21th ACM Multimedia October 21-25, 2013 BARCELONA Contents
Message from the General Chairs……………………………………………………………………………………………………………………………………… ▶ 3 MM 2013 Conference Organization…………………………………………………………………………………………………………………………………… ▶ 7 Technical Program Area Chairs…………………………………………………………………………………………………………………………………………… ▶ 11 Keynote Talks……………………………………………………………………………………………………………………………………………………………………………… ▶ 13 Multimedia Art Exhibition 2013………………………………………………………………………………………………………………………………………… ▶ 17 Program at a Glance………………………………………………………………………………………………………………………………………………………………… ▶ 19
Oct. 21, 2013………………………………………………………………………………………………………………………………………………………………………………… ▶ 27
Oct. 22, 2013………………………………………………………………………………………………………………………………………………………………………………… ▶ 43
Oct. 23, 2013………………………………………………………………………………………………………………………………………………………………………………… ▶ 55
Oct. 24, 2013………………………………………………………………………………………………………………………………………………………………………………… ▶ 69 Contents
Oct. 25, 2013………………………………………………………………………………………………………………………………………………………………………………… ▶ 81
Area Map with Conference Location……………………………………………………………………………………………………………………………… ▶ 95
Places of Interest………………………………………………………………………………………………………………………………………………………………………… ▶ 99
1 Message from the General Chairs
We are delighted to welcome you to the 21st ACM International Conference on Multimedia, ACM Multimedia 2013, which will be held from October 21th to October 25th, 2013 in Barcelona, Spain.
Barcelona was founded on the Mediterranean coast, between two rivers, over 2,000 years ago. Since then, it has been the traditional gateway to Spain. Through it entered Romans, Arabs and Christians, as well as the many diverse cultures, which came to enrich its heritage. The traces of this history and diversity can be followed as you walk through the city; through its Gothic Quarter, built on the Roman ruins; through its art-nouveau Eixample district, presided over by Gaudí’s exuberant architecture, which at the same time reveals an ordered and rational urban layout. This diversity and harmony are also apparent in the character of the people of Barcelona, who are enterprising and hard-working, enjoy life and, in particular, have great civic pride and are lovers of culture.
These “multimedia” characteristics have made Barcelona into a first-class tourist destination and the ideal setting for meetings and congresses. This open, welcoming city, which shed its skin and opened up to the sea in order to host the 1992 Olympic Games, has since then focused its energies on another major global project: the 2004 Forum of Cultures. This event, the renewed expression of Barcelona’s vocation to be an international benchmark for meetings and dialogue, has made it possible to complete the city’s seafront, and improve significantly its range of services in the field of congresses, hotels and catering and culture. In a nutshell, Barcelona is the perfect venue for ACM Multimedia and we hope you will enjoy Barcelona as much as its inhabitants do it every single day!
ACM Multimedia is the premier conference and worldwide event bringing together multimedia experts and practitioners across academia and industry. The central feature of the conference, which continues this year as in every year since its inception, is the outstanding Technical Program. This year’s conference features both oral and poster presentations covering all aspects of the multimedia field chosen through a highly selective review process.
In addition to the Technical Program, this year’s conference features a diverse range of activities including Panels, Demonstrations, and Tutorials. Additionally, a wide array of Workshops brings focus on new topics for investigation. The conference features also special sessions on Brave New Ideas, a 3 Grand Challenge contest and Open Source Software Competition and includes a Doctoral Symposium • The Multimedia Art Exhibition features both invited and selected artists. It will open for the duration for mentoring graduate students. Finally, the conference provides a rich Multimedia Art Exhibition of the conference in the satellite venue located in the center of the city. to stimulate artists and researchers alike to meet and discover the frontiers of multimedia artistic • Following the last two years’ precedent, Tutorials are made free for all participants. communication! • Recognizing that students are the lifeblood of our next generation of multimedia thinkers, this year’s Student Travel Grant is greatly expanded. Innovations for this Year’s Conference: We hope these innovations make for a special conference this year. In attempt to continuously improve ACM Multimedia and ensure its vibrant role for the multimedia community, we have made a number of enhancements for this year’s conference: We greatly acknowledge those who have contributed to the success of ACM Multimedia 2013. We • The Technical Program Committee defined twelve Technical Areas for major focus for this year’s thank the organizers of ACM Multimedia 2012 for their useful suggestions and comments which conference, including introducing new Technical Areas for Music & Audio and Crowdsourcing helped us to improve the organization the 2013 edition. We also thank them for giving us the template to reflect their growing interest and promise. We have also changed the names of some traditional for this booklet. We thank the many paper authors and proposal contributors for the various technical Technical Areas and provided extensive description of each area to help the authors choosing the and program components. We thank the large number of volunteers, including the Organizing most appropriate Technical Area for their manuscripts. Committee members and Technical Program Committee members who worked very hard to create • We have introduced a new role in the organization of the conference: the author’s advocate. His this year’s outstanding conference. Every aspect of the conference was also aided by local committee explicit role was to listen to the authors, and to help them if reviews are clearly below average members and by the hard work of Grupo Pacifico, to whom we are very grateful. We thank also ACM quality. The authors could request the mediation of the author’s advocate after the reviews have staff and Sheridan Printing Company for their constant support. been sent to them and they had to clearly justify the reasons why such mediation is needed (the reviews or the meta-review were below average quality). The task of the advocate was to investigate Finally, we thank our many supporters who generously supported ACM Multimedia 2013. They carefully the matter and to request additional review or reexamination of the decision of the include FXPAL, HUAWEI, YAHOO! LABS, Technicolor, MediaMixer, Microsoft Research, particular manuscript. This year, the author’s advocate was Pablo Cesar, CWI, The Netherlands. Facebook, IBM Research, Telefonica, Google, and INRIA. Other generous support was kindly • We have decided to keep a couple of plenary sessions which will bring singular focus to conference provided by SIGMM, Springer, and NSF. activities: keynotes, Multimedia Grand Challenge competition, Best Paper session, Technical Achievement Award and Best PhD Award sessions. The other technical sessions are held in parallel to allow pursuit of more specialized interests at the conference. We have limited the number of Alejandro Jaimes Nicu Sebe Nozha Boujemaa parallel session to no more than 3 to minimize the risk of having overlapping interests. Yahoo Labs, Spain University of Trento, Italy INRIA, France • The use of video spotlights for advertising the works to be presented. These were meant to offer all attendees an opportunity to become aware of the content of each paper, and thus to be attracted to ACM Multimedia 2013 General Chairs attend the corresponding poster or talk. • Workshops and Tutorials are held on separate days from the main conference in order to reduce conflict with the regular Technical Program.
4 5 MM 2013 Conference Organization
General Chairs: Alejandro (Alex) Jaimes (Yahoo Labs, Spain) Nicu Sebe (University of Trento, Italy) Nozha Boujemaa (INRIA, France) Program Chairs: Daniel Gatica-Perez (IDIAP & EPFL, Switzerland) David A. Shamma (Yahoo!, USA) Marcel Worring (University of Amsterdam, The Netherlands) Roger Zimmermann (National University of Singapore, Singapore) Author's Advocate: Pablo Cesar (CWI, The Netherlands)
Multimedia Grand Challenge Chair: Yiannis Kompatsiaris (CERTH, Greece) Neil O’Hare (Yahoo Labs, Spain)
Interactive Arts Chairs: Antonio Camurri (University of Genova, Italy) Marc Cavazza (University of Teesside, UK)
Local Arrangement Chair: Mari-Carmen Marcos (University Pompeu Fabra, Spain)
Sponsorship Chairs: Ricardo Baeza-Yates (Yahoo Labs, Spain) Bernard Merialdo (Eurecom, France)
Panel Chairs: Yong Rui (Microsoft, China) Winston Hsu (National Tawain University, Taiwan) Michael Lew (University of Leiden, The Netherlands)
7 Brave New Ideas Chairs: Web & Social Media Chair: Jiebo Luo (University of Rochester, USA) Michele Trevisol (Yahoo Labs, Spain) Shuicheng Yan (National University of Singapore, Singapore) Program Booklet Editors: Doctorial Symposium Chairs: Junjie Cai(University of Texas San Antonio, USA) Hayley Hung (Technical University of Delft, The Netherlands) Yang Zhou(University of Texas San Antonio, USA) Marco Cristani (University of Verona, Italy) History Preservation Chairs: Open Source Software Competition Chairs: Selcuk Candan (Arizona State University USA) Ioannis (Yiannis) Patras (Queen Mary, University of London, UK) Noboru Babaguchi (Osaka University, Japan) Andrea Vedaldi (Oxford University, UK) SIGMM Chair: Tutorial Chairs: Shih-Fu Chang (Columbia University, US) Kiyoharu Aizawa (University of Tokyo, Japan) Lexing Xie (Australian National University, Australia) SIGMM Director of Conferences: Nicu Sebe (University of Trento, Italy) Workshop Chairs: Maja Pantic (Imperial College, UK ) Vladimir Pavlovic (Rutgers University, USA)
Student Travel Grant Chairs: Ramanathan Subramanian (ADSC, Singapore) Jasper Uijlings (University of Trento, Italy)
Publicity Chairs: Marco Bertini (University of Florence, Italy) Ichiro Ide (Nagoya University, Japan)
Technical Demo Chairs: Yi Yang (Carnegie Mellon University, USA) Xavier Anguera (Telefonica Research, Spain)
Proceedings Chairs: Bogdan Ionescu (University Politehnica of Bucharest, Romania) Qi Tian (University of Texas San Antonio, USA)
8 9 Technical Program Area Chairs
Art, Entertainment, and Culture: Antonio Camurri, University of Genoa (Italy) Marc Cavazza, University of Teesside (United Kingdom)
Authoring and Collaboration: Aisling Kelliher, Carnegie Mellon University (United States) Raphael Troncy, EURECOM (France)
Crowdsourcing: Martha Larson, Delft University of Technology (Netherlands) Wei Tsang Ooi, National University of Singapore (Singapore)
Media Transport and Delivery: Michael Zink, University of Massachusetts (United States) Wanmin Wu, Ricoh (United States)
Mobile & Multi-device: Jochen Huber, SUTD (Singapore) & MIT Media Lab (United States) Winston Hsu, University of Taiwan (Taiwan)
Multi-media Analysis: Dhiraj Joshi, FX Palo Alto Lab, Inc. (United States) Lei Zhang, Tsinghua University (China) Matthew Cooper, FX Palo Alto Lab Inc. (United States) Rainer Lienhart, Universitt Augsburg (Germany) Shuicheng Yan, National University of Singapore (Singapore)
Multi-media HCI: Frank Bentley, Yahoo Labs (United States) Max Mühlhäuser, Technische Universität Darmstadt (Germany)
Music & Audio: Bryan Pardo, Northwestern University (United States) Cynthia Liem, Delft University of Technology (Netherlands) 11 Keynote Talks Search, Browsing and Discovery: Alan Smeaton, Dublin City University (Ireland) Multimedia Framed Roelof van Zwol, Netflix (United States) Dr. Elizabeth F. Churchill (Ebay Research Labs) Tao Mei, Microsoft Research Asia (China) Zheng-Jun Zha, National University of Singapore (Singapore) Abstract: Multimedia is the combination of several media forms. Information designers, educationalists and Security and Forensics: artists are concerned with questions such as: Is text, or audio or video, or a combination of all three, Hyoung Joong Kim, Korea University (Republic of Korea) the best format for the message? Should another modality (e.g., haptics/touch, olfaction) be invoked Rita Cucchiara, University of Modena and Reggio Emilia (Italy) instead to make the message more effective and/or the experience more engaging? How does the Social Media & Presence: setting affect perception/reception? How does framing affect people’s experience of multimedia? How Lyndon Kennedy, Yahoo Research (United States) is the artifact changed through interaction with audience members? Munmun De Choudhury, Microsoft Research (United States) In this presentation, I will talk about people’s experience of multimedia artifacts like videos. I will Systems and Middleware: discuss the ways in which framing affects how we experience multimedia. Framing can be intentional– Mohamed Hefeeda, Simon Fraser University (Canada) scripted creations produced with clear intent by technologists, designers, media producers, media Pascal Frossard, EPFL (Switzerland) artists, film-makers, archivists, documentarians and architects. Framing can also be unintentional. Everyday acts of interest and consumption turn us, the viewers, into co-producers of the experiences of the multimedia artifacts we have viewed. We download, annotate, comment and share multimedia artifacts online. Our actions are reflected in viewcounts, displayed comments and content ranking. Our actions therefore change how multimedia artifacts are interpreted and understood by others.
Drawing on examples from the history of film and of performance art, from current social media research and from research conducted with collaborators over the past 16 years, I will illustrate how content understanding is modulated by context, by the “framing” of the content. I will consider three areas of research that are addressing the issue of framing, and that have implications for our understanding of ‘multimedia’ consumption, now and in the future: (1) The psychology and psychophysiology of multimedia as multimodal experience; (2) Emerging practices with contemporary social media capture and sharing from personal devices; and (3) Innovations in social media and audience analytics focused on more deeply understanding media consumption.
