表紙案 A
Web & Smartphone Application Multimedia Art Exhibition 2012 MMapp Eternal / Moment Oct.Web 29– & Smartphone Application Oct. 20–Nov. 4 2012
Venue: Todaiji Culture Center, Small Hall WelcomeWelcome to to ACMMM2012ACMMM2012 in Nara! in Nara! 2kg Deer Satoru Tamura Supported by NEC Display Solutions, Ltd. / ASAHI-SHUZO SAKE BREWING CO.,LTD. All Rights Reserved, Copyright ©2006 You’ve just unlocked SATORU TAMURA Deer Badge! Curator / producer: Tomoe Moriyama (Multimedia Art Program Chair / Museum of We Weoffer offer a smartphone a smartphone/web / Web applicationapplication to to enrich enrich your Contemporary Art Tokyo, JP) experienceyour experience at ACMMM2012 at ACMMM2012 in Nara. in Nara. You Youcan checkin Hideyuki Ando (Multimedia Art Program Chair / Osaka University, JP) to sessionscan checkin / events to sessions/events of the conference of the conference and historic sites in Nara through this application. Participants who 2kg Deer and historic sites in Nara through this application. Satoru Tamura madeParticipants specific who checkins made specific are given checkins special are givenbadges and Optically Coupled Oscillators (OCOs) -- LED Fireflies can specialshare badgestheir experiences and can share withtheir experiences others on withTwitter / Route Checkin Munehisa Sekikawa, Akinori Tsuji, Keiko Kimoto, Ikkyu Aihara, Daisuke Ito, Tetsushi Ueta, Kazuyuki Aihara, Hiroshi Kawakami Facebook.others on This Twitter/Facebook. application also This provides application the also following People who unlocked this badge: Tōdai-ji empathetic heartbeat Hideyuki Ando, Junji Watanebe, Masahiko Sato usefulprovides information: the following useful information: 東大寺 ThinkingGarden © Hideyuki Ando, Junji Watanebe, Masahiko Sato Yoshiaki Mima, Ken-ichi Kimura, Hidekatsu Yanagi OCT • Conference program of ACMMM2012 Todaiji Culture Center New - Conference program of ACMMM2012 30 Empathetic Heartbeat Area map 11:10 Hideyuki Ando, Junji Watanebe, Masahiko Sato • - Area map Things to do in Nara 11:40 Participatory Art Cards & Archive System for Public Exhibition: A Case Study through • - Things to do in Nara 11:40 TOMCCAP Ars Wild Card Editorial Optically Coupled Oscillators (OCOs) -- LED • Information center Lunch Lunch Fireflies - Information center Board Hideaki Ogawa, Emiko Ogawa, Manuela Naveau, Christopher Lindinger, Roland Haring, , is a Buddhist temple complex located in the city of Munehisa Sekikawa, Akinori Tsuji, Keiko Kimoto, Meeting Matthew Gardiner, Martina Mara, Horst Hörtner Ikkyu Aihara, Daisuke Ito, Tetsushi Ueta, • Historic- Historic sites sites 13:10 Nara, Japan. Its Great Buddha Hall ( 大仏殿 Kazuyuki Aiihara, Hiroshi Kawakami 13:10 Daibutsuden), the largest wooden building in the Restaurants, - Restaurants, cafes, cafes, and and barsbars world, houses the world's largest bronze statue of the • MM Art Oral SessionBuddha Vairocana, known in Japanese simply as The Silent Power - Applications of research in medical X-ray combining with Cont.