hsu.cheng-hsin/Desktop/acmmm07/student_grants.html[1/28/2010 9:24:37 AM]

CONTENTS

FOREWORD ...... 3 MAPS ...... 7

AUGSBURG TRAM LINES ...... 7 LIVE ARTS EXHIBITION ...... 8 CONFERENCE SITE MAP...... 9 FLOOR PLANS ...... 10 1: Keynote and Best Paper Sessions ...... 10 2: Conference Sessions, Workshops, and Tutorials ...... 10 OVERVIEW OF THE FULL CONFERENCE PROGRAM ...... 11

MONDAY, SEPTEMBER 24 ...... 11 TUESDAY, SEPTEMBER 25 ...... 11 WEDNESDAY, SEPTEMBER 26 ...... 12 THURSDAY, SEPTEMBER 27 ...... 12 FRIDAY, SEPTEMBER 28 ...... 13 MIR 2007 - Workshop on Multimedia Information Retrieval ...... 13 MV 2007 - Workshop on Mobile Video ...... 13 TVS 2007 - TRECVID Video Summarization ...... 13 HCM 2007 - Human-Centered Multimedia ...... 13 MS 2007 - The Many Faces of Multimedia Semantics ...... 13 EMME 2007 - Educational Multimedia and Multimedia Education ...... 13 SATURDAY, SEPTEMBER 29 ...... 13 MIR 2007 Workshop on Multimedia Information Retrieval ...... 13 HALF-DAY TUTORIALS ...... 15

MONDAY, SEPTEMBER 24, 2007 ...... 15 MAIN CONFERENCE FULL PROGRAM ...... 17

TUESDAY, SEPTEMBER 25, 2007 ...... 17 WEDNESDAY, SEPTEMBER 26, 2007 ...... 25 THURSDAY, SEPTEMBER 27, 2007 ...... 33 WORKSHOPS ...... 37

FRIDAY, SEPTEMBER 28, 2007 ...... 37 MIR 2007 - Workshop on Multimedia Information Retrieval ...... 37 MV 2007- Workshop on Mobile Video 2007 ...... 41 TVS 2007 - TRECVID Video Summarization ...... 45 HCM 2007- Human-Centered Multimedia ...... 47 MS 2007 - The Many Faces of Multimedia Semantics ...... 49 EMME 2007- Educational Multimedia and Multimedia Education ...... 51 SATURDAY, SEPTEMBER 29, 2007 ...... 55 MIR 2007 - Workshop on Multimedia Information Retrieval ...... 55 CO-SPONSORS ...... 57 SUPPORTERS ...... 57 CONFERENCE ORGANIZATION ...... 59

1

FOREWORD

Welcome to the Fifteenth ACM International Conference on Multimedia (ACM MM 2007), held September 24-29, 2007 at University of Augsburg in the beautiful and historic city of Augsburg, Bavaria, Germany. The city was founded 15 BC in the reign of Roman emperor Augustus.

ACM Multimedia is the premier annual professional meeting for communicating the state-of-the- art in multimedia research, technology, and art. As in previous years, starting with the first ACM Multimedia conference in 1993, the conference seeks to bring together researchers and practitioners in academia, industry, and government who are interested in exploring and exploiting new and multiple media to create new capabilities for human expression, communication, collaboration, and interaction. ACM Multimedia covers all aspects of multimedia computing: from underlying technologies to applications, theory to practice, and servers to networks to devices.

Multimedia is an interdisciplinary endeavor, and the variety of conference events reflects this. The overall conference encompasses three major parts: interesting tutorials on Monday, September 24, an exciting three-day main conference on Tuesday through Thursday, September 25-27, and a set of workshops in hot multimedia areas on Friday and Saturday, September 28-29.

The three-day main conference comprises several different technical program elements, each with separate submissions and reviewing: full papers, short papers, a panel, the doctoral symposium, a Brave New Topics session, technical demonstrations, a video program, an open source contest, and the Interactive Arts Program. We are excited to host two research keynote presentations by Prof. Wolfgang Wahlster of DFKI and the University of Saarland and Dr. Minoru Etoh of NTT DoCoMo, who will give unique perspectives of their research work in academia and industry. In addition two high-profile applications keynotes will be given by Dr. Fageth of CeWe Color, Europe's number one photo services company, and Prof. Lutz Heuser of SAP AG.

The program co-chairs for ACM MM 2007 are Alan Hanjalic, Sunghyun Choi, Brian Bailey, and Nicu Sebe, who were responsible, along with a program committee of 137 members, for selecting the long paper program in the areas of Content, Applications, Systems, and Multimedia Interactions. These tracks received 298 long paper submissions (113 in Content, 90 in Applications, 64 in Systems, and 30 in Multimedia Interactions). Each paper was reviewed by at least three qualified reviewers in a double-blind review process. The program committee met on June 14, 2007 in Delft, Netherlands to discuss the papers and make final selections for papers to be included as oral presentations in the conference program. This rigorous review process resulted in the acceptance of 57 long papers: 19 in the Content track, 18 in the Applications track, 13 in the Systems track, and 7 in the newly introduced Multimedia Interactions track. This represents an acceptance rate of 19 percent. We heartily thank the program co-chairs and the program committee members for their outstanding and dedicated work.

The short paper program received a record number of 255 submissions (a 43% increase over the previous year) and, after a thorough review process, accepted 70 papers resulting in an acceptance rate of 27 percent. These short papers will be presented during poster sessions at the conference. Many thanks to the short paper program co-chairs Chitra Dorai, Julien Laganier, and Susanne Boll for an excellent job.

3 We also wish to acknowledge and thank the co-chairs of the demonstration program, Wei-Ying Ma and Milind Naphade; the chair of the video program, Thomas Haenselmann; the co-chairs of the doctoral symposium, Thomas Plagemann and Vera Goebel; the new foundations co-chairs, Edward Chang and Shin'ichi Satoh; the open source competition chair, Apostol Natsev; and the panel co-chairs, Yap-Peng Tan and Mohan Kankanhalli. These chairs put in an enormous amount of work to bring us a diverse, high quality conference, and their contributions are much appreciated.

The Interactive Arts Program includes long and short papers as well as an exhibition that is housed at the new building site of the school of design at the University of Applied Sciences Augsburg. We are in particular grateful to the school of design, not only because we are the first that are allowed to use the new building but also as the location is nicely situated between the city centre and the conference location.

The exhibition will run throughout the conference, and we encourage all attendees while they are on their way to or from the conference to view these novel works of art utilizing a rich variety of media. The Interactive Arts Program chairs - Frank Nack, Alejandro Jaimes, and Thomas Rist - did a wonderful job, working with their exhibition curators and program committee, to put together a first-rate arts program to complement the technology focus of the main conference. The competition was high and only 16 % of the submissions made it into the exhibition. We thank the co-chairs, but in particular Thomas Rist who took the largest burden as local chair, and all those who helped to organize and run this program.

This year’s conference schedule begins with seven half-day tutorials on a wide range of topics of interest to the multimedia community, from introductory to advanced, from machine learning for multimedia to a programming course for mobile phones, adeptly organized by the tutorial co-chairs Benoit Huet and Malcolm Slaney. After the main conference, six workshops are held on the final two days. Workshop co-chairs Belle Tseng and Daniel Gatica-Perez have done a great job working with the individual workshop chairs to ensure that these run smoothly.

We also wish to acknowledge and thank the publicity co-chairs, Wolfgang Effelsberg, Yong Rui, and Alf Zugenmaier; the registration co-chairs, Yi Wu, Marc Emmelman and Eva Hörster; the treasurer, Barbara de Vega; the technical program coordinator, Chitra Dorai; and the web chairs, Benedikt Gleich and Simon Hoffmann. These colleagues all contributed tremendously to the success of the conference. The proceedings chair, Roger Zimmermann, did an outstanding job putting together these multi-faceted proceedings. Special thanks go to the local arrangements co-chairs Gregor van den Boogaart, Jochen Lux, Simon Hoffmann and Susanne Boll, who worked tirelessly to ensure that the myriad details of the conference venue were addressed, including dealing with the inevitable emergencies and surprises along the way.

Thanks to the ACM and their special interest groups, SIGMM and SIGGRAPH, for co-sponsoring this event, and to Barbara de Vega for being always available to organize and think through the many little thinks that came up during the planning of this conference. We would also like to thank our supporters: CeWe Color, FXPAL, Google, IBM, Microsoft Research, SAP, Yahoo! Research, DoCoMo Comm. Labs Europe, MAN Roland, NEC, Philips Research, Ricoh, and the University of Augsburg for providing us with the nice conference facilities in the large lecture hall building of the physics department. We also thank the University of Applied Sciences Augsburg for hosting the arts program. Their generous support made several key aspects of the conference possible, including the various prizes, student travel, and the Interactive Arts Program. IBM awarded a student travel grant which enabled more students to attend the

4 conference. In this context we would also thank Arnon Amir for his hard work as the sponsoring chairs.

Finally, we wish to thank all of the contributors in every category; the work you do is the reason this conference exists. We invite all attendees to actively participate in the week’s activities: listen, learn, discuss, debate, appreciate, suggest, encourage, enlighten, and be enlightened.

Rainer Lienhart Anand R. Prasad MM’07 General Co-chair MM’07 General Co-chair University of Augsburg, DoCoMo Comm. Labs Europe GmbH, Augsburg Munich

5

MAPS

AUGSBURG TRAM LINES

7 The map on the previous page shows the Augsburg tram lines and how they connect the various conference sites. All tram lines intersect at Königsplatz, the city’s main transportation hub. To change lines, you have to go to Königsplatz first. Also, many conference hotels are within walking distance from Königsplatz.

The most important tram line for the conference members is tram number 3, with the end points ‘Stadtbergen’ and ‘Inninger Str.’, respectively. Line 3 connects the Augsburg central train station with the University of Applied Sciences (called Fachhochschule Augsburg, location of arts exhibitions) and the campus of the University of Augsburg (the main conference site). The end point of the tram line is always being displayed on the front and sides of the tram. It tells you in which direction the tram is currently travelling. Inside the tram, the next stop is always being announced and/or displayed.

To get to either conference site from downtown Augsburg, take line 3 in direction ‘Inninger Str.’. It leaves at Königsplatz platform ‘F’ every 5 to 10 minutes, depending on the current day and time.

The live arts exhibition at the University of Applied Sciences (Fachhochschule Augsburg) is only two stops away from Königsplatz: after getting off the tram at ’Rotes Tor’, it is just a three-minute walk along ‘Rote-Torwall-Staße’” to the Fachhochschule (see separate map below).

The University campus is roughly a 10 minute ride from Königsplatz. The stop to get off the tram is called ‘Universität’. You will find yourself right at the spot marked with an ‘H’ and labeled “Straßenbahnlinie 3 – Haltestelle Universität” as shown on the map on the previous page.

To get back to downtown from either site, get on any line 3 tram towards Stadtbergen. It will arrive at Königsplatz platform ‘G’. From there, you can either walk back to your hotel (in most cases), or change tram and bus lines, or catch a taxi.

LIVE ARTS EXHIBITION (at Fachhochschule Augsburg/University of Applied Sciences, Fakultät für Informatik)

The live arts exhibition takes place in the building marked „KLM“ on the right. The tram stop “Rotes Tor” is shown to the left. Simply follow “Rote-Torwall-Str.” along the ancient city walls.