12 13 Keynote Talks I will conclude with some technical excitements, design/development challenges and experiential possibilities that lie ahead. The Space Between The Images
Leonidas J. Guibas (Stanford University) Dr. Elizabeth Churchill is Director of Human Computer Interaction at eBay Research Labs (ERL) in San Jose, California. Formerly a Principal Research Scientist at Yahoo! Research, she founded, staffed and managed the Internet Experiences Group. Abstract: Until September of 2006, she worked at the Palo Alto Research Center (PARC), California, in the Computing Science Lab (CSL). Multimedia content has become a ubiquitous presence on all our computing devices, spanning the gamut from Prior to that she formed and led the Social Computing Group at FX Palo Laboratory, Fuji Xerox’s research lab in Palo Alto. live content captured by device sensors such as smartphone cameras to immense databases of images, audio and video stored in the cloud. As we try to maximize the utility and value of all these petabytes of content, we Originally a psychologist by training, throughout her career Elizabeth has focused on understanding people’s social and often do so by analyzing each piece of data individually and foregoing a deeper analysis of the relationships collaborative interactions in their everyday digital and physical contexts. With over 100 peer reviewed publications and 5 edited between the media. Yet with more and more data, there will be more and more connections and correlations, books, topics she has written about include implicit learning, human-agent systems, mixed initiative dialogue systems, social because the data captured comes from the same or similar objects, or because of particular repetitions, aspects of information seeking, digital archive and memory, and the development of emplaced media spaces. She has been a symmetries or other relations and self-relations that the data sources satisfy. This is particularly true for media regular columnist for ACM interactions since 2008. of a geometric character, such as GPS traces, images, videos, 3D scans, 3D models, etc.
Elizabeth has a BSc in Experimental Psychology, an MSc in Knowledge Based Systems, both from the University of Sussex, In this talk we focus on the “space between the images”, that is on expressing the relationships and a PhD in Cognitive Science from the University of Cambridge. In 2010, she was recognised as a Distinguished Scientist by between different mutlimedia data items. We aim to make such relationships explicit, tangible, first- the Association for Computing Machinery (ACM). Elizabeth is the current Executive Vice President of ACM SigCHI (Human class objects that themselves can be analyzed, stored, and queried — irrespective of the media they Computer Interaction Special Interest Group). She is a Distinguished Visiting Scholar at Stanford University’s Media X, the originate from. We discuss mathematical and algorithmic issues on how to represent and compute industry affiliate program to Stanford’s H-STAR Institute. relationships or mappings between media data sets at multiple levels of detail. We also show how to analyze and leverage networks of maps and relationships, small and large, between inter-related data. The network can act as a regularizer, allowing us to to benefit from the “wisdom of the collection” in performing operations on individual data sets or in map inference between them.
We will illustrate these ideas using examples from the realm of 2D images and 3D scans/shapes — but these notions are more generally applicable to the analysis of videos, graphs, acoustic data, biological data such as microarrays, homeworks in MOOCs, etc. This is an overview of joint work with multiple collaborators, as will be discussed in the talk.
14 15 The ACM Multimedia 2013 Art Exhibition Dr. Leonidas Guibas obtained his Ph.D. from Stanford under the supervision of Donald Knuth. His main subsequent employers were Xerox PARC, DEC/SRC, MIT, and Stanford. He is currently the Paul Pigott Professor of Computer Science Location: Venue: FAD, Foment de les Arts i del Disseny, Plaça dels Àngels 5-6, Barcelona (and by courtesy, Electrical Engineering) at Stanford University. He heads the Geometric Computation group and is part Time : October 21-28, 2013 of the Graphics Laboratory, the AI Laboratory, the Bio-X Program, and the Institute for Computational and Mathematical Organizers: Marc Cavazza, Teesside University, UK Engineering. Professor Guibas’ interests span geometric data analysis, computational geometry, geometric modeling, computer Antonio Camurri, University of Genova, Italy graphics, computer vision, robotics, ad hoc communication and sensor networks, and discrete algorithms. Some well-known Reception: Only full conference attendees, Wednesday, Oct. 23, 7:30-9:00 pm. past accomplishments include the analysis of double hashing, red-black trees, the quad-edge data structure, Voronoi-Delaunay Exhibition open to the public. algorithms, the Earth Mover’s distance, Kinetic Data Structures (KDS), Metropolis light transport, and the Heat-Kernel Signature. Professor Guibas is an ACM Fellow, an IEEE Fellow and winner of the ACM Allen Newell award. 1. Emotion Forecast Maurice Benayoun (City University of Hong Kong) 2. Critical Anabela Costa (France) 3. Smile-Wall Shen-Chi Chen, He-Lin Luo, Kuan-Wen Chen, Yu-Shan Lin, Hsiao-Lun Wang, Che-Yao Chan, Kai-Chih Huang, Yi-Ping Hung (National Taiwan University) 4. SOMA Guillaume Faure (France) 5. A Feast of Shadow Puppetry Zhenzhen Hu, Min Lin, Si Liu, Jiangguo Jiang, Meng Wang, Richang Hong, Shuicheng Yan, Hefei University of Technology and NUS 6. Tele Echo Tube Hill Hiroki Kobayashi, Kaoru Saito, Akio Fujiwara (University of Tokyo) 7. 3D-Stroboscopy Sujin Lee (Sogang University, South Korea) 8. The Qi of Calligraphy He-Lin Luo, Yi-Ping Hung (Taiwan National University), I-Chun Chen (Tainan National University of the Arts) 9. Gestural Pen Animation Sheng-Ying Pao and Kent Larson (MIT Media Lab, USA) 10.MixPerceptions Jose San Pedro (Telefonica Research, Spain), Aurelio San Pedro (Escola Massana, Barcelona), Juan Pablo Carrascal (UPF, Barcelona), Matylda Szmukier (Telefonica Research, Spain)
16 17 Program at a Glance: October 21 Monday
Room 207 Room 412 Room 502 Room 409 4th ACM/IEEE ARTEMIS 2013 5th International International ACM Multimedia 2nd International Workshop on Workshop on Analysis Workshop on 9:00-11:00 Workshop on Socially- Multimedia for Cooking and Retrieval of Geotagging and Its Aware Multimedia and Eating Activities Tracked Events and Applications (CEA2013) Motion in Imagery Streams 11:00-11:30 Coffee 4th ACM/IEEE ARTEMIS 2013 5th International International ACM Multimedia 2nd International Workshop on Workshop on Analysis Workshop on 11:30-13:00 Workshop on Socially- Multimedia for Cooking and Retrieval of Geotagging and Its Aware Multimedia and Eating Activities Tracked Events and Applications (CEA2013) Motion in Imagery Streams 13:00-14:30 Lunch 4th ACM/IEEE ARTEMIS 2013 2nd ACM 5th International International International 2nd International Workshop on Workshop on Analysis Workshop on 14:30 - 16:30 Workshop on Socially- Multimedia for Cooking and Retrieval of Multimedia Analysis Aware Multimedia and Eating Activities Tracked Events and for Ecological Data (CEA2013) Motion in Imagery (MAED 2013) Streams 16:30-17:00 Coffee 4th ACM/IEEE ARTEMIS 2013 2nd ACM 5th International International International 2nd International Workshop on Workshop on Analysis Workshop on 17:00 - 18:30 Workshop on Socially- Multimedia for Cooking and Retrieval of Multimedia Analysis Aware Multimedia and Eating Activities Tracked Events and for Ecological Data (CEA2013) Motion in Imagery (MAED 2013) Streams
19 Program at a Glance: October 21 Monday Program at a Glance: October 22 Tuesday
Room 507 Room 503 Room 504 Room 607 Room 207 Room 412 Room 502 Room 409
Tutorial: Towards Next- International ACM Foundations and Workshop on Event- 4th International Tutorial: Social Tutorial: Multimedia Data-driven challenge- Generation Workshop on Applications of based Media Workshop on Human Interactions over Information 9:00-11:00 based workshop ACM Multimedia 9:00-11:00 Crowdsourcing for Semantic Integration and Behavior Geographic-Aware Retrieval: Music and MM 2013 – AVEC 2013 Recommendation Multimedia Technologies for Processing Understanding (HBU) Multimedia Systems Audio Systems (CrowdMM 2013) Multimedia Content
11:00-11:30 Coffee 11:00-11:30 Coffee
Tutorial: International ACM Tutorial: Towards 4th International Tutorial: Social Tutorial: Multimedia Foundations and Workshop on Event- Workshop on Data-driven challenge- Next-Generation Workshop on Human Interactions over Information Applications of based Media 11:30-13:00 Crowdsourcing for 11:30-13:00 based workshop ACM Multimedia Behavior Geographic-Aware Retrieval: Music and Semantic Integration and Multimedia MM 2013 – AVEC 2013 Recommendation Understanding (HBU) Multimedia Systems Audio Technologies for Processing (CrowdMM 2013) Systems Multimedia Content 13:00-14:30 Lunch 13:00-14:30 Lunch Tutorial: Blending International ACM the Physical and the 3rd International 4th International Tutorial: Privacy Tutorial: Workshop on Event- Workshop on Virtual in Musical Workshop on Tutorial: Massive- Workshop on Human Concerns of Sharing Crowdsourcing for based Media 14:30 - 16:30 Crowdsourcing for Technology: from 14:30 - 16:30 Interactive Multimedia Scale Multimedia Behavior Multimedia in Social Multimedia Integration and Multimedia interface design to on Mobile and Portable Semantic Modeling Understanding (HBU) Networks Research Processing (CrowdMM 2013) multimodal signal Devices (IMMPD’13) processing 16:30-17:00 Coffee 16:30-17:00 Coffee Tutorial: Blending 3rd International International ACM the Physical and the Tutorial: Workshop on Event- 4th International Tutorial: Privacy Workshop on Tutorial: Massive- Workshop on Virtual in Musical Crowdsourcing for based Media Workshop on Human Concerns of Sharing 17:00 - 18:30 Interactive Multimedia Scale Multimedia 17:00 - 18:30 Crowdsourcing for Technology: from Multimedia Integration and Behavior Multimedia in Social on Mobile and Portable Semantic Modeling Multimedia interface design to Research Processing Understanding (HBU) Networks Devices (IMMPD’13) (CrowdMM 2013) multimodal signal processing
20 21 Program at a Glance: October 22 Tuesday Program at a Glance: October 23 Wednesday
Room 507 Room 503 Room 504 Room 607 Room 113 Room 114 Room 115 Room 116 Room 118 8:45-9:00 Opening (GC) First ACM MM Workshop on Workshop on Workshop on Event- Keynote 1 (Elisabeth Churchill): Multimedia Framed Workshop on 9:00-10:00 Multimedia Indexing Personal Data Meets based Media Chair: David A. Shamma 9:00-11:00 Immersive Media and Information Distributed Integration and Experiences Retrieval for Healthcare Multimedia Processing 10:00-11:15 Best Paper Session (4 - 18 mins each) (ACM MM MIIRH) 11:15-11:45 Coffee break 11:00-11:30 Coffee Panel: Cross-Media First ACM MM Analysis and Mining Workshop on Workshop on Workshop on Event- Workshop on Oral session 1: Oral session 2: Music Mark Zhang, Alberto del Multimedia Indexing Personal Data Meets based Media 11:30-13:00 Immersive Media 11:45 - 13:00 Experience (4 - 18 mins and Play (4 - 18 mins Bimbo, Selcuk Candan, and Information Distributed Integration and Experiences each) each) Alexander Hauptmann, Retrieval for Healthcare Multimedia Processing Ramesh Jain, Alexis Joly, (ACM MM MIIRH) Yueting Zhuang 13:00-14:30 Lunch Journal of TOMCCAP First ACM MM Multimedia Editorial Workshop on Workshop on Workshop on Event- 13:00 - 14:45 Lunch (not provided) Board Meeting Workshop on Multimedia Indexing Personal Data Meets based Media Meeting (by (by 14:30 - 16:30 Immersive Media and Information Distributed Integration and invitation) invitation) Experiences Retrieval for Healthcare Multimedia Processing Oral session 4: Art, Oral session 3: Brave new Topics: Social (ACM MM MIIRH) Performance, and 14:45 - 16:00 Annotation (4 - 18 mins and Cognitive Aspects (3 Sports (4 - 18 mins each) papers - 18 mins each) 16:30-17:00 Coffee each) 16:00 - 16:30 Coffee break First ACM MM Oral session 6: Workshop on Workshop on Workshop on Event- Oral session 5: Action Brave new Topic: New Workshop on Streaming and Multimedia Indexing Personal Data Meets based Media 16:30 - 17:45 and Event Recognition Data and Modalities (3 17:00 - 18:30 Immersive Media Synchronization (4 - and Information Distributed Integration and (4 - 18 mins each) papers - 18 mins each) Experiences 18 mins each) Retrieval for Healthcare Multimedia Processing (ACM MM MIIRH) * 19:30 Reception at FAD(near Plaza Catalunya, 30 mins from conference venue by public transport). Only full conference attendees. 22 23 Program at a Glance: October 24 Thursday
Room 113 Room 114 Room 115 Room 116 Room 118 Keynote presentation 2 (Leonidas Guibas): The Space 9:00-10:00 Between The Images Chair: Nozha Boujemaa 10:00-10:30 Coffee break
10:30-12:30 Multimedia Grand Challenge
12:30 - 14:30 SIGMM Business Meeting (Light lunch provided)
Posters 1 (40) & 14:30-16:00 Demos1 (20) 15:30-16:00 Coffee break
Oral session 7: MM13-14 Security and Open Source exchange Forensics (3 - 16:00 - 18:00 Software meeting 18 mins each) competition (by 16:00-16:55 (16:00-18:15) invitation)
* The banquet is on Thursday (24 Oct) at 19:00 at CCIB.