-B.Daibutsu (大仏). The temple also serves as the - Souvenirs Japanese headquarters of the Kegon school of photography and digital graphic design • Souvenirs Image Ret. Buddhism. Shih-Ting Tsai, Ming-Hsiu Mia Chen, Chi-Cheng Chang, Yu-Hung Kuo, Miranda Lawry, Yi-Shu Ting • Free - Free Wi-Fi Wi-Fi hotspots hotspots 14:50 Interactive Art "Maelstrom&Vortex": The Body's Speed – A Race between Digital Japan Media Arts Festival Domestic etc. etc. Traveling Exhibitions 15:20 and Analog Speeds Japan Media Arts Festival Oral Session He-Lin Luo, Yi-Ping Hung We Wehope hope you you will will touch touch the the state-of-art research research Large-Scale Image Ret. andand the the ancient ancient secretsecret of Naraof Nara through through our our Passage+ 17:00 Makoto Shirose, Masahito Hirose, Kentaro Oku, Masato Koide, Naoya Hirai application! application! "Yu bi Yomu": Interactive reading of dynamic text Kazushi Maruya, Miki Uetsuki, Hideyuki Ando, Junji Watanabe The New Dunites Further Information is available on Andres Burbano, Danny Bazo, Sölen K. DiCicco, Angus Forbes Further Information is available on Japan Media Arts Festival Domestic Traveling Exhibitions http://www.acmmm12.org/app/ Japan Media Arts Festival http://www.acmmm12.org/app/ beyond [space art+design] project beyond [space art+design] project beyond [space art+design] beyond [space art+design] 2 3
100 Area Map with Conference Locations
Nara Prefectural Nara Prefectural Todaiji Todaiji Cultural Hall Cultural Hall❶ Culture Center ❶ Culture Center 奈良県文化会館 奈良県文化会館 東大寺文化センター 東大寺文化センター (Keynotes & MMGC Venue) (Keynotes & MMGC Venue) (Art Exhibit Venue) (Art Exhibit Venue) Nara Kintetsu NaraShin-Omiya StationKintetsu Shin-Omiya Station Royal Hotel 近鉄新大宮駅Royal Hotel 近鉄新大宮駅 Nara Prefectural Nara Prefectural Nara Nara Hotel Halftime Hotel Halftime〒 〒 11 11 New Public Hall New Public Hall Kintetsu Nara Station Kintetsu Nara Station Prefectural Prefectural 奈良県新公会堂 奈良県新公会堂 〒 12 〒 12 近鉄奈良駅 近鉄奈良駅Seven- Office Seven- Office (Main Conf. Venue) (Main Conf. Venue) 〒 〒 〒 〒 16❻❾26 ●Eleven 1716〒❻❾26 ●ElevenYume-Kaze17 〒 Plaza Yume-Kaze Plaza (lunch Venue) (lunch Venue) 27 10 18 ❸27 10 18 ❸ 13 13 ❼ ❼ 19 21 19 21 Nara Washington Nara Washington 22 22 Hotel Nikko Nara HotelHotel NikkoPlaza Nara HotelKintetsu Plaza Building Kintetsu Building❹ 20 23 ❹ 20 23 (Banquet Venue) 25 (Banquet Venue) 25 〒 〒 Hotel Hotel JR Nara Station ❺ JR Nara StationFujita ❺ Fujita 241415 241415 JR奈良駅 JR奈良駅 Nara Nara ❷ ❷ 〒 〒 〒 Nara〒 Hotel Nara Hotel ❽ Sun Hotel Nara ❽ Sun Hotel Nara
〒 〒 Comfort Hotel Nara Comfort Hotel Nara 28 28 29 29
Cultural Sites near the venues Free shuttle bus stops Public bus stops (See p.20) ⓴22 Ken Shinkokaido (from the stations) N N ❶ Todaiji Temple（東大寺） (For ACMMM participants only. See p.18) ⓮ JR Nara eki (bus stop #1: for the venues) ⓴23 Ken Shinkokaido (for the stations) ❷ Kasuga TaishaWE Shrine（春日大社） WE❽ JR Nara Station (for/from New Public Hall) ⓯ JR Nara eki (bus stop #11: from the venues) ⓴24 JR Nara eki (bus stop #9: for Kansai InternationalAirport) ❸ Kofukuji Temple（興福寺） ❾ Kintetsu Nara Station (for New Public Hall) ⓰ Kintetsu Nara eki (bus stop #1: for the venues) ⓴25 JR Nara eki (bus stop #10: from Kansai International S S ❹ Nara National Museum（奈良国立博物館） ❿ Kintetsu Nara Station (from New Public Hall) ⓱ Kencho mae (from the stations) Airport) Nara Prefectural Cultural Hall (for JR Nara Station) ⓲ Kencho mae (from the venues) ⓴26 Kintetsu Nara eki (bus stop #20: for Kansai International Cash dispensers (ATM) 500ft ⓫ 500ft Nara Prefectural Cultural Hall (from JR Nara Station Todaiji Daibutsuden Kokuritsuhakubutsukan Airport) ❺ JP Bank (at the 2nd floor of VIERRA Nara) ⓬ ⓳ 200m and New200m Public Hall) (for the stations) ⓴27 Kintetsu Nara eki (from Kansai International Airport) ❻ JP Bank (in Miyatake service station) New Public Hall (for JR and Kintetsu Nara stations) Daibutsuden Kasuga Taisha mae (from the stations) ⓴28 Nara Hotel (for Kansai International Airport) ❼ JP Bank (in Daily-Yamazaki) ⓭ ⓴ 21 Todaiji Daibutsuden (from the stations) ⓴29 Nara Hotel (from Kansai International Airport) ❼〒 Japan Post Offices (JP Bank ATMs inside) ⓴ 4 5 Program at a Glance: October 29
Nara Prefectural Venue Nara Prefectural New Public Hall Cultural Hall Todaiji Culture Center Conf. Room 1 Conf. Room 2 Conf. Rooms 3 & 4 Reception Hall & International Gold Bell Meeting Small Room Noh Theater （1F） （1F） (2F) Foyer (2F) Hall Hall Room A Hall 09:30 10:00 Dynamic Adaptive A Human-Centered Interacting with Streaming over Perspective on Workshop image collections Workshop HTTP Multimedia Data Science CrowdMM SAM T1 T2 T3 Multimedia 13:00 Journal of Multimedia Art Exhibition Lunch Lunch Editorial Board 2012 14:00 Meeting Eternal / Moment Continuous Privacy Concerns (By invitation) (10:00–17:00) Workshop Multimedia Analysis of in Multimedia and Recommendation Workshop （‒14:30） SAM Emotions Their Solutions CrowdMM T4 T5 T6 17:30 17:45 Reception@Nara Prefectural New Public Hall, Garden 20:00
Workshops
Full day SAM International Workshop on Socially-Aware Multimedia Full day CrowdMM International ACM Workshop on Crowdsourcing for Multimedia 2012
Tutorials AM T1 Interacting with Image Collections - Visualisation and Browsing of Image Repositories AM T2 Dynamic Adaptive Streaming over HTTP - From Content Creation to Consumption AM T3 A Human-Centered Perspective on Multimedia Data Science PM T4 Continuous Analysis of Emotions for Multimedia Applications PM T5 Privacy Concerns in Multimedia and Their Solutions PM T6 Multimedia Recommendation 6 7 Program at a Glance: October 30
Nara Prefectural Venue Nara Prefectural New Public Hall Cultural Hall Todaiji Culture Center Conf. Room 1 Conf. Room 2 Conf. Rooms 3 & 4 Reception Hall & International Gold Bell Meeting Small Room Noh Theater （1F） （1F） (2F) Foyer (2F) Hall Hall Room A Hall 09:00 Opening 09:30 Best Paper Candidate Session PL1 11:10 11:40 Core time (11:10 TOMCCAP Lunch –12:40) Lunch Editorial Board Meeting (By invitation) Multimedia 13:10 Art Exhibition Oral Session Oral Session 2012 Oral Session Content-Based Brave New Ideas Video Eternal / Moment Image Retrieval Audio and Music Applications Poster (10:00–17:00) Session 1 OS1 OS2 BNI OS3 PS1 14:50 & 15:20 Technical Panel Demo 1 Oral Session Oral Session Oral Session TD1TD4 Large-Scale Person and PA1 Video Search Face Analysis (Content is dead; Distribution Long Live OS4 OS5 Content!) OS6 17:00 17:45 20th Anniv. Plenary Keynote PL2 18:45 8 9 Program at a Glance: October 31
Nara Prefectural Venue Nara Prefectural New Public Hall Cultural Hall Todaiji Culture Center Conf. Room 1 Conf. Room 2 Reception Hall & Foyer International Gold Bell Meeting Small Room Noh Theater Conf. Rooms 3 & 4 （1F） （1F） (2F) & Meeting Room 2 2F)( Hall Hall Room A Hall 09:00 Technical Achiev. Award PL3 & Ph. D. Thesis Award PL4 10:00 10:20 20th Anniv. Panel PL5 12:20 ACM MM MM12–MM13 Meeting Lunch Lunch Lunch Women’s (By invitation) Core time Luncheon Multimedia (12:50 (12:40–) Art Exhibition 13:50 –14:20) 2012 Eternal / Moment 14:20 (10:00–17:00) Oral Session Open Source Oral Session Oral Session Software Poster Session 2 PS2 Visual Search Human-Centric Competition Presentation and PS2 Media OSSC Organization & OS7 OS8 （‒15:50） OS9 Technical Demo 2 16:00 TD2 16:30 & Oral Session Oral Session Oral Session Video Program Haptics SIGMM VP Event Buisiness Semantic & OS10 Recognition Tagging (–17:45) Meeting Industrial Exhibits OS11 OS12 IE 18:10 18:45 Noh Play 19:45 10 11 Program at a Glance: November 1
Nara Prefectural Venue Nara Prefectural New Public Hall Cultural Hall Todaiji Culture Center Conf. Room 1 Conf. Room 2 Conf. Rooms 3 & 4 Reception Hall & Foyer International Gold Bell Meeting Small Room Noh Theater （1F） （1F） (2F) & Meeting Room 2 2F)( Hall Hall Room A Hall 09:00 Plenary Talk PL6 10:00 Multimedia Grand Challenge Solutions PL7 12:00 12:15 Multimedia Multimedia Core time Systems Art Exhibition Lunch & Lunch Journal Editorial 2012 Doctoral Board Meeting Eternal / Moment Symposium (By invitation) (10:00–17:00) 13:45 Poster Session 14:15 (12:45‒14:15） DSP Oral Session Doctoral Oral Session Symposium Image Analysis Best Paper Session Mobile Systems Poster Session 3 PS3 OS13 DS1 OS14 15:55 & 16:25 Technical Demo 3 Oral Session TD3 Doctoral Oral Session Image Content & Symposium Social Media Analysis Oral Paper Session Industrial Exhibits OS15 DS2 OS16 IE 18:05
19:00 Banquet@Hotel Nikko Nara, Hiten & Hagoromo Ballrooms 21:00 12 13 Program at a Glance: November 2
Nara Prefectural Venue Nara Prefectural New Public Hall Cultural Hall Todaiji Culture Center Conf. Room 1 Conf. Room 2 Conf. Room 3 Conf. Room 4 Reception Hall & International Gold Bell Meeting Small Room Noh Theater （1F） （1F） (2F) (2F) Foyer (2F) Hall Hall Room A Hall 09:00
Workshop Workshop Workshop Workshop Workshop Workshop AMVA CBAMS-EH UXeLATE MIRUM PATCH MAED 12:30 (‒12:45) (‒13:00) Multimedia Lunch Lunch Art Exhibition 2012 13:30 Eternal / Moment Workshop Workshop Workshop Workshop Workshop (10:00–17:00) GeoMM IMMPD MIRUM CEA MAED 17:00
Workshop
Full day MAED 1st ACM International Workshop on Multimedia Analysis for Ecological Data Full day MIRUM 2nd International ACM Workshop on Music Information Retrieval with User-Centered and Multimodal Strategies AM AMVA 1st ACM International Workshop on Audio and Multimedia Methods for Large Scale Video Analysis AM CBMAS-EH 1st ACM Multimedia Workshop on Cloud-Based Multimedia Applications and Services for E-Health AM UXeLATE 1st ACM International Workshop on User Experience in e-Learning and Augmented Technologies in Education AM PATCH Personalized Access to Cultural Heritage: Multimedia by the Crowd, for the Crowd PM GeoMM 1st ACM International Workshop on Geotagging and Its Applications in Multimedia PM IMMPD The 2nd ACM International Workshop on Interactive Multimedia on Mobile and Portable Devices PM CEA The 4th Workshop on Multimedia for Cooking and Eating Activities
14 15 Contents