8 CONFERENCE SITE MAP

9 FLOOR PLANS

1: KEYNOTES, BEST PAPER SESSION Hörsaal 1 (HS1)

2: CONFERENCE SESSIONS, TUTORIALS, WORKSHOPS Institut für Physik – Hörsaalzentrum

1st Floor 2nd Floor

10

OVERVIEW OF THE FULL CONFERENCE PROGRAM

MONDAY, SEPTEMBER 24

Room 1003 2001 2002 2003

Tutorial: Bayesian Tutorial: Mobile Tutorial: MPEG Tutorial: Digital 08:30-10:00am Methods Phone Programming Inpainting

Tea & Coffee Break Tutorial: Bayesian Tutorial: Mobile Tutorial: MPEG Tutorial: Digital 10:30am-noon Methods Phone Programming Inpainting

Lunch Break Tutorial: Active Tutorial: Human Tutorial: Large 1:30-3:00pm Learning Centered Systems Data Methods

Tea & Coffee Break Tutorial: Active Tutorial: Human Tutorial: Large 3:30-5:00pm Learning Centered Systems Data Methods

TUESDAY, SEPTEMBER 25

Room HS1 1001 1002 1004 2001+2002 2003+Hallway other

8:30-9:00am Opening

9:00-10:00am Keynote I

Tea & Coffee Break Best 10:30am- 10:30- Paper 5:30pm: 12:30am Session Keynote I demo Lunch (Hörsaal- zentrum) 2:00-3:30pm Content 1 App. 1 Systems 1 Demos 1

Tea & Coffee Break 4:00-5:30pm Content 2 App. 2 HCI 1 Posters 1 4:00- 10:00pm: Live Arts Exhibition 6:30-7:30pm Welcome - Goldener Saal (Rathaus / City Hall) (University of Applied 7:30-10:00pm Conference Reception & Live Arts Exhibition Sciences)

11

WEDNESDAY, SEPTEMBER 26

Room HS1 1001 1002 1004 2001+2002 2003+Hallway

App. 8:30-10:00am Keynotes

Tea & Coffee Break Content 10:30am-noon App. 3 Arts 1 Demos 2 3

Lunch & ACM Business Meeting

Content Posters 2 1:30-3:00pm BNT 1 HCI 2 4 Arts Posters

Tea & Coffee Break 3:00- 7:00pm BNT 2 Systems Live Arts 3:30-5:00pm Arts 2 Posters 3 Exhibition App. 4 2 (Univ. of Applied Sciences) 7:00 - 11:00pm Conference Banquet (Kurhaus Göggingen)

THURSDAY, SEPTEMBER 27

Room HS1 1001 1002 1003 1004

9:00- 10:00am Keynote II

Tea & Coffee Break 10:30am- noon Content 5 App. 5 Arts 3 Systems 3

Lunch 1:30- Doctorial 3:00pm Content 6 Open Source Symposium Systems 4

Tea & Coffee Break 3:00- 7:00pm 3:30- Live Arts 5:00pm Panel App. 6 Video Session Exhibition

12

FRIDAY, SEPTEMBER 28

MIR 2007 - WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL September 28 - 29, 2007 Location: 1001

MV 2007 - WORKSHOP ON MOBILE VIDEO September 28, 2007 Location: 1002

TVS 2007 - TRECVID VIDEO SUMMARIZATION September 28, 2007 Location: 1004

HCM 2007 - HUMAN-CENTERED MULTIMEDIA September 28, 2007 Location: 1003

MS 2007 - THE MANY FACES OF MULTIMEDIA SEMANTICS September 28, 2007 Location: 2003

EMME 2007 - EDUCATIONAL MULTIMEDIA AND MULTIMEDIA EDUCATION September 28, 2007 Location: 2002

SATURDAY, SEPTEMBER 29

MIR 2007 WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL September 28 - 29, 2007 Location: 1001

13

Monday, September 24, 2007 HALF-DAY TUTORIALS

MONDAY, SEPTEMBER 24, 2007

8:30am - noon – Morning Tutorials

Tutorial: Bayesian Methods for Multimedia Signal Processing Location: 1003 A. Taylan Cemgil

Tutorial: Digital Inpainting Location: 2003 Timothy K. Shih

Tutorial: MPEG Multimedia Standards: Evolution and Future Developments Location: 2002 Fernando Pereira

Tutorial: Mobile Phone Programming for Multimedia Location: 2001 Jürgen Scheible

1:30 - 5:00 pm – Afternoon Tutorials

Tutorial: Active Learning for Multimedia Location: 1003 Georges M. Quénot

Tutorial: Large Data Methods for Multimedia Location: 2003 Michael A. Casey, Frank Kurth

Tutorial: Human-Centered Multimedia Systems Location: 2001 Alejandro Jaimes, Nicu Sebe

15

Tuesday, September 25, 2007 MAIN CONFERENCE FULL PROGRAM

TUESDAY, SEPTEMBER 25, 2007

8:30 - 9:00am – Conference Opening Remarks Location: HS 1 Session Chair: Anand Prasad, Rainer Lienhart

9:00 - 10:00am – Keynote Presentation Location: HS 1 Session Chair: Rainer Lienhart

SmartWeb: Multimodal Web Services on the Road Prof. Wolfgang Wahlster - DFKI

______

10:00 - 10:30am – Tea & Coffee Break (sponsored by Ricoh) Location: Hallway ______

10:30 - 12:30am – Best Paper Session Location: HS 1 Session Chair: Alan Hanjalic

Correlative Multi-Label Video Annotation Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Jinhui Tang, Tao Mei, Hong-Jiang Zhang

Re-Cinematography: Improving the Camera Dynamics of Casual Video Michael L. Gleicher, Feng Liu

Rate Allocation for Multi-User Video Streaming over Heterogeneous Access Networks Xiaoqing Zhu, Piyush Agrawal, Jatinder Pal Singh, Tansu Alpcan, Bernd Girod

Media Adaptation Framework in Biofeedback System for Stroke Patient Rehabilitation Yinpeng Chen, Weiwei Xu, Hari Sundaram, Thanassis Rikakis, Sheng-Min Liu

______

10:30am - 5:30pm – Keynote Demo Location: Outside in front of lecture hall building Session Chair: Gregor van den Boogaart

The team of Prof. Dr. Wolfgang Wahlster is demoing the concepts they he has introduced during his talk on SmartWeb: Multimodal Web Services on the Road

17 Tuesday, September 25, 2007 ______

12:30am - 2:00pm – Conference Lunch (sponsored by FXPAL) Location: Mensa ______

2:00 - 3:30pm – Content 1: Content Analysis Applications Location: 1001 Session Chair: Apostol Natsev

Trajectory Based Event Tactics Analysis in Broadcast Sports Video Guangyu Zhu, Qingming Huang, Changsheng Xu, Yong Rui, Shuqiang Jiang, Wen Gao, Hongxun Yao

A Computation Method for Video Segmentation Utilizing the Pleasure-Arousal-Dominance Emotional Information Sutjipto Arifin, Peter Y. K. Cheung

Can We Trust Digital Image Forensics? Thomas Gloe, Matthias Kirchner, Antje Winkler, Rainer Böhme

______

2:00 - 3:30pm – Applications 1: Enhancing User Experiences Location: 1002 Session Chair: Lloyd Rutledge

The Kindest Cut: Enhancing the User Experience of Mobile TV through Adequate Zooming Hendrik Knoche, Marco Papaleo, M. Angela Sasse, Allesandro Vanelli-Coralli

Multi-Scale Video Cropping Hazem El-Alfy, David Jacobs, Larry Davis

Enriching SMIL with Assertions for Temporal Validation Annalisa Bossi, Ombretta Gaggi

______

2:00 - 3:30pm – Systems 1: Streaming Location: 1004 Session Chair: Ketan Mayer-Patel

Improving VoD Server Efficiency with BitTorrent Yung Ryn Choe, Derek L. Schuff, Jagadeesh M. Dyaberi, Vijay S. Pai

On the Minimum Delay Peer-to-Peer Video Streaming: How Realtime Can It Be? Yong Liu

Playout Scheduling and Loss-Concealments in VoIP for Optimizing Conversational Voice Communication Quality Batu Sat, Benjamin W. Wah

18 Tuesday, September 25, 2007 2:00 - 3:30pm – Demo Session 1 Location: Seminar Rooms 2001 & 2002 Session Chair: Wei-Ying Ma

OLIVE - A Conceptual Web Image Search Engine Adrian Popescu, Pierre Alain Moëllic

Person-Based Search in Videos Bart Kroon, Sabri Boughorbel, Alan Hanjalic

Intelligent Browsing of Concert Videos Suphi Umut Naci, Alan Hanjalic

Atomique: A Photo Repository for Decentralized and Distributed Photo Sharing on the Web Marian Dörk, Andreas Nürnberger, Javier Velasco Martín

An Object Recognition System for Automatic Image Annotation and Browsing of Object Catalogs Michela Lecca, Stefano Messelodi, Claudio Andreatta

Demo SPP: A Demonstrator for a Scalable P2P VoD Infrastructure Piotr Srebrny, Karl-André Skevik, Vera Goebel, Thomas Plagemann

Fast Annotation of Video Objects for Interactive TV Helmut Neuschmied, Remi Trichet, Berard Merialdo

An Image-based Outdoor Place Recognition and Information Retrieval System Hanlin Goh, Yiqun Li, Joo-Hwee Lim mediaWalker: A Video Archive Explorer based on Time-Series Semantic Structure Ichiro Ide, Tomoyoshi Kinoshita, Tomokazu Takahashi, Shin'ichi Satoh, Hiroshi Murase

Statistical Summarization of Content Features for Fast Near-duplicate Video Detection Heng Tao Shen, Xiaofang Zhou, Zi Huang, Jie Shao

Logo Seeker: A System for Detecting and Matching Logos in Natural Images Subhajit Sanyal, Srinivasan H. Sengamedu

______

3:30 - 4:00pm – Tea & Coffee Break (sponsored by DoCoMo Euro-Labs) Location: Hallway ______

4:00 - 5:30pm – Content 2: Video Structuring Location: 1001 Session Chair: Alan Smeaton

Novelty Detection for Cross-Lingual News Stories with Visual Duplicates and Speech Transcripts Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo

Efficient Spatiotemporal-Attention-Driven Shot Matching Shan Li, Moon-Chuen Lee

19 Tuesday, September 25, 2007 Cross-Domain Video Concept Detection Using Adaptive SVMs Jun Yang, Rong Yan, Alexander G. Hauptmann

______

4:00 - 5:30pm – Applications 2: Browsing and Searching Video Location: 1002 Session Chair: Berna Erol

The Use of Topic Evolution to help Users Browse and Find Answers in News Video Corpus Shi-Yong Neo, Yuanyuan Ran, Hai-Kiat Goh, Yan-Tao Zheng, Tat-Seng Chua, Jintao Li

Video Search Re-Ranking via Multi-Graph Propagation Jingjing Liu, Wei Lai, Xian-Sheng Hua, Yalou Huang, Shipeng Li

Practical Elimination of Near-Duplicates from Web Video Search Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo

______

4:00 - 5:30pm – HCI 1: New Media Interaction Location: 1004 Session Chair: Nicu Sebe

Generating Views of the Buzz: Browsing Popular Media and Authoring using Mixed-Initiative Composition Eunyee Koh, Andruid Kerne, Andrew Webb, Sashikanth Damaraju, David Sturdivant

Beyond "Beyond Being There": Towards Multiscale Communication Systems Nicolas Roussel, Sofiane Gueddana

Interactive Video Browsing on Mobile Devices Wolfgang Hürst, Georg Götz, Martina Welte

______

4:00 - 5:30pm – Poster Session 1: Content Analysis Location: Hallway and Seminar Room 2003 Session Chair: Julien Laganier

Reliability-Based 3D Reconstruction in Real Environment Hansung Kim, Ryuuki Sakamoto, Itaru Kitahara, Tomoji Toriyama, Kiyoshi Kogure

Broadcast News Story Segmentation Using Social Network Analysis and Hidden Markov Models Alessandro Vinciarelli, Sarah Favre

Color Conceptualization Xiaodi Hou, Liqing Zhang

Human Behaviour Consistent Relevance Feedback Model for Image Retrieval Jing Liu, Zhiwei Li, Mingjing Li, Hanqing Lu, Songde Ma

20 Tuesday, September 25, 2007 Cross-modal Correlation Learning for Clustering on Image-Audio Dataset Hong Zhang, Yueting Zhuang, Fei Wu

Gradual Transition Detection with Conditional Random Fields Jinhui Yuan, Jianmin Li, Bo Zhang

Image Classification Using Tensor Representation Ziming Zhang, Syin Chan, Liang-Tien Chia

The Importance of Query-Concept-Mapping for Automatic Video Retrieval Dong Wang, Xirong Li, Jianmin Li, Bo Zhang

Mining Repetitive Clips through Finding Continuous Paths Junsong Yuan, Wei Wang, Jingjing Meng, Ying Wu, Dongge Li

Segregated Feedback with Performance-based Adaptive Sampling for Interactive News Video Retrieval Huan-Bo Luan, Shi-Yong Neo, Hai-Kiat Goh, Yong-Dong Zhang, Shou-Xun Lin, Tat-Seng Chua

Typicality Ranking via Semi-Supervised Multiple-Instance Learning Jinhui Tang, Xian-Sheng Hua, Guo-Jun Qi, Xiuqing Wu

Feature Selection Using Principal Feature Analysis Yijuan Lu, Ira Cohen, Xiang Zhou, Qi Tian

Region-Based Visual Attention Analysis with Its Application in Image Browsing on Small Displays Huiying Liu, Shuqiang Jiang, Qingming Huang, Changsheng Xu, Wen Gao

Singing Voice Detection using Perceptually-Motivated Features Tin Lay Nwe, Haizhou Li

Deriving Semantics for Image Clustering from Accumulated User Feedbacks Yanhua Chen, Manjeet Rege, Ming Dong, Farshad Fotouhi

Clustering Web Images with Multi-modal Features Manjeet Rege, Ming Dong, Jing Hua

Image Matting Using Linear Optimization Shifeng Chen, Zhenguo Li, Jianzhuang Liu, Xiaoou Tang

Video Annotation by Graph-Based Learning With Neighborhood Similarity Meng Wang, Tao Mei, Xun Yuan, Yan Song, Li-Rong Dai

Combining Stroke-based and Selection-based Relevance Feedback for Content-based Image Retrieval Jingyu Cui, Changshui Zhang

Temporal Feature Induction for Baseball Highlight Classification Michael Fleischman, Brandon Roy, Deb Roy

A Real-Time Augmented-Reality System for Sports Broadcast Video Enhancement Jungong Han, Dirk Farin, Peter H.N. de With

21 Tuesday, September 25, 2007 Enhancing Image Annotation by Integrating Concept Ontology and Text-based Bayesian Learning Model Rui Shi, Chin-Hui Lee, Tat-Seng Chua