25 Program at a Glance: October 25 Friday Oct. 21, 2013 Workshops, Tutorials
Room 113 Room 114 Room 115 Room 116 Room 118 09:00–18:30
Technical Achievment Award: 2nd International Workshop on International Workshop on Socially-Aware Multimedia (SAM 2013) Room 207 9:30-10:15 Dick Bulterman Chair: Shih-Fu Chang 09:00–18:30 4th International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams Phd Thesis award: 10:15-10:45 Room 412 Xirong Li 09:00–18:30 10:45-11:15 Coffee break 5th International Workshop on Cooking and Eating Activities Posters2 Room 502 (37) & 11:15-12:45 09:00–18:30 Demos2 Workshop on Geotagging and Its Applications (20) Room 409 09:00–18:30 Multimedia Women Workshop on Event-based Media Integration and Processing Lunch (not provided) Systems 12:45 - 14:30 lunch (by Doctoral Symposium Lunch (by invitation) lunch (by Room 607 invitation) 09:00–13:00 invitation) Tutorial 1 - Foundations and Applications of Semantic Technologies for Multimedia Content Oral session 8: Room 503 Oral session 9: Social Multimodal Doctoral Symposium 1 Speaker: Ansgar Scherp (Uni Mannheim, Germany) 14:30 - 15:45 Dynamics (4 - 18 mins Analysis (4 - 18 (14:30 - 15:30) Tutorial 2 - Next-Generation Multimedia Recommendation Systems each) Room 504 mins each) Speakers: Jialie Shen (SMU Singapore) Doctoral Symposium Shuicheng Yan (NUS) 15:45 - 16:15 Coffee break poster session (15:30 - Xian-Sheng Hua (Microsoft) 16:30) 09:00–13:00 Oral session 10: Oral session 11: Scene Data-driven challenge-based workshop ACM MM 2013 (AVEC 2013) Doctoral Symposium 2 16:15 - 17:30 Similarity Search (4 Understanding (4 - 18 mins Room 507 (16:30 - 17:30) - 18 mins each) each) 09:00–13:00 Workshop on Event-based Media Integration and Processing Room 607
26 27 14:30–16:30 Full-day Workshop SAM 09:00–20:00 3rd International Workshop on Interactive Multimedia on Mobile and Portable Devices (IMMPD’13)… Room 507 2nd International Workshop on Socially-Aware Multimedia 14:30–18:30 (SAM 2013) Tutorial 3- Crowdsourcing for Multimedia Research Room 503 Organizers: Pablo Cesar (CWI, NL) Oct. 21 Speakers: Mohammad Soleymani (Imperial College London) Matthew Cooper (FXPAL) Martha Larson(TU Delft) David A. Shamma (Yahoo!) Tutorial 4 - Massive-Scale Multimedia Semantic Modeling Doug Williams (BT) Room 504 Location: Room 207 Speakers: John R. Smith(IBM Research) Liangliang Cao (IBM Research) 09:00–09:15 Welcome Address Doug Williams, Matthew Cooper, David A. Shamma, Pablo Cesar 09:15–10:00 Keynote Talk Learning How People Use Multimedia Socially Eric Gilbert, Gerogia Tech Session 1: Socially-Aware Multimedia Retrieval Session Chair: Matthew Cooper
10:00–10:15 Are There Cultural Differences in Event Driven Information Propagation Over Social Media? Jianbo Yuan, Quanzeng You and Jiebo Luo 10:15-10:30 Exploiting Socially-Generated Side Information in Dimensionality Reduction Alejandro Marcos Alvarez, Makoto Yamada and Akisato Kimura 10:30-10:45 Socially-aware video recommendation using users’ profiles and crowdsourced annotations Marco Bertini, Alberto Del Bimbo, Andrea Ferracani, Francesco Gelli, Daniele Maddaluno and Daniele Pezzatini 10:45-11:00 Socially Motivated Multimedia Topic Timeline Summarization Mathilde Sahuguet and Benoit Huet 11:00-11:30 Coffee Break
28 29 11:30-13:00 Fireside chat with Lyndon Kennedy Full-day Workshop 09:30–17:30 Emerging Trends in Social Multimedia 13:00–14:30 Lunch Break 4th ACM/IEEE ARTEMIS 2013 International Workshop on Analysis and 14:30-15:30 Fireside chat by Munmun De Choudhury Retrieval of Tracked Events and Motion in Imagery Streams Oct. 21 Oct. 21 Role of Social Media in Tackling Challenges in Mental Health Organizers: Marco Bertini (University of Florence, Italy) Anastasios Doulamis (TU Crete, Greece) Session 2: Social Interaction and Presence Nikolaos Doulamis (Cyprus University of Technology, Cyprus) Session Chair: Doug Williams Jordi Gonzàlez (Universitat Autònoma de Barcelona, Spain) Thomas Moeslund (University of Aalborg, Denmark) 15:30-15:45 Empathic interactions in future media scenarios Location: Room 412 08:50–09:00 Koen Willaert, Martijn Vandenberghe, Mike Matton, Bob De Wit and Peter Welcome by the organizers Versieren Session 1: 15:45-16:00 CoStream@Home: Connected Live Event Experiences Video Features and Scene Analysis Niloo Dezfuli, Sebastian Günther, Mohammadreza Khalilbeigi and Jochen Huber 09:00–09:30 On Improving the Robustness of Variational Optical Flow Mahmoud Mohamed, Germany 16:00-16:15 A QoE Testbed for socially aware video-mediated group communication 09:30–10:00 Hand gesture recognition with depth data Marwin Schmitt, Pablo Cesar, Simon Gunkel and Peter Hughes Fabio Dominio; Mauro Donadeo; Giulio Marin; Pietro Zanuttigh; Guido Maria 16:15-16:30 Connected Media and Presence Cortelazzo, Italy Joke Kort, Harold Nefs, Charlie Gullström and Tjerk de Greef 10:00–10:30 Domain Transfer for Person Re-identification 16:30-17:00 Coffee Break Rya Layne; Timoth Hospedales; Shaogangong, United Kingdom 10:30–11:00 Nobody Likes Mondays: Foreground Detection and Behavioral Patterns Analysis in 17:00-17:45 Keynote Talk Complex Urban Scenes Understanding Social Media Engagement: Have Expectations Exceed Results? Gloria Zen; John Krumm; Nicu Sebe; Eric Horvitz; Ashish Kapoor, Italy Dick C.A. Bulterman, CWI 11:00–11:30 Coffee Break 17:45-18:30 Conclusion Doug Williams, Matthew Cooper, David A. Shamma, Pablo Cesar Session 2 : Retrieval of Multimedia Objects/Events 18:30-20:00 Drinks and Cava 11:30–12:00 A Non-parametric Unsupervised Approach for Content Based Image Retrieval and Clustering Konstantinos Makantasis; Anastasios Doulamis; Nikolaos Doulamis, Greece 12:00–12:30 Warping Trajectories for Video Synchronization Sukrit Shankar; Joan Lasenby; Anil Kokaram, United Kingdom 12:30–14:30 Lunch Break
30 31 Session 3 : Analysis of Visual Events Full-day Workshop 09:00–18:30 14:30–15:00 Abnormal Crowd Behavior Detection and Localization Using Maximum Sub- 5th International Workshop on Multimedia for Cooking and Eating sequence Search Activities (CEA2013) Kai-Wen Cheng; Yie-Tarng Chen; Wen-Hsien Fang, Taiwan Oct. 21 Oct. 21 Organizers: 15:00–15:30 Behavior Recognition from Video based on Human Constrained Descriptor and Adaptable Kiyoharu Aizawa(Univ. of Tokyo, JP) Neural Networks Location: Room 502 Athanasios Voulodimos; Nikolaos Doulamis; Stelios Tsafarakis, Greece 15:30–16:00 Background Modeling Methods for Visual Detection of Maritime Targets Paris Kaimakis; Nicolas Tsapatsoulis, Cyprus Session 1 16:00–16:30 Cross-Domain Traffic Scene Understanding by Motion Model Transfer Xun Xu; Shaogang Gong; Timothy Hospedales, United Kingdom 09:00–10:00 Invited Presentation 16:30 - 16:55 Closing remarks Cooking with Computers, a winning recipe! Amelie Cordier, LIRIS, CNRS, France 10:00–10:10 Welcome and opening remarks
11:00–11:30 Coffee Break
Session 2 Long oral presentations 11:30-12:00 Knives are picked before slices are cut: Recognition through activity sequence analysis Ahmet Iscen, Pinar Duygulu 12:00-12:30 Controlling Saltiness without Salt: Evaluation of Taste Change by Applying and Releasing Cathodal Current Hiromi Nakamura, Homei Miyashita 12:30-13:00 A Regional Food's Features Extraction Algorithm and Its Application Trung Duc Nguyen, Diep Nguyen, Yasushi Kiyoki
13:00–14:40 Lunch Session 3 Short oral presentations 14:40-14:50 Automatic Authoring of a Domestic Cooking Video Based on the Description of Cooking Instructions Yasuhiro Hayashi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase
32 33 Full-day Workshop 09:00–18:30 14:50-15:00 Remote Cognitive Rehabilitation Support System for Menu and Meal Preparation Workshop on Event-based Media Integration and Processing Mutsuo Sano, Kenzaburo Miyawaki, Hiromi Mitsumori, Kimiko Ohtani, Syunichi Yonemura, Michiko Ohde Organizers: Fausto Giunchiglia, University of Trento, Italy Oct. 21 Oct. 21 15:00-15:10 “Interactive Cooking Simulator” – showing food ingredients appearance Sang "Peter" Chin, Johns Hopkins University, US changes in frying pan cooking Giulia Boato, University of Trento, Italy Fumihiro Kato, Shoichi Hasegawa Bogdan Ionescu, University Politehnica of Bucharest, Romania 15:10-15:20 User-adaptive models for recognizing food preparation activities Yiannis Kompatsiaris, Centre for Research and Technology Hellas, Greece Sebastian Stein, Stephen Mckenna Location: Room 607 15:20-15:30 Active Labeling Application Applied to Food-Related Object Recognition Marc Bolaños, Maite Garolera, Petia Radeva 09:00–09:15 Opening Remarks 15:30-15:40 Detecting Start and End Times of Object-Handlings on a Table by Fusion of Fausto Giunchiglia, Sang "Peter" Chin Camera and Load Sensors Ryuta Yasuoka, Atsushi Hashimoto, Takuya Funatomi, Michihiko Minoh Session 1 “Social media and events” 15:40-15:50 Taste and Place: design, HCI, location and food Alan Chamberlain, Chloe Griffiths 09:15–10:00 Towards Smart Social Systems 15:50-16:00 Extraction of ingredient names from recipes by combining linguistic Ramesh Jain, University of California, Irvine, US annotations and CRF selection 10:00-10:45 Classifying Images and Videos by Learning from Web Data Thierry Hamon, Natalia Grabar Jiebo Luo, University of Rochester, US 16:00-16:10 A Product Line Approach to Customized Recipe Generation José H. Canós, Ma Carmen Penadés, Marcos R. S. Borges, Abel Gómez 11:00–11:30 Coffee Break 16:10-16:20 Image-Based Food Volume Estimation Chang Xu, Ye He, Nitin Khanna, Albert Parra, Carol Boushey, Edward Delp 11:30–12:15 Insights from Big Data: Interaction, Design, and Innovation 16:20-17:30 Posters & Coffee Alejandro Jaimes, Yahoo! Research-Barcelona, Spain 12:15-13:00 Understanding Events and Message Popularity in Media-rich Social Networks 17:30-17:40 Award ceremony & Closing Lexing Xie, Australian National University, Australia
13:00–14:30 Lunch Break
Session 2 “Event indexing and summarization”
14:30-15:15 Event-based Summarization for Media Hyperlinking Benoit Huet, EURECOM, France
34 35 Half-day Workshop 09:00–13:00 15:15-16:00 Supervised Learning and Clustering for Event Indexing in Social Media Symeon Papadopoulos, CERTH-ITI, Greece ACM Multimedia Workshop on Geotagging and Its Applications 16:00-16:45 Event Duality: Exploitation of Personal and Social Dimensions for Photo Indexing Workshop Chairs: Liangliang Cao, IBM T. J. Watson Research Center, USA Oct. 21 Oct. 21 Ivan Tankoyeu, University of Trento, Italy Gerald Friedland, International Computer Science Institute, USA, 20:00 Gala dinner Pascal Kelm, Technische Universitaet of Berlin, Germany Location: Room409
09:00–09:05 Welcome and opening remarks
Keynote Session 1
09:05–09:35 Exploring the World Through Photos Bart Thomee, Yahoo! Research Barcelona 09:35–10:05 Vision with a Billion Eyes Jiebo Luo, University of Rochester
Oral Session 1: Geotags and Human Behavior
10:05–10:25 City-View Image Retrieval Leveraging Check-in Data Wen-Yu Lee, Yin-Hsi Kuo, Winston H. Hsu 10:25–10:45 Personalized Intra- and Inter-City Travel Recommendation Using Large-Scale Geotags Toshihiko Yamasaki, Noah Snavely, Andrew Gallagher, Tsuhan Chen 10:45–11:05 Rare is Interesting: Connecting Spatio-Temporal Behavior Patterns with Subjective Image Appeal Gokhan Yildirim, Sabine Süsstrunk 11:05–11:20 Coffee
36 37 Keynote Session 2 10:00–10:25 Challenge introduction Michel Valstar, Bjoern Schuller, Kirsty Smith, Florian Eyben, Bihan Jiang, Sanjay 11:20–11:50 What Happens Where? Bilakhia, Sebastian Schnieder, Roddy Cowie and Maja Pantic