Web & Smartphone Application …………………………………………………………………………………………………………………………………… ▶ 2 Multimedia Art Exhibition 2012 Eternal / Moment ………………………………………………………………………………………… ▶ 3 Area Map with Conference Locations ………………………………………………………………………………………………………………………… ▶ 4 Program at a Glance ……………………………………………………………………………………………………………………………………………………………… ▶ 6 Bus Guide ……………………………………………………………………………………………………………………………………………………………………………………▶ 18 Twitter Hashtag: #acmmm12 Floor Plans …………………………………………………………………………………………………………………………………………………………………………………▶ 22 Twitter Account: acmmm2012 Lunch Guide ……………………………………………………………………………………………………………………………………………………………………………▶ 25 Message from the General Chairs ………………………………………………………………………………………………………………………………▶ 26 Web Page: http://www.acmmm12.org/ Message from the Technical Program Chairs ………………………………………………………………………………………………………▶ 29 Message from the ACM SIGMM Chair ……………………………………………………………………………………………………………………▶ 32 MM 2012 Conference Organization …………………………………………………………………………………………………………………………▶ 34 Technical Program Area Chairs ……………………………………………………………………………………………………………………………………▶ 37 20th Anniversary Keynote Talk ……………………………………………………………………………………………………………………………………▶ 38 20th Anniversary Panel ……………………………………………………………………………………………………………………………………………………▶ 40 Contents Plenary Talk ………………………………………………………………………………………………………………………………………………………………………………▶ 41 Facebook Page: ACM Multimedia 2012 Industrial Exhibits …………………………………………………………………………………………………………………………………………………………………▶ 42
Oct. 29, 2012 …………………………………………………………………………………………………………………………………………………………………………▶ 43
Oct. 30, 2012 …………………………………………………………………………………………………………………………………………………………………………▶ 56
Oct. 31, 2012 …………………………………………………………………………………………………………………………………………………………………………▶ 70
Nov. 1, 2012 ……………………………………………………………………………………………………………………………………………………………………………▶ 88
Nov. 2, 2012 ……………………………………………………………………………………………………………………………………………………………………… ▶ 107
Places of Interest……………………………………………………………………………………………………………………………………………………………… ▶ 126
16 17 Free Shuttle Bus Schedule The bus with "ACM Multimedia 2012" sign on the windshield is available for free for ACM MM participants. Space on the bus is limited and is available on a first-come, first-served basis. The bus will leave once it is full or at the scheduled departure time. Oct. 29 Oct. 30 Oct. 31 Nov. 1 Nov. 2 Morning Morning Morning Morning Morning No. JR Kintetsu New No. JR Kintetsu New No. JR Kintetsu New No. JR No. JR Kintetsu New of Nara Nara Public of Nara Nara Public of Nara Nara Public of Nara Cultural of Nara Nara Public buses Station Station Hall buses Station Station Hall buses Station Station Hall buses Station Hall buses Station Station Hall 1 8:00 8:10 8:20 2 8:00 8:10 8:20 2 8:00 8:10 8:20 3 8:15 8:25 Banquet 2 8:00 8:10 8:20 1 8:20 8:30 8:40 2 8:20 8:30 8:40 2 8:20 8:30 8:40 3 8:40 8:50 No. From New Public Hall to 1 8:20 8:30 8:40 of banquet venue 1 2 2 3 2 8:40 8:50 9:00 8:40 8:50 9:00 8:40 8:50 9:00 9:05 9:15 buses (Hotel Nikko Nara) 8:40 8:50 9:00 1 9:00 9:10 9:20 2 9:00 9:10 9:20 2 9:00 9:10 9:20 1 9:00 9:10 9:20 10 From 18:10 1 9:20 9:30 9:40 2 9:20 9:30 9:40 2 9:20 9:30 9:40 2 9:20 9:30 9:40 From banquet venue to 1 2 2 No. 1 9:40 9:50 10:00 9:40 9:50 10:00 9:40 9:50 10:00 of Nara Royal Hotel via 9:40 9:50 10:00 Evening Evening Evening buses Kintetsu Shin-omiya Station Evening No. New Kintetsu JR No. of New Cultural No. New Kintetsu JR 1 21:00 No. New Kintetsu JR of Public Nara Nara buses Public Hall Hall of Public Nara Nara of Public Nara Nara buses buses 1 21:30 buses Hall Station Station 2 17:25 17:35 Hall Station Station Hall Station Station No. From banquet venue to 2 17:45 17:55 18:05 No. of Cultural JR 2 18:20 18:30 18:40 of Nara Hotel via 1 16:30 16:40 16:50 1 19:40 19:50 20:00 buses Hall Nara Station 1 19:40 19:50 20:00 buses Kintetsu Nara Station 1 16:50 17:00 17:10 2 20:00 20:10 20:20 2 18:50 19:00 2 20:00 20:10 20:20 1 21:00 1 17:10 17:20 17:30 1 20:20 20:30 20:40 2 19:15 19:25 1 20:20 20:30 20:40 1 21:30 1 17:30 17:40 17:50 JR Nara Station Kintetsu Nara Station Nara Prefectural New Public Hall Nara Prefectural Cultural Hall