Refining Video Annotation by Exploiting Pairwise Concurrent Relation Zheng-Jun Zha, Tao Mei, Xian-Sheng Hua, Guo-Jun Qi, Zengfu Wang

Multi-layer Multi-Instance Kernel for Video Concept Detection Zhiwei Gu, Tao Mei, Xian-Sheng Hua, Jinhui Tang, Xiuqing Wu

Detecting and Segmenting Humans in Crowded Scenes Mikel D. Rodriguez, Mubarak Shah

A 3-Dimensional SIFT Descriptor and its Application to Action Recognition Paul Scovanner, Saad Ali, Mubarak Shah

Zurfer: Mobile Multimedia Access in Spatial, Social and Topical Context Amy Hwang, Shane Ahern, Simon King, Mor Naaman, Rahul Nair, Jeannie Yang

______

4:00 - 10:00pm – Live Arts Exhibition Location: University of Applied Sciences Augsburg Session Chair: Thomas Rist

Amagatana – the mystical sword Yuichiro Katsumoto, Masa Inakage

The Ball in The Hole – interactive video installation Eleonora Maria Irene Oreggia, Silvano Galliani

Ghost(s) / Fantôme(s) – a participative video-data processing installation Vincent Levy miXer: The Communication Entertainment Content by using "Entrainment Phenomenon" and "Bio-Feedback" Tomohisa Tomida, Anna Ishihara, Ueki Atsuro, Yoshitaka Tomari, Kensuke Fukushima, Masa Inakage

One Million Heartbeats – an interactive art installation that collects one million heartbeats from participants Su-Chu Hsu, Jin-Yao Lin, Carven Chen, Ying-Chung Chen, Jiun-Shian Lin, Keng-Hau Chang

Space of two categories – interactive installation with shadow projection Hanna Haaslahti, Seppo Heikkilä

SpherAleas – a tridimensional interactive / sound / image installation Gregory Lasserre, Anais met den Ancxt

Conversation Piece – a speech-based interactive art installation Alexa Wright, Alf Linney, Mike Lincoln, Alun Evans

22 Tuesday, September 25, 2007 TypeTrace – an interactive application that records all the keyboard strokes you make, similar to spyware Takumi Endo

Will.0.w1sp – an interactive installation exploring our ability to recognise human motion without human form Kirk A. Woolford

______

6:30 - 10:00pm – Conference Reception (sponsored by Microsoft Research)

The conference reception will start at 6:30pm in the Golden Hall of the Town Hall, where wine and brezels will be served and the mayor of Augsburg is giving his welcome. At around 7:30pm we will walk over to the new computer science building of the University of Applied Sciences Augsburg, where the actual reception will take place while everybody can enjoy the highly creative interactive arts exhibition.

6:30 - 7:30pm – Golden Hall at the Town Hall of Augsburg

The Town Hall that was built by Elias Holl between 1615 to 1620. It is the landmark of the city and it is also said to be the most significant secular Renaissance building north of the Alps. The restored Golden Hall is famous for its magnificent, pompous portals, coffered ceiling and mural paintings. The Perlach Tower next to the Town Hall offers a spectacular panoramic view of Augsburg and is open from May to October.

7:30 - 10:00pm –Reception and Arts Exhibition Location: Unversity of Applied Science Augsburg (Fachhochschule Augsburg), Fakultät für Informatik, Friedberger Straße 2 a, 86161 Augsburg

23

Wednesday, September 26, 2007

WEDNESDAY, SEPTEMBER 26, 2007

8:30 - 10:00am – Applications Keynotes Location: HS 1 Session Chair: Arnon Amir

Applied Image Science - From Consumers' Digital Files to Tangible Products Dr. Reiner Fageth - CeWe Color

The Workplace of the Future Prof. Lutz Heuser – SAP AG ______

10:00 - 10:30am – Tea & Coffee break (sponsored by NEC) Location: Hallway ______

10:30 - noon – Content 3: Multimedia Model Learning Location: 1001 Session Chair: Hari Sundaram

Automatic Object Model Acquisition and Object Recognition by Integrating Linguistic and Visual Information Tomohide Shibata, Norio Kato, Sadao Kurohashi

Tagging over Time: Real-world Image Annotation by Lightweight Meta-learning Ritendra Datta, Dhiraj Joshi, Jia Li, James Z. Wang

Spectral Regression: A Unified Subspace Learning Framework for Content-Based Image Retrieval Deng Cai, Xiaofei He, Jiawei Han

______

10:30 - noon – Applications 3: You’re Being Watched Location: 1002 Session Chair: Karrie Karahalios

Distributed Query Processing for Mobile Surveillance Stewart Greenhill, Svetha Venkatesh

DOTS: Support for Effective Video Surveillance Andreas Girgensohn, Don Kimber, Jim Vaughan, Tao Yang, Frank Shipman, Thea Turner, Eleanor Rieffel, Lynn Wilcox, Francine Chen, Tony Dunnigan

Line Cameras for Monitoring and Surveillance Sensor Networks Jiang Yu Zheng, Shivank Sinha

25 Wednesday, September 26, 2007 10:30am - noon – Arts Session 1: Pieces in Art Location: 1004 Session Chair: Frank Nack

Annotation of Paintings with High-level Semantic Concepts using Transductive Inference and Ontology-based Concept Disambiguation Liza Leslie, Tat-Seng Chua, Ramesh Jain

Discussion: How Meta is Digital Art?

______

10:30am - noon – Demo Session 2 Location: Seminar Rooms 2001 & 2002 Session Chair: Milind Naphade

Automated Home Video Editing: a Multi-Core Solution Chengkun Xue, Liqun Li, Feng Yang, Patricia P. Wang, Tao Wang, Yimin Zhang, Yankui Sun vADeo - Video Advertising System Srinivasan H. Sengamedu, Neela Sawant, Smita Wadhwa

Information Dense Summaries for Review of Patient Performance in Biofeedback Rehabilitation Weiwei Xu, Hari Sundaram

High Definition H.264 Decoding on Cell Broadband Engine Yu Yuan, Rong Yan, Huoding Li, Xing Liu, Sheng Xu

Video Collage Xueliang Liu, Tao Mei, Xian-Sheng Hua, Bo Yang, He-Qin Zhou,

VideoSense: A Contextual Video Advertising System Tao Mei, Linjun Yang, Xian-Sheng Hua, Shipeng Li

DJ DreamFactory Jingjing Liu, Yalou Huang, Dong Li, Fanghao Wu, Bin Li

SBIA: Search-based Image Annotation by Leveraging Web-Scale Images Xirong Li, Xin-Jing Wang, Changhu Wang, Lei Zhang

M-MUSICS: Mobile Content-based Music Retrieval System Byeong-jun Han, Eenjun Hwang, Seungmin Rho, Minkoo Kim

Videntifier: Identifying Pirated Videos in Real-Time Kristleifur Dadason, Herwig Lejsek, Fridrik Ásmundsson, Björn Jónsson, Laurent Amsaleg

Unsupervised Content-based Indexing for Sports Video Retrieval Michael Fleischman, Humberto Evans, Deb Roy

Intertainment - Interactive TV Services on Mobile Devices Günther Hölbling, Tilmann Rabl, Harald Kosch

26 Wednesday, September 26, 2007 ______

Noon - 1:30pm – Conference Lunch (sponsored by SAP) Location: Mensa ______

1:30 - 3:00pm – Poster Session 2 (Arts, Content, Applications) Location: Hallway and Seminar Room 2003 Session Chair: Frank Nack

Shadow Casting for Soft and Engaging Immersion in Augmented Virtuality Artworks Christian Jacquemin, Bertrand Planes, Rami Ajaj

Hide & SEEK: Sharing Cultural Knowledge Thierry Giles, Michael Marienek, Katharine S. Willis, Jens Geelhaar

The Body as a Medium: Reassessing the Role of Kinesthetic Awareness in Interactive Applications Aaron M. Levisohn

Generation of Self-Referential Animated Photomosaic Daryl D'Souza, Vic Ciesielski, Marsha Berry, Karen Trist

Performative Surface: Double Sided Interaction Hugues Bruyère, Thierry Giles

Aesthetic Selection of Naked Genes Milos Rankovic

SMSBlogging: Blog-on-the-street Public Art Project Archana Prasad, Sean Olin Blagsvedt, Kentaro Toyama

Arrays of Water Jets as User Interfaces: Detection and Estimation of Flow by Listening to Turbulence Signatures using Hydrophones Ryan E. Janzen, Steve Mann

The Lens of Ludic Engagement: Evaluating Participation in Interactive Art Installations Ann J. Morrison, Peta Mitchell, Margot Brereton

Automatic Classification of Didactic Functions of e-Learning Resources Marek Meyer, Alexander Hannappel, Christoph Rensing, Ralf Steinmetz

Image Inpainting by Global Structure and Texture Propagation Ting Huang, Shifeng Chen, Jianzhuang Liu, Xiaoou Tang

Visual Analysis of Fingering for Pedagogical Violin Transcription Bingjun Zhang, Jia Zhu, Ye Wang, Wee Kheng Leow

Scale Adaptive Visual Attention Detection by Subspace Analysis Yiqun Hu, Deepu Rajan, Liang-Tien Chia

Tracking Multiple Speakers Using CPHD Filter Nam Trung Pham, Weimin Huang, Sim Heng Ong

27 Wednesday, September 26, 2007 Learning the Consensus on Visual Quality for Next-Generation Image Management Ritendra Datta, Jia Li, James Z. Wang

A Refined Rate Allocation Scheme with Adaptive Playback Adjustment for Robust HD Video Stream Transmission Yuanhai Zhang, Wei Huangfu, Kaihui Li, Changqiao Xu

A Web-based Aggregated Platform for User-contributed Interactive Media Broadcasting Jingjing Liu, Yalou Huang, Dong Li, Fanghao Wu, Bin Li

Synchronization of Multi-Camera Video Recordings Based on Audio Prarthana Shrestha, Mauro Barbieri, Hans Weda

Outdoor Place Recognition using Compact Local Descriptors and Multiple Queries with User Verification Yiqun Li, Joo-Hwee Lim

MusicSense: Contextual Music Recommendation using Emotional Allocation Modeling Rui Cai, Chao Zhang, Chong Wang, Lei Zhang, Wei-Ying Ma

Voice Activity Detection by Lip Shape Tracking Using EBGM Masaki Aoki, Ken Masuda, Hiroyoshi Matsuda, Tetsuya Takiguchi, Yasuo Ariki

An Online System for Gathering Image Similarity Judgements Alexei Yavlinsky, Daniel Heesch

Analysis of Usage Patterns in Experiential Multiple Perspective Web Search Rahul Singh, Ya-Wen Hsu

Empirical Study of 3D Video Source Coding for Autostereoscopic Displays Roger Cheng, Klara Nahrstedt

Video Summarization by Redundancy Removing and Content Ranking Tao Wang, Yue Gao, Patricia P. Wang, Eric Li, Wei Hu, Yimin Zhang, Junhai Yong

Improving Gaming Experience in Zonal MMOGs Dewan Ahmed, Shervin Shirmohammadi, Jauvane Oliveira

______

1:30 - 3:00pm – Content 4: Image Annotation Location: 1001 Session Chair: Dongge Li

Bipartite Graph Reinforcement Model for Web Image Annotation Xiaoguang Rui, Mingjing Li, Zhiwei Li,Wei-Ying Ma, Nenghai Yu

Exploiting Spatial Context Constraints for Automatic Image Region Annotation Jinhui Yuan, Jianmin Li, Bo Zhang

Dual Cross-Media Relevance Model for Image Annotation Jing Liu, Bin Wang, Mingjing Li, Zhiwei Li, Weiying Ma, Hanqing Lu, Songde Ma

______

28 Wednesday, September 26, 2007 1:30 - 3:00pm – Brave New Topics Session, Part 1 Location: 1002 Session Chair: Lexing Xie

Contextual Wisdom: Social Relations and Correlations for Multimedia Event Annotation Amit Zunjarwad, Hari Sundaram, Lexing Xie

Systems Challenges of Media Collectives Ketan Mayer-Patel

How Flickr Helps us Make Sense of the World: Context and Content in Community-Contributed Media Collections Lyndon Kennedy, Mor Naaman, Shane Ahern, Rahul Nair, Tye Rattenbury

______

3:30 - 4:00pm – Brave New Topics Session, Part 2

Semantics, Content, and Structure of Many for the Creation of Personal Photo Albums Susanne Boll, Ansgar Scherp, Philipp Sandhaus, Utz Westermann

______

1:30 - 3:00pm – HCI 2: Interfaces to Smart Spaces Location: 1004 Session Chair: Alejandro Jaimes

Madame Bovary on the Holodeck: Immersive Interactive Storytelling Marc Cavazza, Jean-Luc Lugrin, David Pizzi, Fred Charles

Audio-Visual Multi-Person Tracking and Identification for Smart Environments Keni Bernardin, Rainer Stiefelhagen

Privacy and the Access of Information in a Smart House Environment Simon Moncrieff, Svetha Venkatesh, Geoff West

______

3:00 - 7:00pm – Live Arts Exhibition Location: University of Applied Sciences Augsburg Session Chair: Thomas Rist

Please see page 22 for the list of artworks ______

3:00 - 3:30pm – Tea & Coffee break (sponsored by MAN Roland) Location: Hallway ______

29 Wednesday, September 26, 2007 3:30 - 5:00pm – Arts Session 2: Art Pieces Location: 1001 Session Chair: Alejandro Jaimes

The Listening Room: A Speech-based Interactive Art Installation Alexa Wright, Alf Linney, Mike Lincoln, Alun Evans

Particulate Matters: Generating Particle Flows from Human Movement Kirk A. Woolford, Carlos Guedes

Discussion: How Particle is Digital Art?