Oct. 21 John R. Smith, IBM T. J. Watson Research Center 10:25–10:50 Diagnosis of Depression by Behavioural Signals: A Multimodal Approach Oct. 21 Nicholas Cummins, Jyoti Joshi, Abhinav Dhall, Vidhyasaharan Sethu, Roland Oral Session 1: Photo Localization Goecke and Julien Epps 10:50–11:15 Depression Recognition based on Dynamic Facial and Vocal Expression 11:50–12:10 Localization of Points of Interest from Georeferenced and Oriented Photographs Features using Partial Least Square Regression Bart Thomee, Yahoo! Research Barcelona Hongying Meng, Di Huang, Heng Wang, Hongyu Yang, Mohammed Al-Shuraifi 12:10–12:30 A Novel Fusion Method for Integrating Multiple Modalities and Knowledge and Yunhong Wang for Multimodal Location Estimation Pascal Kelm, Sebastian Schmiedeke, Jaeyoung Choi, Gerald Friedland, Venkatesan 11:15–11:45 Coffee Nallampatti Ekambaram, Kannan Ramchandran, Thomas Sikora 11:45–12:10 Audiovisual Three-Level Fusion for Continuous Estimation of Russell’s 12:30–13:00 Panel Discussion Emotion Circumplex Enrique Sánchez-Lozano, Paula Lopez-Otero, Laura Docio-Fernandez, Enrique 13:00 Announcing the Best Paper Award Argones-Rúa and José Luis Alba-Castro 12:10–12:35 Vocal Biomarkers of Depression Based on Motor Incoordination Half-day Workshop AVEC 09:00–13:00 James Williamson, Thomas Quatieri, Brian Helfer, Rachelle Horwitz, Bea Yu and Daryush Mehta Data-driven challenge-based workshop ACM MM 2013 12:35–13:00 Challenge result and conclusion (AVEC 2013) Michel Valstar, Bjoern Schuller, Kirsty Smith, Florian Eyben, Bihan Jiang, Sanjay Bilakhia, Sebastian Schnieder, Roddy Cowie and Maja Pantic Workshop Chairs: Björn Schuller, TUM, Germany Michel Valstar, University of Nottingham, UK Roddy Cowie, Queen’s University Belfast, UK Maja Pantic, Imperial College London, UK Jarek Krajewski, University of Wuppertal, Germany Location: Room 507 09:00–10:00 Keynote Specificity of Nonverbal Behavior and Interpersonal Communication to Depression Severity: Beyond Group Differences Jeffrey Cohn
38 39 Half-day Workshop MAED 14:30–18:30 Half-day Workshop IMMPD 14:30–18:20 2nd ACM International Workshop on Multimedia Analysis for Ecological 3rd International Workshop on Interactive Multimedia on Mobile and Data Portable Devices(IMMPD’13)
Oct. 21 (MAED 2013) Oct. 21 Workshop Chairs: Jiebo Luo, University of Rochester, USA Workshop Chair: Concetto Spampinato, University of Catania, Italy Caifeng Shan, Philips Research, The Netherlands Vasileios Mezaris, CERTH, Greece Ling Shao, The University of Sheffield, UK Jacco van Ossenbruggen, CWI, The Netherlands Minoru Etoh, NTT DOCOMO, Japan Location: Room 409 14:30–14:40 Opening Remarks: Ling Shao 14:30–15:15 Keynote 14:40–15:30 Keynote: Insights from Big Data: Interaction, Design, and Innovation Robert Fisher Alejandro Jaimes, Yahoo! Barcelona Session 1: Oral Session: Living organisms and environment monitoring Oral Session 1: 15:15–16:30 Acoustic detection of elephant presence in noisy environments 15:30–15:50 Convex Object Surface Mapping for Wide Field of View Video Representation M. Zeppelzauer, A. S. Stoeger, and C. Breiteneder Dan Mikami, Daisuke Ochi, Ayumi Matsumoto, Akira Kojima Cross-modal alignment for wildlife recognition 15:50–16:10 Improved Binary Feature Matching through Fusion of Hamming Distance T. Dusart, A. Venkat, and M.-F. Moens and Fragile Bit Weight A video processing and data retrieval framework for fish population Dongye Zhuang monitoring 16:10–16:30 Optimized Speech Balloon Placement for Automatic Comics Generation E. Beauxis-Aussalet, S. Palazzo, G. Nadarajan, E. Arslanova, and L. Hardman Wei-Ta Chu, Chia-Hsiang Yu Smart multi-modal marine monitoring via visual analysis and data fusion 16:30–17:00 Coffee Break D. Zhang, E. O'Connnor, K. McGuinness, T. Sullivan, N. O'Connor, and F. Regan Oral Session 2: 16:30–17:00 Coffee 17:00–17:20 A Smart Watch-based Gesture Recognition System for Assisting People with 17:00–17:45 Keynote Visual Impairments Margrit Betke Lorenzo Porzi, Stefano Messelodi, Carla Maria Modena, Elisa Ricci Session 2: Oral Session: Evaluation and applications 17:20–17:40 Sound Preferences of Persons with Hearing Loss Playing an Audio-Based 17:45–18:30 The ImageCLEF plant identification task 2013 Computer Game H. Goeau, A. Joly, P. Bonnet, V. Bakic, J.-F. Molino, D. Barthelemy, and N. Rumi Hiraga, Kjetil Hansen Boujemaa 17:40–18:00 Hand Segmentation for Gesture Recognition in EGO-Vision A case study of trust issues in scientific video collectionsy Giuseppe Serra, Marco Camurri, Lorenzo Baraldi, Michela Benedetti, Rita E. Beauxis-Aussalet, E. Arslanova, L. Hardman, and J. van Cucchiara A mobile platform for biogeography M. Mishima, T. Matsumoto, S. Takano, and O. Matsuda 40 41 18:00–18:20 Energy Efficient Multi-player Smartphone Gaming using 3D Spatial Oct. 22, 2013 Workshops, Tutorials Subdivisioning and PVS Techniques Anand Bhojan, Zeng Qiang 09:00–18:30 4th International Workshop on Human Behavior Understanding (HBU) Room 207 Oct. 21 09:00–18:30 International ACM Workshop on Crowdsourcing for Multimedia (CrowdMM 2013) Room 412 09:00–18:30 First ACM MM Workshop on Multimedia Indexing and Information Retrieval for Healthcare (ACM MM MIIRH) Room 507
09:00–18:30 Oct. 22
Workshop on Personal Data Meets Distributed Multimedia Room 503 09:00–18:30 Workshop on Immersive Media Experiences Room 504 09:00–18:30 Workshop on Event-based Media Integration and Processing Room 607
09:00–13:00 Tutorial 5 - Social Interactions over Geographic-Aware Multimedia Systems Room 502 Speakers: Roger Zimmerman (NUS), Yi Yu (NUS) Tutorial 6 - Multimedia Information Retrieval: Music and Audio Room 409 Speakers: Markus Schedl (Linz, Austria), Emilia Gomez (UPF Barcelona), Masataka Goto (AIST)
42 43 09:00–18:30 14:30–18:30 Full-day Workshop Tutorial 7 - Privacy Concerns of Sharing Multimedia in Social Networks Room 502 4th International Workshop on Human Behavior Understanding Speaker: Gerald Friedland (ICSI) (HBU 2013) Tutorial 8 - Blending the Physical and the Virtual in Musical Technology: from interface design to multimodal signal processing Workshop Chairs: Albert Ali Salah, Boğaziçi Univ., Turkey Room 409 Hayley Hung, Delft Univ. of Technology, The Netherlands Speakers: George Tzanetakis (U Victoria, Canada), Oya Aran, Idiap Research Intitute, Switzerland Sidney Fels (UBC) Hatice Gunes, Queen Mary Univ. of London (QMUL), UK Michael Lyons (Ritsumeikan U, JP) Location: Room 207 Oct. 22
Oct. 22 09:00–09:10 Welcome Creative Applications of Human Behavior Understanding Albert Ali Salah, Hayley Hung, Oya Aran, Hatice Gunes
Interactions in Arts, Creativity, Entertainment, and Edutainment 09:10–10:00 Keynote: Multimodal Systems for Embodied Experience of Music and Audiovisual Content Antonio Camurri (Casa Paganini – InfoMus Research Centre, DIBRIS , University of Genoa) 10:00–10:20 A Behavioral Study on the Effects of Rock Music on Auditory Attention Letizia Marchegiani and Xenofon Fafoutis 10:20–10:40 Human Nonverbal Behaviour Understanding in the Wild for New Media Art Evan Morgan and Hatice Gunes 10:40–11:00 Creative Dance: an Approach for Social Interaction Between Robots and Children Raquel Ros and Yiannis Demiris 11:00–11:30 Coffee & Posters Stylistic features for affect-based movie recommendations Jussi Tarvainen, Stina Westman and Pirkko Oittinen ATTENTO: ATTENTion Observed for Automated Spectator Crowd Monitoring Davide Conigliaro, Francesco Setti, Chiara Bassetti, Roberta Ferrario and Marco Cristani 44 45 11:00–11:30 Coffee & Posters 16:30–17:00 Coffee & Posters Human Behavior Understanding with wide area sensing floors Efficient Graph Construction for Label Propagation based Multi-observation Martino Lombardi, Augusto Pieracci, Paolo Santinelli, Roberto Vezzani and Rita Face Recognition Cucchiara Fadi Dornaika, Alireza Bosgahzadeh and Bogdan Raducanu Real-Time Comprehensive Sociometrics for Two-Person Dialogs Multiple Local Curvature Gabor Binary Patterns for Facial Action Umer Rasheed, Yasir Tahir, Shoko Dauwels, Justin Dauwels, Daniel Thalmann and Recognition Nadia Thalmann Anil Yüce, Nuri Murat Arar and Jean-Philippe Thiran Social and affective signals I A Dense Deformation Field for Facial Expression Analysis in Dynamic Sequences of 3D Scans 11:30–11:50 NovA: Automated Analysis Of Nonverbal Signals In Social Interactions Mohamed Daoudi, Hassen Drira, Boulbaba Ben Amor and Sfefano Berretti Tobias Baur, Ionut Damian, Florian Lingenfelser, Johannes Wagner and Elisabeth Oct. 22
MMLI: Multimodal Multiperson Corpus of Laughter in Interaction Oct. 22 André Radoslaw Niewiadomski, Maurizio Mancini, Tobias Baur, Giovanna Varni, Harry 11:50–12:10 Towards Real-time Continuous Emotion Recognition from Body Movements Weiyi Wang, Valentin Enescu and Hichem Sahli Griffin and Min S.H Aung 12:10–12:30 Head, shoulders and hips behaviors during turning Nesrine Fourati and Catherine Pelachaud Social and affective signals II 12:30–12:50 Social behavior modeling based on Incremental Discrete Hidden Markov Models 17:00–17:20 Human behaviour in HCI: Complex Emotion Detection through Sparse Speech Alaeddine Mihoub, Gérard Bailly and Christian Wolf Features 12:50–14:40 Lunch Ingo Siegert, Kim Hartmann, David Philippou-Hübner and Andreas Wendemuth 17:20–17:40 VIP: A complete framework for computational eye-gaze research Action and activity recognition Keng-Teck Ma, Terence Sim and Mohan Kankanhalli 14:40–15:30 Keynote: Learning to Interact (Naturally) with (All) Users 17:40–18:30 Panel discussion: Challenges in creative applications of human behavior Pushmeet Kohli (Microsoft Research Cambridge) understanding Antonio Camurri, Pushmeet Kohli, Rita Cucchiara, Albert Ali Salah, Hayley Hung, 15:30–15:50 Transfer Learning of Human Poses for Action Recognition Mario F. Rodríguez Martínez, Carlos Medrano, Elias Herrero and Carlos Orrite Oya Aran, Hatice Gunes 15:50–16:10 Dynamic Feature Selection for Online Action Recognition Victoria Bloom, Dimitrios Makris and Vasileios Argyriou 16:10–16:30 A Fully Unsupervised Approach to Activity Discovery Umut Avci and Andrea Passerini
46 47 Full-day Workshop 09:00–18:30 International ACM Workshop on Crowdsourcing for Multimedia 2013 (CrowdMM 2013)
Workshop Chairs: Wei-Ta Chu (National Chung Cheng University, TW) Martha Larson (Delft University of Technology, NL) Kuan-Ta Chen (Academia Sinica, TW)
09:00–09:10 Opening Remarks 09:10–10:00 Keynote Oct. 22
When the Crowd Watches the Crowd: Understanding Impressions in Online Conversational Video Daniel Gatica-Perez, Idiap Research Institute Session 1: Annotation
10:00–11:05 1000 Songs for Emotional Analysis of Music Mohammad Soleymani; Michael N. Caro; Erik Schmidt; Cheng-Ya Sha; Yi-Husan Yang Crowdsourcing for Affective-Interaction in Computer Games Gonçalo Tavares; André Mourão; Joao Magalhaes How Do Users Make a People-Centric Slideshow? Gonçalo Tavares; André Mourão; Joao Magalhaes 11:05–11:30 Coffee
Session 2 : Task Design
11:30–12:10 Crowdsourced Object Segmentation with a Game Amaia Salvador; Axel Carlier; Xavier Giro-I-Nieto; Oge Marques; Vincent Charvillat Divide and Conquer: Atomizing and Parallelizing A Task in A Mobile Crowdsourcing Platform Angel Sappa; Felipe Lumbreras; Ariel Amato; Alicia Fornés; Josep Lladós
49 12:10–13:00 Ideas from Competition Full-day Workshop 09:00–18:30
13:00–15:00 Lunch First ACM MM Workshop on Multimedia Indexing and Information Retrieval for Healthcare Session 3 : Evaluation (ACM MM MIIRH) Workshop Chairs: 15:00–16:10 Assessing Internet Video Quality Using Crowdsourcing Jenny Benois-Pineau, University of Bordeaux 1, France Alexia Briasouli, CERTH -ITI Oscar Figuerola Salas; Velibor Adzic; Akash Shah; Hari Kalva Alex Hauptman, Carnegie-Mellon University, USA Crowdsourcing-based Multimedia Subjective Evaluations: A Case Study on Image Recognizability and Aesthetic Appeal 09:00–10:00 Keynote Judith Redi; Tobias Hossfeld; Pavel Korshunov; Filippo Mazza; Isabel Povoa; Oct. 22
Oct. 22
Image Analysis for Biomedical and Healthcare Applications Christian Keimel L. Shapiro, University of Washington, USA Crowdsourced Evaluation of the Perceived Viewing Quality in User-Generated Video Session 1: Multimedia And Multimodal Pattern Recognition For Healthcare Applications Stefan Wilk; Wolfgang Effelsberg 16:10–16:30 Poster Session 10:00–10:30 Activity detection and recognition of daily living events 16:30–17:00 Coffee K. Avgerinakis , University of Surrrey, UK, A. Briassouli, I. Kompatsiaris, 17:00–18:00 Interactive Panel Discussion CERTH-ITI, Greece 18:00–18:10 Concluding Remarks 10:30–11:00 Modeling Instrumental Activities of Daily Living in Egocentric Vision as Sequences of Active Objects and Context for Alzheimer Disease Research I. González Díaz, V. Buso, J. Benois-Pineau, University of Bordeaux, LaBRI, France, G. Bourmaud, R. Megret, University of Bordeaux, IMS Laboratory, France 11:00–11:30 Coffee
11:30–12:00 Combining Multiple Sensors for Event Recognition of Older People C.F. Crispim-Junior, INRIA – Sophia Antipolis, Q. Ma, Beihang University, China, B. Fosty, R. Romdhane, F. Bremond,M. Thonnat, INRIA – Sophia Antipolis 12:00–12:30 Graph-Based Analysis of Physical Exercise Actions O. Çeliktutan, C. Burak Akgül, Bogazici University, Turkey,C. Wolf, Université de Lyon, France, B. Sankur, Bogazici University, Turkey 12:30–13:00 Fall Detection in Multi-Camera Surveillance Videos: Experimentations and Observations S. Wang, University of Queensland, Zh. Xu, Zhejiang University, Y. Yang, CMU, USA, X. Li, University of Queensland, Ch. Pang, CSIRO, A. Hauptmann, CMU
50 51 13:00–14:30 Lunch Full-day Workshop 09:00–18:30
14:30–15:30 Keynote Workshop on Personal Data Meets Distributed Multimedia Dementia and Dependency: a Major Challenge for the 21st century J.-F. Dartigues, University Hospital of Bordeaux, France Workshop Chairs: Vivek Singh, MIT, USA Session 3 : Multimedia Analysis and Feedback in Medicine Tat-Seng Chua, NUS Ramesh Jain, University of California, Irvine, USA 15:30–16:00 Leveraging Biosignal and Collaborative Filtering for Context-Aware Alex (Sandy) Pentland, MIT, USA Recommendation M. F. Alhamid, M. Rawashdeh , H. Al Osman, A. El Saddik, University of Ottawa, 09:00–10:00 Keynote Canada Oct. 22 Oct. 22
The Power of the Data: Opportunities and Challenges in Big and Personal Data 16:00–16:30 Automatically Recommending Multimedia Content for Use in Group Reminiscence Mining Therapy Nuria Oliver, Telefonica, Spain A. Bermingham, Dublin City University, J. O'Rourke, Adelaide & Meath Hospital Session 1: Technical Talks Tallaght, C. Gurrin, Dublin City University, R. Collins, Adelaide & Meath Hospital Tallaght, K. Irving, A. Smeaton, Dublin City University 10:00–10:20 Situation Fencing: Making Geo-Fencing Personal and Dynamic 16:30–17:00 Coffee Siripen Pongpaichet; Vivek K. Singh; Ramesh Jain; Alex Sandy Pentland 10:20–10:40 Crowds, Bluetooth, and Rock'n'Roll. Understanding Music Festival Participant Behavior 17:00–17:30 A Cognitive Assistive System for Monitoring the Use of Home Medical Devices Jakob Eg Larsen; Piotr Sapiezynski; Arkadiusz Stopczynski; Morten Mørup; Y. Cai, Y., Yang, A. Hauptmann, Carnegie Mellon University, USA Rasmus Theodorsen 17:30–18:00 Clinical Experience Sharing by Similar Case Retrieval 10:40–11:00 Building Health Persona from Personal Data Streams N. Barzegar Marvasti, C. Burak Akgül, N. Kökciyan, S. Üsküdarlı, P. Yolum, Laleh Jalali; Ramesh Jain Bogazici University, R. Turkay, B. Bakir, Istanbul University, B. Acar, Bogazici 11:00–11:30 Coffee University 18:00–18:30 Medical Image Retrieval using Bag of Meaningful Visual Words Session 2: Ignite Talks A.Foncubierta Rodriguez, A. García Seco de Herrera, H. Müller, University of Applied Sciences of Western Switzerland (HES-SO), Switzerland 11:30–11:40 A Mobile Personal Informatics System with Interactive Visualizations of Mobility and Social Interactions Andrea Cuttone; Sune Lehmann; Jakob Eg Larsen 11:40–11:50 An Evaluation of Wearable Activity Monitoring Devices Fangfang Guo;Yu Li; Mohan Kankanhalli; Michael Brown
52 53 11:50–12:00 Combining Crowd-Generated Media and Personal Data: Semi-Supervised Learning for Full-day Workshop 09:00–18:30 Context Recognition Long-Van Nguyen-Dinh; Mirco Rossi; Ulf Blanke; Gerhard Tröster Workshop on Immersive Media Experiences 12:00–12:10 The Influence of Social Norms on Synchronous versus Asynchronous Communication Technologies Workshop Chairs: Teresa Chambel, University of Lisbon, Portugal Abdullah Almaatouq; Fahad Alhasoun; Riccardo Campari; Anas Alfaris V. Michael Bove, MIT Media Lab, USA Sharon Strover, University of Texas at Austin, USAA 12:10–13:20 Panel and Breakout Brainstorming Session Paula Viana, Polytechnic of Porto and INESC TEC, Portugal What’s in it for me? How Can Big Multimedia Aid Quantified-self Applications. Graham Thomas, BBC, UK Panelists: Alan Smeaton; Daniel Gatica-Perez; Hari Sundaram Oct. 22
Oct. 22 13:20–15:00 Lunch 09:00–09:15 Welcome Address
Session 3 : Breakout Brainstorming Session Session 1: Immersion in the Field
15:00–17:00 2 groups brainstorming on how to combine big MM data with quantified-self 09:15–09:35 Immersive Experiences in the Home: a Field Trial on Stereoscopic 3DTV data Jonas De Meulenaere; Koen Willaert; Wendy Van Den Broeck; Lizzy Bleumers Identify one problem, data sources needed, computation tools needed, and research 09:35–09:55 Immersive FPS Games: User Experience and Performance Jean-Luc Lugrin; Marc Cavazza; Fred Charles; Marc Le Renard; Jonathan challenges Freeman; Jane Lessiter 17:00–17:30 Presentations by the two groups 09:55–10:15 Object-Based Audio Applied to Football Broadcasts 17:30–18:00 Discussion and closing Mark Mann; Anthony Churnside; Andrew Bonney; Frank Melchior
Session 2: Participatory and Collaborative Experiences
10:15–10:30 Enhancing Site-Specific Theatre Experience with Remote Partners Akito van Troyer 10:30–10:45 TAG4VD - A Game for Collaborative Video Annotation José Pedro Pinto; Paula Viana 10:45–11:00 Music Recommendations for Groups of Users Pedro Dias; João Magalhaes 11:00–11:30 Coffee Break
54 55 11:30–13:00 Keynote Talk Full-day Workshop 09:00–18:30 Multisensory Mixed Reality with Smell and Taste Adrian Cheok, Prof. of Pervasive Computing, City University London, UK Workshop on Event-based Media Integration and Processing
13:00–14:20 Lunch Organizers: Fausto Giunchiglia, University of Trento, Italy Sang "Peter" Chin, Johns Hopkins University, US Session 3 : Perceptual Immersion Giulia Boato, University of Trento, Italy Bogdan Ionescu, University Politehnica of Bucharest, Romania 14:30–14:50 Simulating the Sensation of Taste for Immersive Experiences Yiannis Kompatsiaris, Centre for Research and Technology Hellas, Greece Nimesha Ranasinghe; Adrian Cheok; Ryohei Nakatsu; Ellen Yi Luen Do Location: Room 607 14:50–15:10 Immersive 360º Mobile Video with an Emotional Perspective João Ramalho; Teresa Chambel Oct. 22 09:00–09:15 Oct. 22 Opening Remarks
15:10–15:30 Synesthetic Enrichment of Mobile Photography Jose San Pedro Session 3 “Event semantics and modeling” Session 4 : Design and Enabling Technologies
09:15–10:00 Events in Multimedia: Theory, Model, and Application 15:30–15:50 Mixed Reality Immersive Design: A study in Interactive Dance Ansgar Scherp, University of Mannheim, Germany João Beira; Rodrigo Carvalho; Sebastian Kox 10:00-10:45 Semantics and modeling of events and contexts 15:50–16:10 Dynamic Adaptive 3D Multi-View Video Streaming over the Internet Opher Etzion, IBM Research Lab Haifa, Israel Cagri Ozcinar; Erhan Ekmekcioglu; Ahmet Kondoz 16:10–16:30 A Practical and Scalable Method for Streaming Omni-Directional Video to 11:00–11:30 Coffee Break Web Users Peter Quax; Jori Liesenborgs; Panagiotis Issaris; Wim Lamotte; Johan Claes 11:30–12:15 Discovering Event Media Semantics using Games with a Hidden Purpose Francesco De Natale, University of Trento, Italy 16:30–17:00 Coffee Break 12:15-13:00 Five Recommendations for Recognizing Video Events by Concept Vocabularies 17:00–18:15 Discussion & Demos - Immersive Media Challenges: Cees G.M. Snoek, University of Amsterdam, Nederlands Where we are, what drives us, what is the future? 13:00–14:30 Lunch Break 18:15–18:30 Wrap Up 14:30–16:00 Panel session, "Future trends in events for media" 13:00–14:30 Closing Remarks Fausto Giunchiglia, Sang "Peter" Chin
56 57 Oct. 23, 2013 Main Conference Day 1
08:45–09:00 Opening (GC) Room 113-115
09:00-10:00 Keynote Presentation 1 (Elisabeth Churchill) …………………………………………………………………………………………………………… ▶ 61 Room 113-115
10:00–11:15 Best Paper Session PL1 ……………………………………………………………………………………………………………………………………………………… ▶ 61 Room 113-115 (Plenary)
11:45-13:00 Oct. 23
Oral Session OS1 Experience……………………………………………………………………………………………………………………………………… ▶ 62 Room 113 Oral Session OS2 Music and Play……………………………………………………………………………………………………………………………… ▶ 62 Room 114 Panel Discussion PA1 Cross-Media Analysis and Mining…………………………………………………………………………… ▶ 63 Room 115 13:00-14:45 Journal of Multimedia Board Meeting (By Invitation) Room 116 TOMCCAP Editorial Meeting (By Invitation) Room 118
59 Keynote Presentation 1 09:00–10:00
Multimedia Framed 14:45-16:00 Dr. Elizabeth F. Churchill (Ebay Research Labs) Oral Session OS3 Annotation……………………………………………………………………………………………………………………………………… ▶ 63 Chair:David A. Shamma Room 113 Location: Room 113-115 Oral Session OS4 Art, Performance and Sports………………………………………………………………………………………………… ▶ 64 Room 114 Brave new Topics BN1 Social and Cognitive Aspects……………………………………………………………………………………… ▶ 64 Room 115
16:30-17:45 Oral Session OS5 Action and Event Recognition……………………………………………………………………………………………… ▶ 65 Room 113 Oral Session OS6 Streaming and Synchronization………………………………………………………………………………………… ▶ 66 Best Paper Candidate Session PL1 10:00-11:15 Oct. 23 Oct. 23 Room 114 …………………………………………………………………………………………… Session Chair: Roger Zimmerman (NUS) Brave new Topic BN2 New Data and Modalities ▶ 67 Location: Room 115 Room 113-115 1. Wow! You Are So Beautiful Today! Luoqi Liu, Hui Xu, Junliang Xing, Si Liu, Xi Zhou and Shuicheng Yan 19:30 2. GIANT: Geo-Informative Attributes for locatioN recogniTion and exploration Reception Quan Fang, Jitao Sang and Changsheng Xu FAD (near Plaza Catalunya) 3. Online Human Gesture Recognition from Motion Data Streams Xin Zhao, Xue Li, Chaoyi Pang, Xiaofeng Zhu and Michael Sheng 4. Attributes-augmented Semantic Hierarchy for Image Retrieval Hanwang Zhang, Zheng-Jun Zha, Yang Yang, Shuicheng Yan, Yue Gao and Tat-Seng Chua
60 61 Oral Session OS1 11:45-13:00 Panel Discussion PA1 11:45-13:00 Experience Location: Room 115 Session Chair: Lyndon Kennedy (Yahoo! Research) Location: Room 113 Cross-Media Analysis and Mining