______

4:00 - 5:00pm –Applications 4: Helping End Users Location: 1002 Session Chair: Brian Bailey

Image Stabilization for 2D Barcode in Handheld Devices Chung-Hua Chu, De-Nian Yang, Ming-Syan Chen

Establishing the Utility of Non-Text Search for News Video Retrieval with Real World Users Michael G. Christel

______

3:30 - 5:00pm – Systems 2: Adaptation & Scalability Location: 1004 Session Chair: Carsten Griwodz

Improving Mobile Ad-hoc Streaming Performance through Adaptive Layer Selection With Scalable Video Coding Min Qin, Roger Zimmermann

Analysis of Waiting-Time Predictability in Scalable Media Streaming Mohammad A. Alsmirat, Musab Al-Hadrusi, Nabil J. Sarhan

An Analytical Model for Progressive Mesh Streaming Wei Cheng, Wei Tsang Ooi, Sebastien Mondet, Romulus Grigoras, Geraldine Morin

______

30 Wednesday, September 26, 2007 3:30 - 5:00pm – Poster Session 3 (Systems & Applications) Location: Hallway and Seminar Room 2003 Session Chair: Susanne Boll

An Efficient Intra Deinterlacing Algorithm with Gradient Detection and Window Matching Wonki Kim, Soonjon Jin, Jechang Jeong

Wavelet-Based Multi-View Video Coding with Full Scalability and Illumination Compensation Jens-Uwe Garbas, Ulrich Fecker, André Kaup

Energy-Aware Data Prefetching for Multi-Speed Disks in Video Servers Minseok Song

Hyperspectral Images Lossless Compression by a Novel Three-dimensional Wavelet Coding Jing Zhang, Guizhong Liu

Hierarchical Collaborative Multicast Francisco A. López-Fuentes, Eckehard Steinbach

Towards Multi-Site Collaboration in Tele-Immersive Environments Wanmin Wu, Zhenyu Yang, Klara Nahrstedt, Gregorij Kurillo, Ruzena Bajcsy

Transparent Protocol Translation for Streaming Håvard Espeland, Carl Henrik Lunde, Håkon Kvale Stensland, Carsten Griwodz, Pål Halvorsen

A Framework for Encoding and Caching Video for Quality Adaptive Progressive Download Siddhartha Chattopadhyay, Lakshmish Ramaswamy, Suchendra M. Bhandarkar

Improving the Delivery of Multimedia Embedded in Web Pages Adam Serbinski, Abdolreza Abhari

A Peer-to-Peer Architecture for Efficient Live Scalable Media Streaming on Internet Xuguang Lan, Nanning Zheng, Jianru Xue, Xiaoguang Wu, Bin Gao

A Compressed Domain Distortion Measure for Fast Video Transcoding Yicheng Huang, Vu An Tran, Ye Wang

Scalable Delivery and Pricing of Streaming Media with Advertisements Musab Al-Hadrusi, Nabil J. Sarhan

Musical Extrapolation of Speech with Auto-DJ Simon Wun, Chern-Han Yong, Ti-Eu Chan

Optimized Cache Management for Scalable Video Streaming Yongfeng Li, Kenneth Ong

Spatial Querying for Retrieval of Human Movement Patterns in Smart Environments Gamhewage C. de Silva, Toshihiko Yamasaki, Kiyoharu Aizawa

Large Head Movement Tracking Using SIFT-based Registration Gangqiang Zhao, Ling Chen, Jie Song, Gencai Chen

Query On Demand Video Browsing Ork de Rooij, Cees Snoek, Marcel Worring

31 Wednesday, September 26, 2007 Adjusting Route Panoramas with Condensed Image Slices Jiang Yu Zheng, Glenn R. Flora

A Modern Day Video Flip-Book: Creating a Printable Representation from Time-Based Media Berna Erol, Jamey Graham, Jonathan J. Hull, Peter E. Hart

Floor-Plan Reconstruction from Panoramic Images Dirk Farin, Wolfgang Effelsberg, Peter H.N. de With

Learning to Gesture: Applying Appropriate Animations to Spoken Text Nathan Nichols, Jiahui Liu, Bryan Pardo, Kristian Hammond, Larry Birnbaum

Introducing TANGerINE: a Tangible Interactive Natural Environment Stefano Baraldi, Alberto Del Bimbo, Lea Landucci, Nicola Torpei, Omar Cafini, Elisabetta Farella, Augusto Pieracci, Luca Benini

Using Audio and Video Features to Classify the Most Dominant Person in a Group Meeting Hayley Hung, Dinesh Jayagopi, Chuohao Yeo, Gerald Friedland, Sileye Ba, Jean-Marc Odobez, Kannan Ramchandran, Nikki Mirghafori, Daniel Gatica-Perez

Emotion-based Impressionism Slideshow with Automatic Music Accompaniment Cheng-Te Li, Man-Kwan Shan

Information Dense Summaries for Review of Patient Performance in Biofeedback Rehabilitation Weiwei Xu, Hari Sundaram

Color-based Clustering for Text Detection and Extraction in Images Jian Yi, Yuxin Peng, Jianguo Xiao

______

7:00 - 9:00pm – Conference Banquet (sponsored by Google and CeWe) Location: Kurhaus Göggingen, Klausenberg 6, 86199 Augsburg

The „Kurhaus“ in Göggingen was built in 1885 by Jean Keller on behalf of Friedrich von Hessing. It is an important monument of German architecture and engineering consisting of plastered brick combined with iron construction and large windows. In 1972 it was severely damaged by fire. It was re-opened in 1996 after extensive renovation. The Kurhaus in Göggingen is regarded as a jewel and unique testimony of late 19th century style. It is now used as a theater and convention facility.

32 Thursday, September 27, 2007 THURSDAY, SEPTEMBER 27, 2007

9:00 - 10:00am – Keynote Presentation II Location: HS 1 Session Chair: Anand Prasad

Insights into Future Mobile Multimedia Applications Dr. Minoru Etoh – NTT DoCoMo

______

10:00 - 10:30 – Tea & Coffee break (sponsored by SAP) Location: Hallway ______

10:30 - noon – Content 5: Video Annotation Location: 1001 Session Chair: Changsheng Xu

Structure-Sensitive Manifold Ranking for Video Concept Detection Jinhui Tang, Xian-Sheng Hua, Guo-Jun Qi, Meng Wang, Tao Mei, Xiuqing Wu

Optimizing Multi-Graph Learning: Towards A Unified Video Annotation Scheme Meng Wang, Xian-Sheng Hua, Xun Yuan, Yan Song, Li-Rong Dai

An Integrated Statistical Model for Multimedia Evidence Combination Sheng Gao, Joo-Hwee Lim, Qibin Sun

______

10:30 - noon – Applications 5: Smart Media Environments Location: 1002 Session Chair: Balakrishnan Prabhakaran

ViewCast: View Dissemination and Management for Multi-party 3D Tele-immersive Environments Zhenyu Yang, Wanmin Wu, Klara Nahrstedt, Gregorij Kurillo, Ruzena Bajcsy

Aging in Place: Fall Detection and Localization in a Distributed Smart Camera Network Adam Williams, Deepak Ganesan, Allen Hanson

Video Personalization in Resourced-Constrained Multimedia Environments Yong Wei, Suchendra M. Bhandarkar, Kang Li

______

33 Thursday, September 27, 2007 10:30 - 12:30am – Arts Session 3: Fluid Art Location: 1003 Session Chair: Frank Nack

Fluid Samplers: Sampling Music Keyboards Having Fluidly Continuous Action and Sound, without Being Electrophones Steve Mann, Ryan E. Janzen

Alternating from 1 to x and Vice Versa - An Interactive Concert-performance Homage to Alighiero Boetti Andrea Valle, Vincenzo Lombardo, Hairi Vogel

Non-Electrophonic Cyborg Instruments: Playing on Everyday Things as if the Whole World Were One Giant Musical Instrument Steve Mann, RyanE. Janzen, Raymond Lo, James Fung

Discussion: How Playful is Digital Art? ______

10:30 - noon – Systems 3: Computing Complexity Location: 1004 Session Chair: Wei Tsang Ooi

Multilevel Parallelization on the Cell/B.E. for a Motion JPEG 2000 Encoding Server Hidemasa Muta, Munehiro Doi , Hiroki Nakano, Yumi Mori

A Workload Prediction Model for Decoding MPEG Video and its Application to Workload- scalable Transcoding Yicheng Huang, An Vu Tran, Ye Wang

Dynamic Complexity Control for Real-Time H.264/AVC Video Encoding Yury Ivanov, Chris J. Bleakley

______

Noon - 1:30pm – Conf. Lunch (sponsored by Yahoo! Research) Location: Mensa ______

1:30 - 3:00pm – Content 6: Video Search Location: 1002 Session Chair: Marcel Worring

Video Search Reranking through Random Walk over Document-Level Context Graph Winston Hsu, Lyndon S. Kennedy, Shih-Fu Chang

Ontology-Enriched Semantic Space for Video Search Xiao-Yong Wei, Chong-Wah Ngo

Semantic Concept-Based Query Expansion and Re-ranking for Multimedia Retrieval Apostol Natsev, Alexander Haubold, Jelena Tesic, Lexing Xie, Rong Yan

______34 Thursday, September 27, 2007 1:30 - 3:00pm – Open Source Software Competition Location: 1002 Session Chair: Apostol Natsev

Best Open Source Software: Programming Web Multimedia Applications with Hop Manual Serrano

Advene: An Open-Source Framework for Integrating and Visualizing Audiovisual Metadata Olivier Aubert, Yannick Prié

GPAC: Open Source Multimedia Framework Jean Le Feuvre, Cyril Concolato, Jean-Claude Moissinac

Xface: Open Source Project and SMIL-Agent Scripting Language for Creating and Animating Embodied Conversational Agents Koray Balci, Elena Not, Massimo Zancanaro, Fabio Pianesi

______

1:30 - 3:00pm – Doctorial Symposium Location: 1003 Session Chair: Thomas Plagemann, Vera Goebel

Large Scale Semantic Structures for Image Retrieval Adrian Popescu

Realizing Multimedia Processes by Combining Intelligent Content and Semantic Web Services Tobias Bürger

Active Reading of Audiovisual Documents Bertrand Richard

______

1:30 - 3:00pm – Systems 4: Coding Support Location: 1004 Session Chair: Klara Nahrstedt

A Utility-Driven Framework for Loss and Encoding Aware Video Adaptation Srinivas Krishnan, Ketan Mayer-Patel

Ligne-Claire Video Encoding for Power Constrained Mobile Environments Siddhartha Chattopadhyay, Suchendra M. Bhandarkar, Kang Li

Display Pre-filtering for Multi-view Video Compression Matthias Zwicker, Sehoon Yea, Anthony Vetro, Clifton Forlines, Wojciech Matusik, Hanspeter Pfister

______

35 Thursday, September 27, 2007 3:00 - 7:00pm – Live Arts Exhibition Location: University of Applied Sciences Augsburg Session Chair: Thomas Rist

Please see page 22 for the list of artworks ______

3:00 - 3:30 – Tea & Coffee break (sponsored by CeWe Color) Location: Hallway ______

3:30 - 5:00pm – Panel Session Location: 1001 Session Chair: Tat-Seng Chua

Towards the Next Plateau – Innovative Multimedia Research beyond TRECVID

Panelists: Alan Hanjalic (Delft University of Technology, The Netherlands) Alan Smeaton (Dublin University, Ireland) John R. Smith (IBM T.J. Watson Research Center, USA) Ramesh Jain (UC Irvine, USA) Svetha Venkatesh (Curtin University, Australia)

______

3:30 - 5:00pm – Applications 6: Querying and Recommending Media Location: 1002 Session Chair: Vera Goebel

QueST: Querying Music Databases by Acoustic and Textual Features Bin Cui, Ling Liu, Calton Pu, Jialie Shen, Kian-Lee Tan

Scalable Music Recommendation by Search Rui Cai, Chao Zhang, Lei Zhang, Wei-Ying Ma

VideoSense - Towards Effective Online Video Advertising Tao Mei, Xian-Sheng Hua, Linjun Yang, Shipeng Li

______

3:30 - 5:00pm – Video Program Location: 1004 Session Chair: Thomas Haenselmann

New Digital Options in Geographically Distributed Dance Collaborations with TEEVE: Tele- immersive Environments for EVErybody Renata Sheppard, Wanmin Wu, Zhenyu Yang, Klara Nahrstedt, Lisa Wymore, Gregorij Kurillo, Ruzena Bajcsy, Katherine Mezur

Tennis Video 2.0 : A New Framework of Sport Video Applications Jui-Hsin Lai, Shao-Yi Chien

36 Friday, September 28, 2007 WORKSHOPS

FRIDAY, SEPTEMBER 28, 2007

MIR 2007 - 9TH ACM SIGMM INTERNATIONAL WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL

Workshop organizers: James Z. Wang, Nozha Boujemaa

8:30 - 10:00am – Workshop Opening and Keynote Speech Location: 1001

Opening Remarks and Introduction of Speaker. Jia Li

Keynote Speech Michael Lesk – Rutgers University

______

10:00 - 10:20am - Coffee break Location: Hallway ______

10:20am - 12:00pm – Oral Session 1: Image Retrieval and Multimedia Modeling Location: 1001 Chair: Marco Bertini

Regularized Regression on Image Manifold for Retrieval Deng Cai et al.