1. Robust Evaluation for Quality of Experience in Crowdsourcing Mark Zhang, Alberto del Bimbo, Selcuk Candan, Alexander Hauptmann, Ramesh Jain, Qianqian Xu, Jiechao Xiong, Qingming Huang and Yuan Yao Alexis Joly, Yueting Zhuang 2. Size Does Matter: How Does Image Display Size Affect Aesthetic Perception? Wei-Ta Chu, Yu-Kuang Chen and Kuan-Ta Chen 3. Non-Reference Audio Quality Assessment for Online Live Music Recordings Zhonghua Li, Ju-Chiang Wang, Jingli Cai, Zhiyan Duan, Hsin-Min Wang and Ye Wang 4. Enabling Low Bitrate Mobile Visual Recognition - A Performance versus Bandwidth Evaluation Yu-Chuan Su, Tzu-Hsuan Chiu, Yan-Ying Chen, Chun-Yen Yeh and Winston H. Hsu Oral Session OS3 14:45-16:00 Oct. 23 Oct. 23
Oral Session OS2 11:45-13:00 Annotation Music and Play Session Chair: Alan Smeaton (Dublin City University) Session Chair: Cynthia Liem (TU Delft) Location: Room 113 Location: Room 114 1. Towards Efficient Sparse Coding for Scalable Image Annotation 1. Competitive affective gaming: Winning with a smile Junshi Huang, Hairong Liu, Jialie Shen and Shuicheng Yan André Mourão and João Magalhães 2. Learning with Limited and Noisy Tagging 2. Tracking-based interaction for object creation in mobile augmented reality Yingming Li, Zhongang Qi, Zhongfei Zhang and Ming Yang Wolfgang Huerst and Joris Dekker 3. Picture Tags and World Knowledge: Learning Tags and Tag Relations from Visual Semantic 3. Physical Modelling and Supervised Training of a Virtual String Quartet Sources Graham Percival, Nicholas Bailey and George Tzanetakis Lexing Xie and Xuming He 4. Using Quadratic Programming to Estimate Musical Attention from Self-Similarity Matrices 4. Annotate for Free: Video Tagging by Mining User Search Behavior Jordan B. L. Smith and Elaine Chew Ting Yao, Tao Mei, Chong-Wah Ngo and Shipeng Li
62 63 Oral Session OS4 14:45-16:00 Oral Session OS5 16:30-17:45 Art, Performance, and Sports Action and Event Recognition Session Chair: Jochen Huber (SUTD & MIT Media Lab) Location: Room 114 Session Chair: Winston Hsu (National Taiwan University) Location: Room 113 1. One-Man-Band: A Touch Screen Interface for Producing Live Multi-Camera Sports Broadcasts 1. Learning Latent Spatio-Temporal Compositional Model for Human Action Recognition Peter Carr, Patrick Lucey, Iain Matthews, Eric Foote and Yaser Sheikh Xiaodan Liang, Liang Lin and Liangliang Cao 2. Tele Echo Tube: beyond Cultural and Imaginable Boundaries 2. Exploring Discriminative Pose Sub-Patterns for Effective Action Classification Hiroki Kobayashi, Michitaka Hirose, Kaoru Saito and Akio Fujiwara Xu Zhao, Yuncai Liu and Yun Fu 3. Heritage of Shadow Puppetry: Creation and Manipulation 3. Human Activities Recognition using Depth Images Min Lin, Zhenzhen Hu, Si Liu, Richang Hong, Meng Wang and Shuicheng Yan Raj Gupta, Alex Yong-Sang Chia, Deepu Rajan, Ee Sin Ng and Eng How Lung 4. Hybrid Robotic/Virtual Pan-Tilt-Zoom Cameras for Autonomous Event Recording 4. We Are Not Equally Negative: Fine-grained Labeling for Multimedia Event Detection Peter Carr, Mike Mistry and Iain Matthews Zhigang Ma, Yi Yang, Zhongwen Xu, Nicu Sebe and Alex Hauptmann Oct. 23
Oct. 23 Brave New Topics BNI 14:45-16:00 Social and Cognitive Aspects
Session Chair: Jiebo Luo (University of Rochester) Shuicheng Yan (NUS) Location: Room 115
1. Social Life Networks: A Multimedia Problem? Amarnath Gupta; Ramesh Jain 2. Unveiling the Multimedia Unconscious: Implicit Cognitive Processes and Multimedia Content Analysis Marco Cristani; Alessandro Vinciarelli; Cristina Segalin; Alessandro Perina 3. Large-scale Visual Sentiment Ontology and Detectors Using Adjective Noun Pairs Damian Borth; Rongrong Ji; Thomas Breuel; Shih-Fu Chang
64 65 Oral Session OS6 16:30-17:45 Brave New Topics BN2 16:30-17:45 Streaming and Synchronization New Data and Modalities
Session Chair: Pablo Caesar (CWI) Session Chair: Jiebo Luo (University of Rochester) Location: Room 114 Shuicheng Yan (NUS) Location: Room 115 1. Unifying Request and Service Scheduling for P2P Non-linear Media Access Systems Zhen Wei Zhao and Wei Tsang Ooi 1. Towards Building a Sketch-based Image Search Engine on a Billion-Level Database 2. FlashStream: A multi-tiered storage architecture for HTTP video streaming incorporating Xinghai Sun; Changhu Wang; Chao Xu; Lei Zhang Flash Memory SSDs 2. Clickage: Towards Bridging Semantic and Intent Gaps via Mining Click Logs of Search Engines Moonkyung Ryu and Umakishore Ramachandran Xian-Sheng Hua; Linjun Yang; Jingdong Wang; Jing Wang; 3. Early Event-Driven (EED) RTCP Feedback for Rapid IDMS Ming Ye; Kuansan Wang; Yong Rui; Jin Li Mario Montagud, Fernando Boronat and Hans Stokking 3. Latent Feature Learning in Social Media Network 4. Orchestration: TV-Like Mixing Grammars applied to Video-Communication for Social Zhaoquan Yuan; Jitao Sang; Yan Liu; Changsheng Xu Groups Marian Ursu, Martin Groen, Manolis Falelakis, Michael Frantzis, Vilmos Zsombori and Rene Kaiser Oct. 23 Oct.23
66 67 Oct. 24, 2013 Main Conference Day 2
09:00-10:00 Keynote Presentation 2 (Leonidas Guibas) ………………………………………………………………………………………………………………… ▶ 71 Room 113-115
10:30-12:30 Multimedia Grand Challenge……………………………………………………………………………………………………………………………………………… ▶ 71 Room 113-115
12:30-14:30 SIGMM Business Meeting PL2 Room 113-115
14:30-16:00
Technical Demo Session 1 ……………………………………………………………………………………………………………………………………………………TD1 ▶ 73 Room 116
Poster Session 1 …………………………………………………………………………………………………………………………………………………………………………PS1 ▶ 75 Oct.24
Room116
69 16:00-16:55 Keynote Presentation 2 09:00-10:00 Oral Session OS7 Security and Forensics……………………………………………………………………………………………………………… ▶ 78 The Space Between The Images Room 113 Leonidas J. Guibas (Stanford University)
Chair:Nozha Boujemaa Location: Room 113-115 Multimedia Grand Challenge 10:30-12:30 16:00-18:15
……………………………………………………………………………………………………………………………… Session Chair: Open Source Software Competition ▶ 79 Neil O'Hare (Yahoo! Research) Room 114 Yiannis Kompatsiaris(CERTH) Location: Room 113-115
1. Action Recognition using Invariant Features under Unexampled Viewing Condition Litian Sun; Kiyoharu Aizawa 16:00-18:00 2. Activity-Aware Adaptive Compression: A Morphing-Based Frame Synthesis Application MM13-MM14 Exchange Meeting (By Invitation) in 3DTI Room 118 Shannon Chen; Pengye Xia; Klara Nahrstedt 3. Human Action Recognition by Fast Dense Trajectories Zongbo Hao; Qianni Zhang; Ebroul Ezquierdo; Nan Sang 19:00 4. Flickr-tag Prediction using Multi-modal Fusion and Meta Information Tapas Dinner Yu-Chuan Su; Tzu-Hsuan Chiu; Guan-Long Wu; Chun-Yen Yeh; Felix Wu; Winston Hsu CCIB 5. Scalable Training with Approximate Incremental Laplacian Eigenmaps and PCA Eleni Mantziou; Symeon Papadopoulos; Yiannis Kompatsiaris Oct.24
Oct.24 6. Image Search by Graph-based Label Propagation with Image Representation from DNN Yingwei Pan; Ting Yao; Kuiyuan Yang; Houqiang Li; Chong-Wah Ngo; Jingdong Wang; Tao Mei 7. Search-Based Relevance Association with Auxiliary Contextual Cues Chun-Che Wu; Kuan-Yu Chu; Yin-Hsi Kuo; Yan-Ying Chen; Wen-Yu Lee; Winston Hsu
70 71 Technical Demo Session 1 TD1 14:30-16:00
Session Chair: Xavier Anguera (Telefonica) 8. Metadata Enrichment For News Video Retrieval -- A Graph-based Propagation Approach Yi Yang (CMU) Kong-Wah Wan; Wei-Yun Yau; Sujoy Roy Location: Room 116 9. Structured Exploration of Who; What; When; and Where in Heterogenous Multimedia News Sources 1. Real-time Salient Object Detection Brendan Jou; Hongzhi Li; Joseph G. Ellis; Daniel Morozoff-Abegauz; Shih-Fu Chang Mei-Chen Yeh; Chia-Ju Lu; Chih-Fan Hsu 10. Beauty is Here: Evaluating Aesthetics in Videos Using Multimodal Features and Free 2. Kanji Snap - an OCR-based smartphone application for learning Japanese kanji characters Training Data Kiia Korpi; Kiyoharu Aizawa Yanran Wang; Qi Dai; Rui Feng; Yu-Gang Jiang 3. Mobile Video Browsing with the ThumbBrowser 11. Estimating Beauty Ratings of Videos using Supervoxels Marco A. Hudelist; Klaus Schoeffmann; Laszlo Boeszoermenyi Gokhan Yildirim; Appu Shaji; Sabine Süsstrunk 4. Physiognomy Master: A Novel Personality Analysis System Based on Facial Features 12. Towards a Comprehensive Computational Model for Aesthetic Assessment of Videos Che-Hao Hsu; Kai-Lung Hua; Wen-Huang Cheng Subhabrata Bhattacharya 5. LAVES: A Instant Mobile Video Search System Based on Layered Audio-Video Indexing 13. Multi-factor Segmentation for Topic Visualization and Recommendation: the MUST-VIS Wu Liu; Feibin Yang; Yongdong Zhang; Qinghua Huang; Tao Mei System 6. Freesound Technical Demo for ACM Multimedia 2013 Chidansh Bhatt; Andrei Popescu-Belis; Maryam Habibi; Sandy Ingram; Stefano Masneri; et al. Frederic Font; Gerard Roma; Xavier Serra 14. Lecture Video Segmentation by Automatically Analyzing the Synchronized Slides 7. Visualizing Web Mash-ups for In-Situ Vision-Based Mobile AR Applications Xiaoyin Che; Haojin Yang; Christoph Meinel Yu You; Ville-Veikko Mattila 8. repoVizz: a framework for remote storage, browsing, annotation, and exchange of multi- model data. Oscar Mayor; Quim Llimona; Marco Marchini; Panos Papiotis; Esteban Maestre Oct.24
Oct.24 9. Small objects query suggestion in a large web-image collection Pierre Letessier; Nicolas Hervé; Julien Champ; Alexis Joly; Olivier Buisson; Amel Hamzaoui 10. Video2Sentence and Vice Versa Amirhossein Habibian; Cees Snoek 11. A tool for catching back your preferred videos from physical collages Christoph Korinke; Mohamad Rabbath; Dennis Lamken; Susanne Boll
72 73 Poster Session 1 PS1 14:30-16:00 12. Pl@ntNet Mobile App Location: Room 116 Hervé Goëau; Pierre Bonnet, Alexis Joly; Vera Bakic; Julien Barbe; Souheil Selmi; Jennifer Carré; 1. Classifying Tag Relevance with Relevant Positive and Negative Examples Daniel Barthelemy; Nozha Boujemaa; Jean-François Molino; Grégoire Duché; Aurélien Péronnet Xirong Li; Cees Snoek 13. Determining Exposure Values from HDR Histograms for Smartphone Photography 2. Non-Rigid Target Tracking based on 'Flow-Cut' in Pair-Wise Frames with online Benjamin Guthier; Kalun Ho; Stephan Kopf; Wolfgang Effelsberg Hough Forests 14. Semantic Dispatching of Multimedia News with MEWS Tao Zhuo; Yanning Zhang; Peng Zhang; Wei Huang; Hichem Sahli Julien Law-To; Gregory Grefenstette; Rémi Landais 3. Object Coding on the Semantic Graph for Scene Classification 15. Cloud Based Multimedia Analytic Platform Jingjing Chen; Yahong Han; Xiaochun Cao; Qi Tian Peng Wu; Rares Vernica; Qian Lin 4. Beyond bag of words: Image representation in sub-semantic space 16. Adaptable and Personalized Game-based Training Systems for Fall Prevention Chunjie Zhang; Shuhui Wang; Qingming Huang; Chao Liang; Jing Liu; Haojie Li; Qi Tian Sandro Hardy; Stefan Göbel; Ralf Steinmetz 5. Speaking Swiss: Languages and Venues on Foursquare 17. AdVisual: A Visual-based Advertising System Darshan Santani; Daniel Gatica-Perez Chao Dong; Shifeng Chen; Xiaoou Tang 6. What are the distance metrics for local features? 18. Multi-Screen Cloud Social TV: Transforming TV Experience into 21th Century Zhendong Mao; Yongdong Zhang; Qi Tian Yichao Jin; Tian Xie; Yonggang Wen; Haiyong Xie 7. Salient Object Detection in Videos by Optimal Spatio-Temporal Path Discovery 19. "Wow! You Are So Beautiful Today!" Ye Luo; Junsong Yuan Luoqi Liu; Hui Xu; Si Liu; Junliang Xing; Xi Zhou; Shuicheng Yan 8. Multiview Semi-Supervised Ranking for Automatic Image Annotation 20. OSCOR: An Orientation Sensor Data Correction System for Mobile Generated Contents Ali Fakeri-Tabrizi; Massih-Reza Amini; Patrick Gallinari Guanfeng Wang; Beomjoo Seo; Yifang Yin; Roger Zimmermann; Zhijie Shen 9. How Do We Deep-Link? Leveraging User-Contributed Time-Links for Non-Linear Video Access Raynor Vliegendhart; Babak Loni; Martha Larson; Alan Hanjalic Oct.24 1 Nov.