Clustering Near-duplicate Images in Large Collections Jun Jie Foo

Learning Semantic Categories for 3D Model Retrieval Ryutarou Ohbuchi

Learning User Intention in Relevance Feedback using Optimization Jian Guan

Unsupervised Content-Based Indexing for Sports Video Retrieval Michael Fleischman

37 Friday, September 28, 2007 ______

12:00 - 1:30pm – Lunch break Location: Mensa ______

1:30 - 3:00pm – Poster Session 1: Multimedia Retrieval and Modeling Location: Hallway Chair: Jia Li

Effective Retrieval of Polyphonic Audio with Polyphonic Symbolic Queries Iman Suyoto, Alexandra Uitdenbogerd, Falk Scholer

Visual Language Modeling for Image Classification Lei Wu, Mingjing Li, Zhiwei Li, Wei-Ying Ma, Nenghai Yu

Optimal Decomposition of P2P Networks based on File Exchange Patterns for Multimedia Content Search & Replication Nikolaos Doulamis, Pantelis Karamolegkos, Anastasios D. Doulamis, Ioannis Nikolakopoulos

Music Similarity: Improvements of Edit-based Algorithms by Considering Music Theory Matthias Robine, Pierre Hanna, Pascal Ferraro

Sample-based Creation of Peer Summaries for Efficient Similarity Search in Scalable Peer-to- Peer Networks Soufyane El Allali, Daniel Blank, Wolfgang Müller, Andreas Henrich

Tempo Induction Algorithm in MP3 Compressed Domain Antonello D'Aguanno, Giancarlo Vercellesi

Visual and Textual Fusion for Region Retrieval from Both Bayesian Reasoning and Fuzzy Matching Aspects Rongrong Ji, Yao Hongxun

Stratified Helix Information of Medial-Axis-Points Matching for 3D Model Retrieval Ji Jia, Zheng Qin, Jiang Lu

______

1:30 - 3:00pm – Poster Session 2: Video Retrieval and Annotation Location: Hallway Chair: Jia Li

Exploiting Redundancy in Cross-Channel Video Retrieval Bouke Huurnink, Maarten de Rijke

Adapting Appearance Models of Semantic Concepts to Particular Videos via Transductive Learning Ralph Ewerth, Bernd Freisleben

Evaluating Bag-of-Visual-Words Representations in Scene Classification Jun Yang, Yu-Gang Jiang, Alexander Hauptmann, Chong-Wah Ngo

38 Friday, September 28, 2007 Searching For Repeated Video Sequences Tolga Can, Pinar Duygulu

TV Ad Video Categorization with Probabilistic Latent Concept Learning Jinqiao Wang, Ling-Yu Duan, Lei Xu, Hanqing Lu, Jesse Jin

Building a Comprehensive Ontology To Refine Video Concept Detection Zheng-Jun Zha, Tao Mei, Zengfu Wang, Xian-Sheng Hua

Scene Duplicate Detection from Videos Based on Trajectories of Feature Points Shin'ichi Satoh

______

3:00 - 3:30pm – Coffee break Location: Hallway ______

3:30 - 5:30pm – Special Session 1: Semantic Indexing of Consumer and Web Videos Location: 1001 Chair: Shih-Fu Chang

Kodak Consumer Video Benchmark Data Set: Concept Definition and Annotation Alexander C. Loui, Jiebo Luo, Shih-Fu Chang, Dan Ellis, Wei Jiang, Lyndon Kennedy, Keansub Lee, Akira Yanagawa

Large-Scale Multimodal Semantic Concept Detection for Consumer Video Shih-Fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Alexander C. Loui, Jiebo Luo

Multi-Modal Web Video Categorization Linjun Yang, Jiemin Liu, Tao Mei, Xiaokang Yang, Xian-Sheng Hua

Watch What I Watch: Using Community Activity To Understand Content David A. Shamma, Ryan Shaw, Peter L. Shafton, Yiming Liu

Learning People Annotation from the Web via Consistency Learning Jay Yagnik, Atiq Islam

ITEMS: Intelligent Travel Experience Management System Chih-Chieh Liu, Chun-Hsiang Huang, Wei-Ta Chu, Ja-Ling Wu

39

Friday, September 28, 2007

MV 2007- WORKSHOP ON MOBILE VIDEO 2007

Workshop organizers: Chang Wen Chen, Eckehard Steinbach

8:30 - 9:30am – Invited Plenary Talk 1 Location: 1002

Advances in Wireless Video Delivery Minoru Eto – NTT DoCoMo Research Laboratories, Japan

______

9:30 - 10:30am – Session 1: Industrial Perspectives on Mobile Video Location: 1002 Session Chair: Chang Wen Chen

Mobile Video Applications and Standards Ye-Kui Wang, Imed Bouazizi, Miska Hannuksela, Igor Curcio

On Practical Crosslayer Aspects in 3GPP Video Services Thomas Stockhammer, Günther Liebl

The OMA BCAST Standard for Bearer-Independent Mobile TV Services Frank Hartung, Markus Kampmann, Thomas Rusert

______

10:30 - 10:50am – Coffee Break Location: Hallway ______

10:50 - 11:50am – Invited Plenary Talk 2 Location: 1002

Mobile and Media Experiences and Technologies Susie Wee – HP Labs, USA

______

11:50am - 1:00pm – Lunch Break Location: Mensa ______

1:00 - 1:30pm – Workshop Sponsor Presentation Location: 1002 Christophe Beaugeant – Nokia Siemens Networks, Germany

41 Friday, September 28, 2007 1:30 - 2:50pm – Session 2: Error-Robust Mobile Video Location: 1002 Session Chair: Eckehard Steinbach

Raptor network video coding Nikoloas Thomos, Pascal Frossard

Bit-error Resilient Packetization for Streaming H.264/AVC Video Jari Korhonen, Pascal Frossard

Quality Assessment Metrics vs. PSNR under Packet Loss Scenarios in MANET Wireless Networks Miguel Martínez-Rach, Othoniel López Granado, Pablo Piñol Peral, Manuel Malumbres, Jose Oliver, Carlos Calafate

Multiple Description H.264 Video Coding with Redundant Pictures Ivana Radulovic, Pascal Frossard, Ye-Kui Wang, Stephan Wenger, Antti Hallapuro, Miska Hannuksela

______

2:50 - 3:50pm – Invited Plenary Talk 3 Location: 1002

Mobile Video Transmission Thomas Wiegand – Heinrich-Hertz-Institut, Germany

______

3:50 - 4:10pm – Coffee Break Location: Hallway ______

4:10 - 5:10pm – Session 3: Scalable Video and Rate Adaptation Location: 1002 Session Chair: Susie Wee

Optimized Scalable Video Transmission Based on Conditional Replenishment of JPEG2000 Code- blocks with Motion Compensation Aous Naman, David Taubman

Discardable Data Adaptation in Scalable Video Coding Yi Guo, Ye-Kui Wang, Miska Hannuksela, Houqiang Li

A Smoothed, Minimum Distortion-Variance Rate Control Algorithm for Multiplexed Transcoded Video Sequences Giuseppe Valenzise, Marco Tagliasacchi, Stefano Tubaro

42 Friday, September 28, 2007 5:10 - 5:50pm – Session 4: Applications Location: 1002 Session Chair: Thomas Wiegand

Ball Appearance Improvement in Low-Resolution Soccer Videos Martin Wrulich, Olivia Nemethova, Luca Superiori, Markus Rupp

Mobile Video Surveillance with Low-Bandwidth Low-Latency Video Streaming Giovanni Gualdi, Rita Cucchiara, Andrea Prati

______

5:50 - 6:00pm – Closing Location: 1002

43

Friday, September 28, 2007

TVS 2007 - TRECVID VIDEO SUMMARIZATION

Workshop organizers: Paul Over, Alan F. Smeaton

8:30 - 10:00am Location: 1004

The TRECVID 2007 BBC Rushes Summarization Evaluation Pilot Paul Over, Alan F. Smeaton, Philip Kelly, Richard Wright

Rushes Video Summarization by Object and Event Understanding Feng Wang, Chong-Wah Ngo

Rushes Summarization by Adaptive Acceleration and Stacking of Shots Marcin Detyniecki, Christophe Marsala

______

10:00 – 10:30am – Coffee Break Location: Hallway ______

10:30 – 11:50am Location: 1004

Feature Fusion and Redundancy Pruning for Rush Video Summarization Jim Kleban, Anindya Sarkar, Emily Moxley, Stephen Mangiat, Swapna Joshi, Thomas Kuo, B.S. Manjunath

Video Summarization Preserving Dynamic Content Francine Chen, Matthew Cooper, John Adcock

Generating Comprehensible Summaries of Rushes Sequences based on Robust Feature Matching Ba Tu Truong, Svetha Venkatesh

Skimming Rushes Video Using Retake Detection Werner Bailer, Felix Lee, Georg Thallinger

______

Noon - 1:30pm – Lunch Break Location: Mensa ______

45 Friday, September 28, 2007 1:30 - 2:45pm – Combined Poster & Demo session Location: 2001

Video Summarization at Brno University of Technology Vítězslav Beran, Michal Hradiš, Adam Herout, Stanislav Sumec, Igor Potúček, Pavel Zemčík, Josef Mlích, Aleš Láník, Petr Chmelař

Clever Clustering vs. Simple Speed-Up for Summarizing BBC Rushes Alexander G. Hauptmann, Michael G. Christel, Wei-Hao Lin, Bryan Maher, Jun Yang, Robert V. Baron, Guang Xiang

A User-Centered Approach to Rushes Summarization via Highlight-Detected Keyframes Daragh Byrne, Peter Kehoe, Hyowon Lee, Ciarán O'Connaire, Alan F. Smeaton, Noel E. O'Connor, Gareth J.F. Jones

Split-Screen Dynamically Accelerated Video Summaries Emilie Dumont, Bernard Merialdo

Rushes Summarization with Self-Organizing Maps Markus Koskela, Mats Sjöberg, Jorma Laaksonen

National Institute of Informatics, Japan at TRECVID 2007: BBC Rushes Summarization Duy-Dinh Le, Shin'ichi Satoh

NTU TRECVID-2007 Fast Rushes Summarization System Chen-Ming Pan, Yung-Yu Chuang, Winston H. Hsu

THU-ICRC at Rush Summarisation of TRECVID 2007 Tao Wang, Yue Gao, Jianguo Li, Patricia P. Wang, Xiaofeng Tong, Wei Hu, Yimin Zhang, Jianmin Li

The Hong Kong Polytechnic University at TRECVID 2007 BBC Rushes Summarization Yang Liu, Yan Liu, Yan Zhang

Attention-based Video Summarization in Rushes Collection Reede Ren, P.Punitha, Joemon Jose

On-line Video Skimming Based on Histogram Similarity Víctor Valdés, José M. Martínez

______

2:45 - 3:30pm – Coffee Break Location: Hallway ______

3:30 - 4:30pm – Plenary discussion Location: 1004

Discussion on lessons learned, plans for 2008

46 Friday, September 28, 2007

HCM 2007- HUMAN-CENTERED MULTIMEDIA

Workshop organizers: Alex Jaimes, Nicu Sebe

8:50 - 10:00am – Workshop Opening and Keynote Presentation Location: 1003 ______

10:00 - 10:30am – Coffee Break Location: Hallway ______

10:30 - 12:10pm – Session 1 Location: 1003 Session Chair: Nicu Sebe

Pillows as Adaptive Interfaces in Ambient Environments Frank Nack, Thecla Schiphorst, Zeljko Obrenovic, Michiel KauwATjoe, Simon de Bakker, Lora Aroyo

Music Emotion Recognition: The Role of Individuality Yi-Hsuan Yang, Ya-Fan Su, Yu-Ching Lin, Homer Chen

3D Tracking of Pointing Gesture for Wearable Visual Interfaces Yunde Jia

Affective Multimodal Mirror: Sensing and Eliciting Laughter Willem Melder, Khiet Truong, Mark Neerincx, David Van Leeuwen

______

12:10 - 1:30pm – Lunch Break Location: Mensa ______

1:30 - 3:10pm – Session 2 Location: 1003 Session Chair: Alex Jaimes

Towards Open Source Authoring and Presentation of Multimedia Content Nikitas Sgouros, Alexandros Margaritis

Preattentive Visualization of Information Relevance Matthias Deller, Achim Ebert, Michael Bender, Stefan Agne, Henning Barthel

Local Spatiotemporal Descriptors for Visual Recognition of Spoken Phrases Guoying Zhao, Matti Pietikäinen, Abdenour Hadid

Interconnected Media for Human-Centered Understanding Katja Einsfeld

47 Friday, September 28, 2007 ______

3:10 - 3:40pm – Coffee Break Location: Hallway ______

3:40 - 4:55pm – Session 3 Location: 1003 Session Chair: Daniel Gatica-Perez

Multimedia and human-in-the-loop: Interaction as content enrichment Bruno Emond

Too Close for Comfort? Adapting to the User's Cultural Background Matthias Rehm

Human Support Improvements by Natural Man-Machine Collaboration Motoyuki Ozeki

______

4:55 - 5:45pm – Panel Session Location: 1003

48 Friday, September 28, 2007

MS 2007 - THE MANY FACES OF MULTIMEDIA SEMANTICS

Workshop organizers: William Grosky, Farshad Fotouhi, Peter Stanchev

8:30 - 10:00am – Session 1: The Semantics of Semantics Location: 2003 Session Chair: William I. Grosky

Invited Keynote Talk: Realizing the Relationship Web: Morphing Information Access on the Web from Today’s Document and Entity-Centric Paradigm to a Relationship-Centric Paradigm Amit Sheth – Wright State University, USA

Contributed Talk: Towards an Ecosystem for Semantics Ansgar Scherp, Ramesh Jain

______

10:00 - 10:30 am – Coffee Break Location: Hallway ______

10:30am- 12:00 – Session 2: Annotation Location: 2003 Session Chair: Amit Sheth

An Efficient Manual Image Annotation Approach based on Tagging and Browsing Rong Yan, Apostol Natsev, Murray Campbell

Automatic Metadata Extraction and Indexing for Reusing e-Learning Multimedia Objects Paolo Bolettieri, Fabrizio Falchi, Claudio Gennaro, Fausto Rabitti

The Use of Semantic-based Predicates Implication to Improve Horizontal Multimedia Database Fragmentation Richard Chbeir, Fekade Getahun, Joe Tekli, Solomon Atnafu

______

12:00 - 1:30pm – Lunch break Location: Mensa ______

1:30 - 3:00pm – Session 3: Semantics of Video Location: 2003 Session Chair: Farshad Fotouhi

Learning Ontology for Personalized Video Retrieval Hiranmay Ghosh, P Poornachander, Anupama Mallik, Santanu Chaudhury

49 Friday, September 28, 2007 Dynamic Pictorial Ontologies for Video Digital Libraries Annotation and Retrieval Marco Bertini, Alberto Del Bimbo, Carlo Torniai, Rita Cucchiara, Costantino Grana

Fast Unsupervised Alignment of Video and Text for Indexing/Names and Faces Subhransu Maji, Ruzena Bajcsy

______

3:00 - 3:30pm – Coffee Break Location: Hallway ______

3:30 - 5:00 pm – Session 4: Emerging Applications Location: 2003 Session Chair: Peter Stanchev

Semantic Similarity based Trust Computation in Websites Hicham Ibrahim, Pradeep Atrey, Abdulmotaleb El Saddik

A Digital Rights Aware Similarity Measure for Multimedia Documents Fabrizio Falchi, Nicola Orio, Walter Allasia, Francesco Gallo

A Distributed Data Space for Music-Related Information Yves Raimond, Christopher Sutton, Mark Sandler

50 Friday, September 28, 2007

EMME 2007- EDUCATIONAL MULTIMEDIA AND MULTIMEDIA EDUCATION

Workshop organizers: Gerald Friedland, Wolfgang Hürst, Lars Knipping

8:30 - 10:00am – Opening Session Location: 2002

Opening and welcome address, workshop introduction, and some notes on the past, the present, and the potential future of educational multimedia systems Gerald Friedland, Wolfgang Hürst, Lars Knipping

Effective Use of Multimedia for Computer-Assisted Musical Instrument Tutoring Graham Percival, Ye Wang, George Tzanetakis

______

10:00 - 10:30am – Coffee break Location: Hallway ______

10:30 - 12:30pm –Session “Educational Multimedia”, Part 1 Location: 2002

Categorization of Educational Presentation Systems Georg Turban

An Automatic Cameraman in a Lecture Recording System Fleming Lampi, Stephan Kopf, Manuel Benz, Wolfgang Effelsberg

Towards an Automatic Semantic Annotation for Multimedia Learning Objects Stephan Repp, Serge Linckels, Christoph Meinel

A Web-Based Group Decision Support System for the Selection and Evaluation of Educational Multimedia Mohammed Abdelhakim, Shervin Shirmohammadi

______

12:30 - 1:30pm – Lunch break Location: Mensa ______

51 Friday, September 28, 2007 1:30 - 3:00pm –Session “Educational Multimedia”, Part 2 Location: 2002

Interaction and Reflection via 3D Path Shape Qualities in a Mediated Constructive Learning Environment Kai Tu, Harvey Thornburg, Ellen Campana, David Birchfield, Matthew Fulmer, Andreas Spanias

Adapting Handwriting Recognition for Applications in Algebra Learning Lisa Anthony, Jie Yang, Kenneth Koedinger

Educational Violin Transcription by Fusing Multimedia Streams Ye Wang, Bingjun Zhang, Olaf Schleusing

______

3:00 - 4:00pm – Poster and Demo Session (& coffee break from 3:00 - 3:30pm) Location: hallway (posters) + 2001 (demonstrations)

Posters:

Introducing Wireless Networking Technologies as a Teaching Tool for Foreign Languages: a Multimedia Laboratory Experiment Frank Favier, John Fynn, Michel Misson

Authoring Educational Multimedia Content Using Learning Styles and Story Telling Principles Nalin Sharda

Haptic Multimedia Handwriting Learning System Mohamad Eid, Rosa Iglesias, Mohamed Mansour, Abdulmotaleb El Saddik

Information Extraction from Mathematical Texts by Means of Natural Language Processing Techniques Sabina Jeschke, Nicole Natho, Olivier Pfeiffer, Marc Wilke

A Framework for the Development of Educational Presentation Systems and Its Application Georg Turban, Max Mühlhäuser

Demonstrations:

Active-Smoothing in Digital Ink Environments Khaireel A. Mohamed, Thomas Ottmann

A Low-Cost Mobile Pointing and Drawing Device Kristian Jantz, Gerald Friedland, Lars Knipping, Raul Rojas

Audio-based Methods for Navigation and Browsing Educational Multimedia Documents Tobias Lauer, Wolfgang Hürst

Adapting Handwriting Recognition for Applications in Algebra Learning (Demonstration related to the according presentation in Session 2) Lisa Anthony, Jie Yang, Kenneth Koedinger

52 Friday, September 28, 2007 4:00 - 5:30pm –Session “Multimedia Education” Location: 2002

Creating Innovative New Media Programs: Need, Challenges, and Development Framework Nalin Sharda

Panel Discussion: The Future of Multimedia Education

Panelists: Susanne Boll (University of Oldenburg, Germany) Ramesh Jain (UC Irvine, USA) Max Mühlhäuser (Darmstadt University of Technology, Germany) Timothy K. Shih (Tamkang University, Taiwan)

______

5:30 - 6:00pm – Closing Remarks Location: 2002

53

Saturday, September 29, 2007

SATURDAY, SEPTEMBER 29, 2007

MIR 2007 - 9TH ACM SIGMM INTERNATIONAL WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL

Workshop organizers: James Z. Wang, Nozha Boujemaa

8:30 - 10:00am – Keynote Presentation Location: 1001

Opening remarks and introduction of speaker Alberto del Bimbo

Keynote Speech Arnold Smeulders – University of Amsterdam, The Netherlands

______

10:00 - 10:20am – Coffee break Location: Hallway ______

10:20am - noon – Oral Session 2: Video Retrieval Location: 1001 Chair: Jiebo Luo

Video Diver: Generic Video Indexing with Diverse Features Dong Wang, Xiaobing Liu

Combining Multimodal Preferences for Multimedia Information Retrieval Eric Bruno, Jana Kludas, Stephane Marchand-Maillet

Trademark Matching and Retrieval in Sports Video Databases Andrew Bagdanov, Lamberto Ballan, Marco Bertini, Alberto Del Bimbo

RoleNet: Treat a Movie as a Small Society Chung-Yi Weng, Wei-Ta Chu, Ja-Ling Wu

Semantic-Event Based Analysis and Segmentation of Wedding Ceremony Videos Wen-Huang Cheng, Yung-Yu Chuang, Bing-Yu Chen, Ja-Ling Wu, Shao-Yen Fang, Yin-Tzu Lin, Chi- Chang Hsieh, Chen-Ming Pan, Wei-Ta Chu, Min-Chun Tien

______

Noon - 1:30pm – Lunch Break Location: Hallway ______

55 Saturday,September 29, 2007 1:30 - 3:00pm – Panel Session: New Challenges in Multimedia Research for the Increasingly Connected and Fast Growing Digital Society Location: 1001 Chair: Jia Li

Panelists: Shih-fu Chang (Columbia University, USA) Michael Lesk (Rutgers University, USA) Rainer Lienhart (University of Augsburg, Germany) Jiebo Luo (Eastman Kodak Research, USA) Arnold Smeulders (University of Amsterdam, The Netherlands)

______

3:00 - 3:30pm – Coffee break Location: Hallway ______

3:30 - 5:00pm – Special Session 2: Personalized Multimedia Information Retrieval Location: 1001 Chair: Nicu Sebe

Personalized Multimedia Retrieval: The New Trend? Nicu Sebe, Qi Tian

Browsing Visual Collections Using Graphs Marcel Worring, Ork de Rooij, Ton van Rijn

Personalized Retrieval of Sports Video Yifan Zhang, Xiaoyu Zhang, Changsheng Xu, Hanqing Lu

Evaluating the Implicit Feedback Models for Adaptive Video Retrieval Frank Hopfgartner, Joemon Jose

56

CO-SPONSORS

SUPPORTERS

57

CONFERENCE ORGANIZATION

General Chairs: Anand R. Prasad (DoCoMo Euro-Labs, Germany) Rainer Lienhart (University of Augsburg, Germany)

Technical Program Coordinator: Chitra Dorai (IBM T.J. Watson Research Center, USA)

Program Chairs: Multimedia Content Alan Hanjalic (Delft University of Technology, The Netherlands) Multimedia Systems Sunghyun Choi (Seoul National University, South Korea) Multimedia Applications Brian Bailey (University of Illinois at Urbana-Champaign, USA) Multimedia Interaction Nicu Sebe (University of Amsterdam, The Netherlands)

Short Paper Chairs: Multimedia Content Chitra Dorai (IBM T.J. Watson Research Center, USA) Multimedia Systems Julien Laganier (DoCoMo Euro-Labs, Germany) Multimedia Applications Susanne Boll (University of Oldenburg, Germany)

Workshop Paper Chairs: Belle Tseng (NEC Labs America, USA) Daniel Gatica-Perez (IDIAP Research Institute, Switzerland)

Tutorial Chairs: Benoit Huet (Eurecom, France) Malcolm Slaney (Yahoo! Research, USA)

Publicity Chairs: Wolfgang Effelsberg (University Mannheim, Germany) Yong Rui (Microsoft Research, USA) Alf Zugenmaier (DoCoMo Euro-Labs, Germany)

Demonstration Chairs: Milind Naphade (IBM T.J. Watson Research Center, USA) Wei-Ying Ma (Microsoft Research, Asia, P.R. China)

Doctorial Symposium Chairs: Thomas Plagemann (University of Oslo, Norway) Vera Goebel (University of Oslo, Norway)

Panels Chairs: Yap-Peng Tan (Nanyang Technological University, Singapore) Mohan S Kankanhalli (National University of Singapore, Singapore)

Interactive Art Program Frank Nack (University Claude Bernard Lyon 1, France) Chairs: Thomas Rist (Augsburg University of Applied Sciences, Germany) Alejandro Jaimes (IDIAP Research Institute, Switzerland)

59

Video Program Chair: Thomas Haenselmann (University of Mannheim, Germany)

Brave New Topics Chairs: Edward Chang (Google Research, P.R. China) Shin'ichi Satoh (National Institute of Informatics, Japan)

Open Source Competition Chair: Apostol Natsev (IBM T.J. Watson Research Center, USA)

Proceedings Chair: Roger Zimmermann (National University of Singapore, Singapore)

Registration Chairs: Yi Wu (Intel Research, USA) Marc Emmelmann (Technical University Berlin, Germany) Eva Hörster (University of Augsburg, Germany)

Treasurer: Barbara de Vega (University of Augsburg, Germany)

Sponsoring Chair: Arnon Amir (IBM Almaden Research Center, USA)

Travel Grant Committee: Chair: Chitra Dorai (IBM T.J. Watson Research Center, USA) David Gotz (IBM T.J. Watson Research Center, USA) Zhenghua Fu (IBM T.J. Watson Research Center, USA)