Oct.24
10. Compact bag-of-words visual representation for effective linear classification Xiaodan Zhuang; Shuang Wu; Pradeep Natarajan; Rohit Prasad; Prem Natarajan 11. Large-scale Web Video Shot Ranking Based on Visual Features and Tag Co-occurrence Do Hang Nga; Keiji Yanai 12. Locality Preserving Verification for Image Search Shanmin Pang; Jianru Xue; Nanning Zheng; Qi Tian 13. Undo the codebook bias by linear transformation for visual applications Chunjie Zhang; Shuhui Wang; Qingming Huang; Chao Liang; Jing Liu; Qi Tian 74 75 14. Score-Informed Audio Decomposition and Applications 27. Spatio-Temporal Fisher Vector Coding for Surveillance Event Detection Jonathan Driedger; Harald Grohganz; Thomas Praetzlich; Sebastian Ewert; Meinard Mueller Qiang Chen; Yang Cai; Lisa Brown; Ankur Datta; Quanfu Fan; Rogerio Feris; Shuicheng 15. Background Subtraction via Coherent Trajectory Decomposition Yan; Alex Hauptmann; Sharathchandra Pankanti Zhixiang Ren; Liang-Tien Chia; Deepu Rajan 28. Efficient Image and Tag Co-Ranking: A Bregman Divergence Optimization Method 16. Motion Matters: A Novel Framework for Compressing Surveillance Videos Lin Wu; Yang Wang Xiaojie Guo; Siyuan Li; Xiaochun Cao 29. Real-Time Privacy-Preserving Moving Object Detection in the Cloud 17. Spatialized Audio Multiparty Teleconferencing with Commodity Miniature Microphone Array Kuan-Yu Chu; Yin-Hsi Kuo; Winston H. Hsu Viet Anh Nguyen; Shengkui Zhao; Tien Dung Vu; Douglas L. Jones; Minh N. Do 30. With One Look: Robust Face Recognition Using Single Sample Per Person 18. Learning Articulated Body Models for People Re-identification De-An Huang; Yu-Chiang Frank Wang Davide Baltieri; Roberto Vezzani; Rita Cucchiara 31. Weakly-supervised Multi-class Object Detection Using Multi-type 3D Features 19. Facial Landmark Localization based on Hierarchical Pose Regression with Cascaded Asako Kanezaki; Tatsuya Harada; Yasuo Kuniyoshi Random Fens 32. Querying for Video Events by Semantic Signatures from Few Examples Zhanpeng Zhang; Wei Zhang; Jianzhuang Liu; Xiaoou Tang Masoud Mazloom; Amirhossein Habibian; Cees Snoek 20. Image context discovery from socially curated contents 33. Towards Cover Group Thumbnailing Akisato Kimura; Katsuhiko Ishiguro; Alejandro Marcos Alvarez; Kaori Kataoka; Kazuhiko Peter Grosche; Meinard Müller; Joan Serrà Murasaki; Makoto Yamada 34. Multi-feature Canonical Correlation Analysis for Face Photo-Sketch Image Retrieval 21. Moment Feature Based Forensic Detection of Resampled Digital Images Dihong Gong; Zhifeng Li; Jianzhuang Liu; Yu Qiao Lu Li; Jianru Xue; Zhiqiang Tian; Nanning Zheng 35. Hand and Foot Gesture Interaction for Handheld Devices 22. Towards Precise POI Localization with Social Media Zhihan Lv; Shafiq Ur Réhman; Muhammad Sikandar Lal Khan Adrian Popescu; Aymen Shabou 36. AirTouch Panel: A Re-Anchorable Virtual Touch Panel 23. Sim-Min-Hash Shih-Yao Lin; Chuen-Kai Shie; Shen-Chi Chen; Yi-Ping Hung Wan-Lei Zhao; Hervé Jégou; Guillaume Gravier 37. Creation of Individual Photo Selections: Read Preferences from the Users' Eyes Nov. 1 Nov. Oct.24 Oct.24
24. Recognizing the Royals -Leveraging Computerized Face Recognition for Identifying Tina Walber; Chantal Neuhaus; Ansgar Scherp; Steffen Staab; Ramesh Jain Subjects in Ancient Artworks 38. Strong Geometrical Consistency in Large Scale Partial-duplicate Image Search Ramya Srinivasan; Amit Roy-Chowdhury; Conrad Rudolph; Jeanette Kohl Junqiang Wang; Jinhui Tang 25. CollARt: a Tool for Creating 3D Photo Collages Using Mobile Augmented Reality 39. Segmental Multi-way Local Pooling for Video Recognition Asier Marzo; Oscar Ardaiz Ilseo Kim; Sangmin Oh; Arash Vahdat; Kevin Cannons; A. G. Amitha Perera; Greg Mori 26. A Multigrid Approach for Bandwidth and Display Resolution Aware Streaming of 3D 40. A 3D Tele-Immersion Streaming Approach Using Skeleton-Based Prediction Deformations Karthik Venkatraman; Suraj Raghuraman; Balakrishnan Prabhakaran; Xiaohu Guo; Zhanyu Wang Yuan Tian; Yin Yang; Xiaohu Guo; Balakrishnan Prabhakaran 41. Consistent Stereo Image Editing 76 Tao Yan; Shengfeng He; Rynson Lau; Yun Xu 77 Oral Session OS7 16:00-16:55 Open Source Software 16:00-18:15 Security and Forensics Session Chair: Marco Bertini (Univ. of Florence)
Session Chair: Rita Cucchiara (UNIMORE) Location: Room 114 Location: Room 113 1. Waisda? Video Labeling Game 1. Facilitating Fashion Camouflage Art Michiel Hildebrand; Maarten Brinkerink; Riste Gligorov; Martijn Steenbergen Van; Johan Ranran Feng and Balakrishnan Prabhakaran Huijkman; Johan Oomen 2. An Efficient Image Homomorphic Encryption Scheme with Small Ciphertext Expansion 2. GamingAnywhere: An Open-Source Cloud Gaming Testbed Peijia Zheng and Jiwu Huang Chun-Ying Huang; De-Yu Chen; Cheng-Hsin Hsu ; Kuan-Ta Chen 3. Multimedia Content Analysis for Security Applications Using Scientific Workflows Ricky Sethi, Yolanda Gil, Hyunjoon Jo and Andrew Philpot 3. The Social Signal Interpretation (SSI) Framework - Multimodal Signal Processing and Recognition in Real-Time Johannes Wagner; Florian Lingenfelser; Tobias Baur; Ionut Damian; Felix Kistler; Elisabeth Andre 4. Recent Developments in openSMILE, the Munich Open-Source Multimedia Feature Extractor Florian Eyben; Felix Weninger; Florian Groß; Björn Schuller 5. ImproveMyCity - An open source platform for direct citizen-government communication Ioannis Tsampoulatidis; Dimitrios Ververidis; Panagiotis Tsarchopoulos; Spiros Nikolopoulos; Ioannis Kompatsiaris; Nicos Komninos 6. LIRE: Open Source Image Retrieval in Java Mathias Lux 7. Golden Retriever - A Java Based Open Source Image Retrieval Engine Oct.24 Oct.24 Lazaros Tsochatzidis; Chryssanthi Iakovidou; Savvas Chatzichristofis; Yiannis Boutalis 8. Stage Framework - An HTML5 and CSS3 Framework for Digital Publishing Rami Aamulehto; Mikko Kuhna; Pirkko Oittinen 9. ESSENTIA: an Audio Analysis Library for Music Information Retrieval Dmitry Bogdanov; Nicolas Wack; Emilia Gómez; Sankalp Gulati; Perfecto Herrera; Oscar Mayor; Gerard Roma; Justin Salamon; Jose Zapata; Xavier Serra
78 79 Oct. 25, 2013 Main Conference Day 3 10. SCReen Adjusted Panoramic Effect - SCRAPE Carl Flynn; David Monaghan; Noel E. O Connor 11. Orcc: Multimedia development made easy 09:30-10:15 Hervé Yviquel; Antoine Lorence; Khaled Jerbi; Gildas Cocherel; Alexandre Sanchez; Technical Achievement Award Mickaël Raulet Room 113-115 Dick Boulterman Chair: Shih-Fu Chang
10:15-10:45 PhD Thesis Award Room 113-115 Xirong Li
11:15-12:45
Technical Demo Session 2……………………………………………………………………………………………………………………………………………………TD2 ▶ 83 Room 116 Poster Session 2…………………………………………………………………………………………………………………………………………………………………………PS2 ▶ 85 Room 116
12:45-14:30
Oct.24 Doctoral Symposium Lunch (By Invitation) Room 113-115 Multimedia Systems Lunch (By Invitation) Room 118 Women Lunch (By Invitation) Room 116 Oct.25
80 81 Technical Demo Session 2 TD2 11:15-12:45 14:30-15:45 Session Chair: Xavier Anguera (Telefonica) ………………………………………………………………………………………………………… Oral Session: OS8 Multimodal Analysis ▶ 88 Yi Yang (CMU) Room 113 Location: Room 116 Oral Session: OS8 Social Dynamics…………………………………………………………………………………………………………………… ▶ 88 Room 114 1. OTMedia: The French TransMedia News Observatory Nicolas Hervé; Marie-Luce Viaud; Jérôme Thièvre; Agnès Saulnier; Pierre Letessier; Julien Champ; Olivier Buisson; Alexis Joly 14:30-15:30 2. TEEVE Endpoint: Towards the Ease of 3D Tele-Immersive Application Development
Doctoral Symposium ………………………………………………………………………………………………………………………………………………………………DS1 ▶ 90 Pengye Xia; Klara Nahrstedt Room 115 3. eHeritage of Shadow Puppetry: Creation and Manipulation Zhenzhen Hu; Min Lin; Si Liu; Meng Wang; Richang Hong; Shuicheng Yan 4. Gesture-based control of physical modeling sound synthesis: a mapping-by-demonstration 15:30-16:30 approach Doctoral Symposium Poster Session ……………………………………………………………………………………………………………………………… ▶ 91 Jules Françoise; Norbert Schnell; Frederic Bevilacqua Room 115 5. News Rover: Exploring Topical Structures and Serendipity in Heterogeneous Multimedia News 16:15-17:30 Brendan Jou; Hongzhi Li; Joseph G. Ellis; Dan Morozoff; Shih-Fu Chang 6. A novel framework for collaborative video recommendation, interest discovery and Oral Session: OS10 Similarity Search………………………………………………………… ▶ 89 Room 113 friendship suggestion based on semantic profiling Oral Session: OS11 Scene Understanding………………………………………………………………………………………………………… ▶ 89 Marco Bertini; Alberto Del Bimbo; Andrea Ferracani; Francesco Gelli; Daniele Maddaluno; Daniele Pezzatini 7. euTV: a system for media monitoring and publishing 16:30-17:30 Marco Bertini; Alberto Del Bimbo; George Ioannidis; Emile Bijk; Isabel Trancoso; Hugo Meinedo 8. CAMMA: Contextual Advertising system for Multimodal News Aggregations Doctoral Symposium ………………………………………………………………………………………………………………………………………………………………DS2 ▶ 93 Giuliano Armano; Alessandro Giuliani; Alberto Messina; Maurizio Montagnuolo Room 115 9. Flarty: recommending art routes using check-ins latent topics Andrea Ferracani; Alberto Del Bimbo; Daniele Pezzatini Oct.25
Oct.25
82 83 Poster Session 2 PS2 11:15-12:45
10. SentiBank: Large-Scale Ontology and Classifiers for Detecting Sentiment and Emotions in Visual Content Damian Borth; Tao Chen; Rong-Rong Ji; Shih-Fu Chang Location: Room 116 11. Augmented and Interactive Video Playback Based On Global Camera Pose 1. Efficient Video Quality Assessment Based on Spacetime Texture Representation Junsheng Fu; Lixin Fan; Yu You Peng Peng; Kevin Cannons; Ze-Nian Li 12. EigenNews: A Personalized News Video Delivery Platform 2. Fitted Spectral Hashing Matt Yu; Peter Vajda; David Chen; Sam Tsai; Maryam Daneshi; Andre Araujo; Yu Wang; Sheng Tang; Yalin Zhang; Jintao Li Huizhong Chen; Bernd Girod 3. Using Emotional Context from Article for Contextual Music Recommendation 13. NovaEmötions: Winning with a smile Chih-Ming Chen; Jen-Yu Liu; Yi-Hsuan Yang; Ming-Feng Tsai André Mourão; Joao Magalhaes 4. Revisiting the VLAD image representation 14. Tell Me What Happened Here in History Jonathan Delhumeau; Philippe-Henri Gosselin; Hervé Jégou; Patrick Pérez Jia Chen; Qin Jin; Weipeng Zhang; Shenghua Bao; Zhong Su; Yong Yu 5. Human Behavior Sensing for Tag Relevance Assessment 15. Group TV: A Cloud based Social TV for Group Social Experience Mohammad Soleymani; Sebastian Kaltwang; Maja Pantic Xiaoyan Wang; Lifeng Sun; Shou Wang 6. Robust Facial Expressions Recognition Using 3D Average Face and Ameliorated AdaBoost 16. GeSoDeck: A Geo-Social Event Detection and Tracking System Jinhui Chen; Yasuo Ariki; Tetsuya Takiguchi Xingyu Gao 7. Visual Business Recognition - A Multimodal Approach 17. Stereotime: A Wireless 2D and 3D Switchable Video Communication System Amir Roshan Zamir; Afshin Dehghan You Yang; Qiong Liu; Yue Gao; Binbin Xiong; Li Yu; Huanbo Luan, Rongrong Ji; Qi Tian 8. 3D view synthesis with inter-view consistency 18. MagicBrush: Image Search by Color Sketch David Wolinski; Olivier Le Meur; Josselin Gautier Xinghai Sun; Changhu Wang; Avneesh Sud; Chao Xu; Lei Zhang 9. Improving event detection using related videos and Relevance Degree Support Vector 19. Jiku Director: An Online Mobile Video Mashup System Machine Duong-Trung-Dung Nguyen; Mukesh Saini; Vu-Thanh Nguyen; Wei Tsang Ooi Christos Tzelepis; Nikolaos Gkalelis; Vasileios Mezaris; Ioannis Kompatsiaris 20. WeCard: A Multimodal Solution for Making Personalized Electronic Greeting Cards 10. Superpixel Segmentation based Structural Scene Recognition Huijie Lin; Jia Jia; Hanyu Liao; Lianhong Cai Shuhui Bu; Zhenbao Liu; Kun Zhou 11. Evaluation of salient point methods Song Wu; Michael Lew Oct.25