Local Arrangements Chairs: Gregor van den Boogaart (University of Augsburg, Germany) Jochen Lux (University of Augsburg, Germany) Simon Hoffmann (University of Augsburg, Germany) Susanne Boll (University of Oldenburg, Germany)

Web Site Chairs: Simon Hoffmann (University of Augsburg, Germany) Benedikt Gleich (University of Augsburg, Germany)

ACM SIGMM Director of Nevenka Dimitrova (Philips Research, USA) Conferences

ACM SIGMM Chair: Ramesh Jain (University of California, Irvine, USA)

Technical Program Committee Multimedia Content: (Full Papers): Chair: Alan Hanjalic (Delft University of Technology, The Netherlands) Kiyoharu Aizawa (University of Tokyo, Japan) Noboru Babaguchi (Osaka University, Japan) Edward Chang (University of California, Santa Barbara, USA) Liang-Tien Chia (Nanyang Technological University, Singapore) Tat-Seng Chua (National University of Singapore, Singapore) Ajay Divakaran (MERL, USA) Chitra Dorai (IBM T.J. Watson Research Center, USA) Abdulmotaleb El Saddik (University of Ottawa, Canada) Daniel Ellis (Columbia University, USA) Yihong Gong (NEC Labs America, USA) William Grosky (University of Michigan, USA) Alexander Hauptmann (Carnegie Mellon University, USA)

60

Xian-Sheng Hua (Microsoft Research Asia, P.R. China) Horace Ip (City University of Hong Kong, Hong Kong) Mohan S Kankanhalli (National University of Singapore, Singapore) John Kender (Columbia University, USA) Irwin King (The Chinese University of Hong Kong, Hong Kong) Anil Kokaram (Trinity College Dublin, Ireland) Michael Lew (Leiden University, The Netherlands) Dongge Li (Motorola Laboratories, USA) Mark Liao (Academia Sinica, Taiwan) Lie Lu (Microsoft Research Asia, P.R. China) Jiebo Luo (Eastman Kodak Company, USA) Wei-Ying Ma (Microsoft Research Asia, P.R. China) Stephane Marchand-Maillet (University of Geneva, Switzerland) Nasir Memon (Polytechnic University, USA) Bernard Merialdo (Eurecom, France) Apostol Natsev (IBM T.J. Watson Research Center, USA) Chong-Wah Ngo (City University of Hong Kong, Hong Kong) Noel O'Connor (Dublin City University, Ireland) Fernando Pereira (IST-TUL, Portugal) Gopal Pingali (IBM T.J. Watson Research Center, USA) Yong Rui (Microsoft Research, USA) Shin'ichi Satoh (National Institute of Informatics, Japan) Bo Shen (Hewlett-Packard Laboratories, USA) Alan Smeaton (Dublin City University, Ireland) John R. Smith (IBM T.J. Watson Research Center, USA) Hari Sundaram (Arizona State University, USA) Qi Tian (University of Texas at San Antonio, USA) Svetha Venkatesh (Curtin University of Technology, Australia) Lynn Wilcox (FX Palo Alto Laboratory, USA) Marcel Worring (University of Amsterdam, Netherlands) Changsheng Xu (I2R, Singapore) Cha Zhang (Microsoft Research, USA)

Multimedia Systems: Chair: Sunghyun Choi (Seoul National University, South Korea) Kevin Almeroth (University of California, Santa Barbara, USA) Surendar Chandra (University of Notre Dame, USA) Ming-Syan Chen (National Taiwan University, Taiwan) Mark Claypool (Worcester Polytechnic Institute, USA) Pedro Cuenca (University of Castilla-La Mancha, Spain) Alberto Del Bimbo (University of Firenze, Italy) Wu-chang Feng (Portland State University, USA) Wu-chi Feng (Portland State University, USA) David Gotz (IBM T.J. Watson Research Center, USA) Carsten Griwodz (University of Oslo, Norway) Yoshihiro Kawahara (The University of Tokyo, Japan) Jong Won Kim (Gwangju Institute of Science & Technology, Korea) Taekyoung Kwon (Seoul National University, Korea)

61

Baochun Li (University of Toronto, Canada) Laurent Mathy (Lancaster University, UK) Andreas U. Mauthe (Lancaster University, UK) Ketan Mayer-Patel (University of North Carolina at Chapel Hill, USA) Sue Moon (KAIST, Korea) Liam Murphy (University College Dublin, Ireland) Klara Nahrstedt (University of Illinois at Urbana-Champaign, USA) Wei Tsang Ooi (National University of Singapore, Singapore) Balakrishnan Prabhakaran (University of Texas at Dallas, USA) Hayder Radha (Michigan State University, USA) Reza Rejaie (University of Oregon, USA) Keith W. Ross (Brooklyn Polytech, USA) Prashant Shenoy (University of Massachusetts, USA) Shervin Shirmohammadi (University of Ottawa, Canada) Hwangjun Song (Pohang University of Science and Technology, Korea) Michael Vernick (Avaya Labs Research, USA) Michael Zink (University of Massachusetts, USA)

Multimedia Applications: Chair: Brian Bailey (University of Illinois at Urbana-Champaign, USA) Brett Adams (Curtin University of Technology, Australia) John Adcock (FX Palo Alto Laboratory, USA) Elisabeth André (University of Augsburg, Germany) Yasuo Ariki (Kobe University, Japan) Frank Bentley (Motorola Laboratories, USA) Dick Bulterman (CWI, The Netherlands) Andrea Cavallaro (Queen Mary, University of London, UK) Ee-Chien Chang (National University of Singapore, Singapore) Elaine Chew (University of Southern California, USA) Matthew Cooper (FX Palo Alto Laboratory, USA) Berna Erol (Ricoh California Research Center, USA) Jianping Fan (University of North Carolina at Charlotte, USA) Anthony Fang (National University of Singapore, Singapore) Jim Gemmell (Microsoft Research, USA) David Gerhard (University of Regina, Canada) Vera Goebel (University of Oslo, Norway) Forouzan Golshani (Wright State University, USA) Thomas Haenselmann (University of Mannheim, Germany) Karrie Karahalios (University of Illinois at Urbana-Champaign, USA) Wei Lai (Microsoft Research Asia, P.R. China) Peiya Liu (Siemens Corporate Research, USA) Shivajit Mohapatra (Motorola Laboratories, USA) Mor Naaman (Yahoo! Research Berkeley, USA) Balakrishnan Prabhakaran (University of Texas at Dallas, USA) Nicolas Roussel (LRI & INRIA Futurs, France) Lloyd Rutledge (CWI, The Netherlands) Andreas Schrader (University of Luebeck, Germany) Timothy Shih (Tamkang University, Taiwan)

62

Zhen Wen (IBM T. J. Watson Research Center, USA) Andy Wilson (Microsoft Research, USA) Jiang-Yu Zheng (Indiana University, USA) Michelle Zhou (IBM T. J. Watson Research Center, USA)

Multimedia Interaction: Chair: Nicu Sebe (University of Amsterdam, The Netherlands) Antonis Argyros (University of Crete, Greece) Barbara Barry (MIT Media Lab, USA) Erhardt Barth (University of Lübeck, Germany) Paulo Barthelmess (Adapx, USA) Susanne Boll (University of Oldenburg, Germany) Herve Bourlard (IDIAP Research Institute, Switzerland) Ira Cohen (Hewlett-Packard Laboratories, USA) David Demirdjian (MIT, USA) Andreas Dengel (DFKI, Germany) Ahmed Elgammal (Rutgers University, USA) Daniel Gatica-Perez (IDIAP Research Institute, Switzerland) Alejandro Jaimes (IDIAP Research Institute, Switzerland) Ashish Kapoor (Microsoft Research, USA) Andruid Kerne (Texas A&M University, College Station, USA) Michael Lyons (Ritsumeikan University, Japan) Frank Nack (University Claude Bernard Lyon 1, France) Jean-Marc Odobez (IDIAP Research Institute, Switzerland) Kazuhiro Otsuka (NTT, Japan) Maja Pantic (Imperial College, UK) Montse Pardas (Technical University of Catalonia, Spain) Ioannis Patras (Queen Mary, University of London, UK) Vladimir Pavlovic (Rutgers University, USA) Catherine Pelechaud (University of Paris 8, France) Gerasimos Potamianos (IBM T. J. Watson Research Center, USA) Patrick Schmitz (University of California, Berkeley, USA) Rainer Stiefelhagen (University of Karlsruhe, Germany) Matthew Turk (University of California, Santa Barbara, USA) Gerd Westermann (SEraja Technologies, Germany) Jie Yang (Carnegie Mellon University, USA) Ming-Hsuan Yang (Honda Research, USA) Massimo Zancanaro (ITC-irst, Italy)

Additional Reviewers for Full Papers: Golam Ashraf (National University of Singapore, Singapore) Pradeep Atrey (University of Ottawa, Canada) Brian Bailey (University of Illinois, USA) Nikolaos Boulgouris (KCL, UK) Rui Cai (Microsoft Research Asia, P.R. China) David Chatting (British Telecom, UK) Trista Chen (FX Palo Alto Laboratory, USA) Ivan Damnjanovic (Queen Mary, University of London, UK)

63

Christophe De Vleeschouwer (Universite Catholique de Louvain, Belgium) Alexandre François (University of Southern California, USA) Andreas Girgensohn (FX Palo Alto Laboratory, USA) Arthur Goshtasby (Wright State University, USA) Karrie Karahalios (University of Illinois, Urbana Champaign, USA) Jayashree Karlekar (National University of Singapore, Singapore) Thomas Kieninger (DFKI GmbH, Germany) Don Kimber (FX Palo Alto Laboratory, USA) Zhiwei Li (Microsoft Research Asia, P.R. China) Chi Wan Lim (Insitute of High Performance Computing, Singapore) Kok-Lim Low (National University of Singapore, Singapore) Emilio Maggio (Queen Mary University of London, UK) Marta Mrak (Queen Mary University of London, UK) Son Nguyen (National University of Singapore, Singapore) Yong Pei (Wright State University, USA) Guojun Qi (Microsoft Research Asia, P.R. China) Tye Rattenbury (University of California, Berkeley, USA) Ansgar Scherp (Oldenburg R&D Institute for Information Technology Tools and Systems (OFFIS), Germany) David Shamma (Yahoo! Research Berkeley, USA) Olivier Steiger (ABB, Switzerland) Thang Truong (National University of Singapore, Singapore) Changhu Wang (University of Science and Technology of China, P.R. China) Xin-Jing Wang (Microsoft Research Asia, P.R. China) John Winn (Microsoft Research Cambridge, UK) Thomas Wischgoll (Wright State University, USA) Lai Kuan Wong (National University of Singapore, Singapore) Lei Zhang (Microsoft Research Asia, P.R. China) Sheng Zhang (National University of Singapore, Singapore) Yu Zheng (Microsoft Research Asia, P.R. China) Roger Zimmermann (National University of Singapore, Singapore) Lawrence Zitnick (Microsoft Research, USA)

Technical Program Committee Multimedia Content: (Short Papers): Chair: Chitra Dorai (IBM T.J. Watson Research Center, USA) Arnon Amir (IBM Almaden Research Center, USA) Jonathan Connell (IBM Research, USA) Chitra Dorai (IBM T.J. Watson Research Center, USA) Robert Farrell (IBM, USA) Eva Hörster (University of Augsburg, Germany) Giridharan Iyengar (IBM T.J. Watson Research Center, USA) John Kender (Columbia University, USA) Xuelong Li (University of London, UK) Ying Li (IBM T.J. Watson Research Center, USA) Gary Marchionini (University of North Carolina at Chapel Hill, USA)

64

Vincent Oria (NJIT, USA) Gopal Pingali (IBM T.J. Watson Research Center, USA) Srinivasan Sengamedu (Yahoo India, India) Jialie Shen (Singapore Management University, Singapore) Malcolm Slaney (Yahoo! Research, USA) Dacheng Tao (The Hong Kong Polytechnic University, Hong Kong) C. Gregor van den Boogaart (University of Augsburg, Germany) Lexing Xie (IBM Research, USA)

Multimedia Systems: Chair: Julien Laganier (DoCoMo Euro-Labs, Germany) Imad Aad (DoCoMo Euro-Labs, Germany) Marcelo Bagnulo (University of Carlos III de Madrid, Spain) Gonzalo Camarillo (Ericsson, Finland) Lars Eggert (Nokia Research Center, Finland) Ahsan Habib (Siemens TTB, USA) Wassim Haddad (Ericsson Research, Sweden) Hermann Hellwagner (University of Klagenfurt, Austria) Ulas Kozat (DoCoMo USA Labs, USA) Gabriel Montenegro (Microsoft Corporation, USA) R. Venkatesha Prasad (Delft University of Technology, The Netherlands) Christian Timmerer (University of Klagenfurt, Austria) Hannes Tschofenig (Nokia Siemens Networks, Germany) Christian Vogt (Ericsson Research Nomadic Lab, Finland)

Multimedia Applications: Chair: Susanne Boll (University of Oldenburg, Germany) Lalitha Agnihotri (Philips Research, USA) Elisabeth André (University of Augsburg, Germany) Yannis Avrithis (National Technical University of Athens, Greece) Kathrin Berkner (Ricoh Innovations, USA) Andreas Butz (University of Munich, Germany) Wei-Ta Chu (National Taiwan University, Taiwan) Hans Gellersen (Lancaster University, UK) Andreas Girgensohn (FX Palo Alto Laboratory, USA) Lynda Hardman (CWI & TU/e, The Netherlands) Hermann Hellwagner (Klagenfurt University, Austria) Otthein Herzog (University of Bremen, Germany) Wolfgang Hürst (Albert-Ludwigs-University of Freiburg, Germany) Ebroul Izquierdo (Queen Mary, University of London, UK) Christian Kray (University of Newcastle Upon Tyne, UK) Erik Mannens (Ghent University, Belgium) Andreas Mauthe (Lancaster University, UK) Klaus Meyer-Wegener (University of Erlangen and Nuremberg, Germany) Wolfgang Müller (Bamberg University, Germany) Mor Naaman (Yahoo! Research Berkeley, USA)

65

Frank Nack (University Claude Bernard Lyon 1, France) Andreas Nürnberger (Otto-von-Guericke-University of Magdeburg, Germany) Zeljko Obrenovic (CWI, The Netherlands) Dinh Phung (Curtin University of Technology, Australia) Thomas Plagemann (University of Oslo, Norway) Michael Rohs (Deutsche Telekom Laboratories, TU Berlin, Germany) Enrico Rukzio (Lancaster University, UK) Lloyd Rutledge (CWI, The Netherlands) Ansgar Scherp (OFFIS Institute for Information Technology, Germany) Cees Snoek (University of Amsterdam, The Netherlands) Hari Sundaram (Arizona State University, USA) Raphael Troncy (CWI, The Netherlands) Jana Urban (University of Glasgow, UK) Lars Wolf (TU Braunschweig, IBR, Germany)

Additional Reviewers: John Adcock (FX Palo Alto Laboratory, USA) Nadia Baaziz (Universite du Quebec en Outaouais, Canada) Wolf-Tilo Balke (L3S Research Center, Germany) Tat-Seng Chua (National University of Singapore, Singapore) Cyril Concolato (GET-ENST, France) James Fung (University of Toronto, Canada) Daniel Gatica-Perez (IDIAP Research Institute, Switzerland) Amy Gooch (Northwestern University, USA) Carsten Griwodz (Simula Research Laboratory, Norway) Enrico Hauer (Fraunhofer SIT, Germany) Andreas Hein (University of Oldenburg, Germany) Niels Henze (OFFIS Research Institute of Information Technology, Germany) Otmar Hilliges (University of Munich, Germany) Simon Hoffmann (University of Augsburg, Germany) Alejandro Jaimes (IDIAP Research Institute, Switzerland) Ton Kalker (Hewlett Packard Laboratories, USA) Ingo Kofler (Klagenfurt University, Austria) Hyowon Lee (Centre for Digital Video Processing, Dublin City University, Ireland) Karin Leichtenstern (University of Augsburg, Germany) Seong-Whan Lee (Korea University, Korea) Ketan Mayer-Patel (University of North Carolina at Chapel-Hill, USA) Florian Obermeier (TU München, Germany) Martin Pielot (OFFIS Research Institute of Information Technology, Germany) Martin Prangl (Klagenfurt University, Austria) Philipp Sandhaus (OFFIS Institute for Information Technology, Germany) Thomas Schlämer (University of Oldenburg, Germany) Eckehard Steinbach (Munich University of Technology, Germany)

66

Tinne Tuytelaars (Katholieke Universiteit Leuven, Belgium) Jamie Ward (Lancaster University, UK) Roger Zimmermann (National University of Singapore, Singapore) Fredrik Ǻberg (Ericsson Research Nomadic Lab, Finland) Carlos Bernardos (University of Carlos III de Madrid, Spain) Roland Bless (University of Karlsruhe, Germany) Pablo Cancela (University of Republica Oriental del Uruguay, Uruguay) Monica Cortes Sack (University of Carlos III de Madrid, Spain) Pierre Garrigues (University of California at Berkeley, USA) Ladan Gharai (University of Southern California/ISI, USA) Alvaro Gomez (University of Republica Oriental del Uruguay, Uruguay) Stuart Goose (Siemens TTB, USA) Miska Hannuksela (Nokia Research Center, Finland) Mohamed Hefeeda (Simon Fraser University, Canada) Markus Kampmann (Ericsson Research, Germany) Sandeep Kanumuri (DoCoMo USA Labs, USA) Ingo Kofler (University of Klagenfurt, Austria) Miika Komu (Helsinki Institute for Information Technology, Finland) Daniel Kraft (University of Karlsruhe, Germany) Jose Felix Kukielka (University of Carlos III de Madrid, Spain) Robert Kuschnig (University of Klagenfurt, Austria) Ora Lassila (Nokia Research Center, USA) Frederico Lecumberry (University of Republica Oriental del Uruguay, Uruguay) Marco Liebsch (NEC Network Labs, Germany) Arto Mahkonen (Ericsson, Finland) Shahbaz Nazrul (Qualcomm, USA) Antonio de la Oliva (University of Carlos III de Madrid, Spain) Wei Tsang Ooi (National University of Singapore, Singapore) Joerg Ott (Helsinki University of Technology, Finland) Colin Perkins (University of Glasgow, UK) Muralishankar Rangarao (PES Institute of Technology, India) Vijay S. Rao (ESQUBE Communication Solutions, India) Christian Schaefer (DoCoMo Euro-Labs, Germany) Thomas Schreck (Fachhochschule Landshut, Germany) Isaac Seoane (University of Carlos III Madrid, Spain) Wilson So (Siemens TTB, USA) Christoph Sorge (University of Karlsruhe, Germany) Ignacio Soto (University of Carlos III de Madrid, Spain) S. H. Srinivasan (Yahoo!, India) Marius Tico (Nokia Research Center, Finland) Mejdi Trimeche (Nokia Research Center, Finland) Vlasios Tsiatsis (Ericsson, Sweden) Samu Varjonen (Helsinki Institute for Information Technology, Finland) Claudia Villalonga (NEC Network Labs, Germany) Stephan Wenger (Nokia Corporation, USA) Lars Wolf (Technical University of Braunschweig, IBR, Germany) Alf Zugenmaier (DoCoMo Euro-Labs, Germany)

67

Kiyoharu Aizawa (Tokyo University, Japan) Pradeep Kumar (Atrey University of Ottawa, Canada) Noboru Babaguchi (Osaka University, Japan) Kobus Barnard (University of Arizona, USA) Rui Cai (Microsoft Research Asia, P.R. China) Mingyu Chen (Carnegie Mellon University, USA) Tat-Seng Chua (National University of Singapore, Singapore) Antonio De La Oliva (University of Carlos III de Madrid, Spain) Abdulmotaleb El Saddik (University of Ottawa, Canada) Sheng Gao (Institute for Infocomm Research, Singapore) William Grosky (University of Michigan, USA) Ahsan Habib (Siemens TTB, USA) Alan Hanjalic (Delft University of Technology, The Netherlands) Simon Hoffmann (University of Augsburg, Germany) Benoit Huet (Institut Eurecom, France) Alejandro Jaimes (IDIAP Research Institute, Switzerland) Mohan S Kankanhalli (National University of Singapore, Singapore) Yoshihiko Kawai (NHK, Japan) Wei Lai (Microsoft Research Asia, P.R. China) Geetika Lakshmanan (IBM Research, USA) Michael Lew (Leiden University, The Netherlands) Dongge Li (Motorola Laboratories, USA) Mingjing Li (Microsoft Research Asia, P.R. China) Jochen Lux (University of Augsburg, Germany) Bernard Merialdo (Institut Eurecom, France) Alexandre Miège (University of Ottawa, Canada) Shi-Yong Neo (National University of Singapore, Singapore) Naoko Nitta (Osaka University, Japan) Fernando Pereira (IST-TUL, Portugal) Thomas Rist (Augsburg University of Applied Sciences, Germany) Shin'ichi Satoh (National Institute of Informatics, Japan) Nicu Sebe (University of Amsterdam, The Netherlands) Bo Shen (Hewlett Packard Laboratories, USA) Yaxiao Song (University of North Carolina at Chapel Hill, USA) Changhu Wang (University of Science and Technology of China, P.R. China) Wei Wang (Motorola Laboratories, USA) Kevin Wilson (MERL, USA) Jianfeng Xu (Tokyo University, Japan) Rong Yan (IBM T.J. Watson Research Center, USA) Jun Yang (Carnegie Mellon University, USA) Yuan Yuan (Aston University, UK) Cha Zhang (Microsoft Research, USA) Dongqing Zhang (Thomson Research, USA) Lei Zhang (Microsoft Research Asia, P.R. China)

Interactive Art Exhibition Annet Decker (Montevideo, The Netherlands) Curators: Frank Nack (University Claude Bernard Lyon 1, France)

68

Anne Nigten (V2_ Institute for the Unstable Media, The Netherlands) Thomas Rist (Augsburg University of Applied Sciences, Germany) Alejandro Jaimes (IDIAP Research Institute, Switzerland)

Interactive Art Program Xavier Amatriain (Telefonica R&D, Spain) Committee: Peter Andres (Independent, USA) Barbara Barry (MIT Media Lab, USA) Jeffrey Boyd (University of Calgary, CA) Sher Doruff (Waag Society, NL) Jonathan Foote (Independent, USA) Joost Geurts (INRIA, France) Andrew Gordon (University of Southern California, USA) Sabine Himmelsbach (Edith Russ Site for Media Art, Germany) Hayley Hung (IDIAP Research Institute, Switzerland) Andruid Kerne (Texas A&M University, USA) Nisar Keshvani (Leonardo Electronic Almanaca/Queensland University of Technology) Julian Knowles (Queensland University of Technology, Australia) Akihiro Kubota (Tama Art University, Japan) Felipe Londono (University of Caldas, Colombia) Michael Lyons (Ritsumeikan University, Japan) Roger Malina (Leonardo/ISAST, USA) Steve Mann (University of Toronto, Canada) Jose-Carlos Mariategui (ATA, Peru) Aranxta Mendiharat (Leonardo, Spain) Wolfgang Muench (LASALLE, Singapore) Laurence Noel (Mondeca, France) Claudio Pinhanez (IBM Research, USA) Wim van der Plas (University of Utrecht, The Netherlands) Daniela Plewe (National University of Singapore, Singapore) Nicolas Reeves (University of Quebec in Montreal, Canada) Remi Ronfard (Artificial Life, Canada) Andrew Senior (IBM, USA) Patrick Schmitz (University of California at Berkeley, USA) Xin Wei Sha (Concordia University, Canada) David A. Shamma (Yahoo! Research Berkeley, USA) Ryan Shaw (University of California at Berkeley, USA) Yukiko Shikata (NTT InterCommunication Center, Japan) Flavia Sparacino (Sensing Places/MIT, USA) Hari Sundaram (Arizona State University, USA) Atau Tanaka (Sony CSL Paris, France) Nicolas Tsingos (INRIA, France) Ron Wakkary (Simon Fraser University, Canada)

Interactive Art Program Thomas Rist (Augsburg University of Applied Sciences, Germany) Coordinators: Robert Rose (Augsburg University of Applied Sciences, Germany)

69

Open Source Competition Chair: Apostol Natsev (IBM T.J. Watson Research Center, USA) Committee: Ashish Gehani (SRI, USA) Matthew Hill (IBM T. J. Watson Research Center, USA) Rong Yan (IBM T. J. Watson Research Center, USA) Jun Yang (Carnegie Mellon University, USA)

70 CO-SPONSORS

SUPPORTERS

Become an ACM MM 2007 Corporate Supporter!

The conference organizers warmly invite your support of ACM Multimedia 2007. Corporate support publicizes your organization's interest in and commitment to the multimedia field. A premier event with international visibility, ACM MM 2007 is the perfect place to inform leaders and students in the field, as well as the interested general public, about your company's activities and products.

The conference recognizes two levels of contribution: Corporate Benefactors and Corporate Sponsors.

Sponsors ($2,000 to 4,999 U.S.)

In recognition of your support at the Sponsor level:

• Your name and logo will be included on conference announcements and the program. • Your company's name, logo, brief description, and link will be included in the conference web site, maintained at http://www.acmmm07.org/ • We will announce your company's contribution at the opening and closing sessions of the conference. • You will have the opportunity to include material and give-always with the conference material for each attendee. • You will receive one free registration for someone from your company to attend the conference. • You will be invited to give a demonstration of your choice at the ACM MM 2007 demo night.

Benefactors ($5,000 U.S. or greater contribution)

Corporate Benefactors receive all the benefits of sponsors as well as the following additional acknowledgements:

• Your name will be listed in all the material as a Benefactor. You will receive special acknowledgement as a benefactor in the conference announcements and publications. • A conference event, such as a coffee break, luncheon, or reception, will be named after your company. Event naming is based on the amount of the contribution and otherwise on a first-come-first-served basis. • You will receive one additional free registration for a second individual from your company to attend the conference.

Please contact the conference sponsoring chair, Arnon Amir, [email protected] for more information and to arrange your company's support of ACM MM 2007.