Oct.25
84 85 12. Cross-media Topic Mining on Wikipedia 23. Swarm Vision Xikui Wang; Yang Liu; Donghui Wang; Fei Wu Danny Bazo; George Legrady; Marco Pinter 13. GLocal Structural Feature Selection with Sparsity for Multimedia Data Understanding 24. Segmenting music through the joint estimation of keys, chords and structural boundaries Yan Yan; Zhongwen Xu; Gaowen Liu; Zhigang Ma;Nicu Sebe Johan Pauwels; Geoffroy Peeters 14. Error Recovered Hierarchical Classification 25. 3D Teleimmersive Activity Classification Based on Application-System Metadata Shiai Zhu; Xiao-Yong Wei; Chong-Wah Ngo Aadhar Jain; Ahsan Arefin; Raoul Rivas; Chien-Nan Chen; Klara Nahrstedt 15. Time Matters! Capturing Temporal Variation in Video using Fisher Kernels 26. Object Co-segmentation Via Discriminative Low Rank Matrix Recovery Ionut Mironica; Jasper Uijlings; Negar Rostamzadeh; Bogdan Ionescu; Nicu Sebe Yong Li; Jing Liu; Zechao Li; Yang Liu; Hanqing Lu 16. A multimodal probabilistic model for gesture-based control of sound synthesis 27. piLDA: Document clustering with selective structural constraints Jules Françoise; Norbert Schnell; Frederic Bevilacqua Siliang Tang; Hanqi Wang; Fei Wu; Ming Chen; Yueting Zhuang 17. Modeling Local Descriptors with Multivariate Gaussians for Object and Scene Recognition 28. Con-Text: Text Detection Using Background Connectivity for Fine-Grained Object Giuseppe Serra; Costantino Grana; Marco Manfredi; Rita Cucchiara Classification 18. Anchor Concept Graph Distance for Web Image Re-ranking Sezer Karaoglu; Jan van Gemert; Theo Gevers Shi Qiu; Xiaogang Wang; Xiaoou Tang 29. Relative Spatial Features for Image Memorability 19. Violence Detection in Hollywood Movies by the Fusion of Visual and Mid-level Audio Cues Jongpil Kim; Sejong Yoon; Vladimir Pavlovic Esra Acar; Frank Hopfgartner; Sahin Albayrak 30. Automatic Egyptian Hieroglyph Recognition by Retrieving Images as Texts 20. Fast Image/Video Collection Summarization with Local Clustering Morris Franken; Jan van Gemert Shuhei Tarashima; Go Irie; Ken Tsutsuguchi; Hiroyuki Arai; Yukinobu Taniguchi 31. Query-Dependent Visual Dictionary Adaptation for Image Reranking 21. Spot the Differences: From a Photograph Burst to the Single Best Picture Jialong Wang; Cheng Deng; Wei Liu; Rongrong Ji Emrah Tasli; Jan Van Gemerts; Theo Gevers 32. Correlated-Spaces Regression for learning continuous emotion dimensions 22. Semantic Pooling for Complex Event Detection Mihalis A. Nicolaou; Stefanos Zafeiriou; Maja Pantic Qian Yu; Jingen Liu 33. RealSense: Directional Interaction for Proximate Mobile Sharing Using Built-in Orientation Sensors Chien Peng Lin; Cheng Yao Wang; Hou Ren Chen; Wei Chen Chu; Mike Chen 34. Understanding and Classifying Image Tweets Tao Chen; Dongyuan Lu; Min-Yen Kan; Peng Cui 35. User Interest and Social Influence Based Emotion Prediction for Individuals Yun Yang; Peng Cui; Wenwu Zhu; Shiqiang Yang Oct.25
Oct.25 36. Bimodal Log-linear Regression for Fusion of Audio and Visual Features Ognjen Rudovic; Stavros Petridis; Maja Pantic 86 87 Oral Session OS8 14:30-15:45 Oral Session OS10 16:15-17:30 Multimodal Analysis Similarity Search Session Chair: Matthew Cooper (FXPAL) Location: Room 113 Session Chair: Yong Rui (Microsoft Research) Location: Room 113 1. Listen, Look, and Gotcha: Instant Video Search with Mobile Phones by Layered Audio-Video Indexing 1. Topology Preserving Hashing for Similarity Search Wu Liu, Tao Mei, Yongdong Zhang, Jintao Li and Shipeng Li Lei Zhang, Yongdong Zhang, Jinhui Tang, Xiaoguang Gu, Jintao Li and Qi Tian 2. Human vs Machine: Establishing a Human Baseline for Multimodal Location Estimation 2. Order preserving hashing for approximate nearest neighbor search Jaeyoung Choi, Venkatesan Ekambaram, Howard Lei, Pascal Kelm, Luke Gottlieb, Thomas Sikora, Jianfeng Wang and Jingdong Wang Kannan Ramchandran and Gerald Friedland 3. Linear Cross-Modal Hashing for Effective Multimedia Search 3. Cross-Media Semantic Representation via Bi-directional Learning to Rank Xiaofeng Zhu, Zi Huang, Heng Tao Shen and Xin Zhao Fei Wu, Xinyan Lu, Zhongfei Zhang, Shuicheng Yan, Yong Rui and Yueting Zhuang 4. Online Multimodal Deep Similarity Learning with Application to Image Retrieval 4. Parallel Field Alignment for Cross Media Retrieval Pengcheng Wu, Steven C.H. Hoi, Hao Xia, Peilin Zhao and Dayong Wang Xiangbo Mao, Binbin Lin, Xiaofei He, Deng Cai and Jian Pei
Oral Session OS11 16:15-17:30 Oral Session OS9 14:30-15:45 Scene Understanding Social Dynamics Session Chair: Dhiraj Joshi (FXPAL) Location: Room 114 Session Chair: Eric Gilbert (Georgia Tech) Location: Room 114 1. Static Saliency vs. Dynamic Saliency: A Comparative Study Tam Nguyen, Mengdi Xu, Guangyu Gao, Mohan Kankanhalli, Qi Tian and Shuicheng Yan 1. Analysis and Forecasting of Trending Topics in Online Media Streams Tim Althoff, Damian Borth, Jörn Hees and Andreas Dengel 2. Building Holistic Descriptors for Scene Recognition: A Multi-objective Genetic Programming Approach 2. Why Not, WINE?: Towards Answering Why-Not Questions in Social Image Search Li Liu, Ling Shao and Xuelong Li Sourav S Bhowmick, Aixin Sun and Ba Quan Truong 3. Scale-based region growing for scene text detection 3. Temporal encoded F-formation System for Improved Social Interaction Detection and Its 3. Junhua Mao, Houqiang Li, Wengang Zhou, Shuicheng Yan and Qi Tian Application Tian Gan, Yongkang Wong, Daqing Zhang and Mohan Kankanhalli 4. Visual Interestingness in Image Sequences
Helmut Grabner, Fabian Nater and Luc Van Gool Oct.25
Oct.25 4. Generating Social Media Snippets for Mobile Browsing Wenyuan Yin, Tao Mei and Chang Wen Chen
88 89 Doctoral Symposium DS1 14:30-15:30 Doctoral Symposiumv Posters Session 15:30-16:30
Session Chair: Marco Cristani (University of Verona) Location: Room 115 Hayley Hung (TU Delft) Location: Room 115 1. Using Tagged Images of Low Visual Ambiguity to Boost the Learning Efficiency of Object Detectors 1. Gesture-Sound Mapping by demonstration in Interactive Music Systems Jules Françoise Elisavet Chatzilari Panel Members: Ye Wang and George Tzanetakis 2. Projective Identity and Procedural Rhetoric in Educational Multimedia: Towards the 2. Context-Aware Gesture Recognition in Classical Music Conducting Enrichment of Programming Self-Concept and Growth Mindsets with Fantasy Role-Play Alvaro Sarasua Michael Scott Panel Members: Ye Wang and George Tzanetakis 3. Recognition of Complex Events in Open-Source Web-Scale Videos: A Bottom up approach 3. Bringing the Sport Stadium Atmosphere to Remote Fans Subhabrata Bhattacharya Pedro Centieiro 4. Motion Compensated Compressed Domain Watermarking Panel Members: Ichiro Ide and Gerald Friedland Tanima Dutta 5. Social Interaction Detection Using A Multi-sensor Approach Tian Gan 6. Virtual Director Technology for Social Video Communication and Live Event Broadcast Production Rene Kaiser 7. Gesture-Sound Mapping by demonstration in Interactive Music Systems Jules Françoise 8. Learning Representations for Affective Video Understanding Esra Acar 9. Context-Aware Gesture Recognition in Classical Music Conducting Alvaro Sarasua 10. Bringing the Sport Stadium Atmosphere to Remote Fans Pedro Centieiro 11. Automatic Melodic and Structural Analysis of Music Material for Enriched Concert Oct.25
Oct.25 Related Experiences Juan J. Bosch 90 91 Doctoral Symposium DS2 16:30-17:30
Session Chair: Marco Cristani (University of Verona) 12. Design, Development and Evaluation of an Adaptive and Standardized RTP/RTCP-based Hayley Hung (TU Delft) IDMS Solution Location: Room 115 Mario Montagud 13. Visual Object Analysis Using Regions and Interest Points 1. Design, Development and Evaluation of an Adaptive and Standardized RTP/RTCP-based Carles Ventura IDMS Solution Mario Montagud Panel Members: Klara Nahrstedt 2. Recognition of Complex Events in Open-Source Web-Scale Videos: A Bottom up approach Subhabrata Bhattacharya Panel Members: Marco Cristani and Arnold Smeulders 3. Social Interaction Detection Using A Multi-sensor Approach Tian Gan Panel Members: Marco Cristani and Hayley Hung Oct.25
Oct.25
92 93 Area Map with Conference Location
95 Area Map with Conference Location Area Map with Conference Location
96 97 Places of Interest
La Rambla and the city center Right in the center of the city, the street called La Rambla is well known for walking around. It is a favorite tourist attraction, with flower sellers, street performers, the beautiful market of La Boqueria , the Liceu Opera house, among many other attractions. From La Rambla you can visit the Barri Gotic and El Raval. The Barri Gotic is the old city of Barcelona which was built on and around the old Roman town of Barcino. This part of the city is an attraction in itself with many churches, plazas, markets and museums. You can see parts of the old Roman walls and below the city history museum – Museu d’Història de la Ciutat – there are remains of Roman houses and streets of Barcino. There are metro stops on both sides of the Gothic Quarter, there are 3 on La Rambla which runs up one side of the area, and on the other is Jaume I.
Sagrada Familia A giant temple, probably Gaudi’s greatest work, and the most visited attraction in Barcelona. Address: Calle Mallorca 401, 08034, Barcelona Metro: Sagrada Familia (Blue Line, L5) and (Purple Line, L2)
Park Guell A magical park with amazing buildings, sculptures, and tile work designed by Gaudi. You will also find Gaudi’s old home in Park Guell which is now open to the public as a small museum. Metro: Lesseps (Green Line, L3). On leaving the metro follow the street signposts for the park.
La Pedrera Another one of Antoni Gaudi’s creations once again hits the top 5 most visited attractions in Barcelona. This building used to be called Casa Mila but nowadays it’s more commonly known as La Pedrera (meaning The Quarry). Gaudi was instrumental in completing this building and his characteristic wavy brick work and colourful tiles are also evident on this masterpiece. Address: La Pedrera, Provenca, 261-265, 08008 Barcelona. Metro: Diagonal (Green Line, L3) and (Blue Line, L5)
98 99