Shuttle Bus Stop for Todaiji Hotel Nikko Culture Center New Public Hall Nara 1 (Art Exhibition Nara Prefectural (banquet venue) Venue) 5 Todaiji Cultural Hall Shuttle Bus Stop for Nandaimon Gate JR Nara Staton West Shuttle Bus Stop Entrance Kintetsu Nara Station from Nara Prefectural Shuttle Bus Stop from (under the ground) New Public Hall Yume-Kaze Plaza New Public Hall JR Nara Staton, (Main Conf. Venue) New Public Hall Nara Shuttle Bus Stop for/from East Bus Terminal 2 Prefectural New Public Hall Entrance Kintetsu Shuttle Bus Stop Office Seven-Eleven Building Nara National Museum JR Nara Station 6 18 19 Public Bus To / From the venue To: Todaiji Culture Center (The Art Exhibit Venue) All local buses cost 200 JPY per ride. ・Bus Route #2 (City circular bus outbound line: 市内循環・外回り ) Get off: Daibutsuden Kasuga Taisha maeNara ( 大仏殿春日大社前 Prefectural New Public) Hall From JR Nara Station 春日大社本殿Todaiji 春日大社本殿 JR Nara Station Kintetsu Nara Station ・Bus Route #70 (Kasuga Taisha Honden: Culture Center) or #97 (Kasuga Taisha Honden: Nara Prefectural) Cultural Hall All of the following buses depart from bus stop #1. Get off: Todaiji Daibutsuden ( 東大寺大仏殿(Art) Exhibition Bus Stop #1 Venue) Bus Stop: Hotel Nikko To: Nara Prefectural New Public Hall Bus Stop #1 (for the venues) Todaiji Daibutsuden Nara 1 Bus Stop: (from the stations) Nara prefectural (banquet venue) (for the venues) Todaiji Daibutsuden (Main Conference Venue) 5 From Nara Prefectural New Public Hall or Todaiji Culture Center Cultural Hall Bus Stop for KokuritsuhakubutsukanNara Prefectural NewNara Publicprefectural Hall 市内循 (for the stations) JR Nara Staton ・Bus Route #2 (City circular bus outbound line: West To: Nara Prefectural Cultural Hall New Public Hall EntranceJR Nara Station KintetsuKintetsu Nara Station Nara Station Yume-Kaze Todaiji (Main Conf. Venue) Bus StopNara from Prefectural Cultural Hall 環・外回り ) (under the ground) (Keynotes & MMGC venue) PlazaCulture Center Bus Stop #11 JR Nara Staton, Get off: Daibutsuden Kasuga Taisha mae ( 大仏殿 (Art Exhibition New Public Hall Nara East (from the venues) Bus TerminalBus Stop #1 ・Bus Route 2#1 (City circular bus inbound line: 市内循 Venue)Bus Stop: Bus Stop: prefectural 春日大社前 HotelEntrance Nikko Kintetsu Todaiji Daibutsuden Office ) Nara Bus Stop #1 (for the venues) 環・内回り ) 1 Nara National Museum BusKen Stop: Shinkokaido Seven-Eleven (for the venues) Building (from the stations)(from the stations) Nara prefectural ・Bus Route #70 (Kasuga Taisha Honden: 春日大社本 (banquet venue) Todaiji Daibutsuden Cultural Hall JR Nara Station 5 Get on: Todaiji Daibutsuden KokuritsuhakubutsukanBus Stop: Daibutsuden Kokuritsuhakubutsukan Nara prefectural Bus Stop for 殿 春日大社本殿 6 Kasuga Taisha mae (for the stations) JR Nara Staton ) or #97 (Kasuga Taisha Honden: ) West ( 東大寺大仏殿・国立博物館 ) New Public Hall Entrance Kintetsu Nara Station (from the stations) Bus Stop:Yume-Kaze Ken Shinkokaido (Main Conf. Venue) Bus Stop from Get off: Ken Shinkokaido ( 県新公会堂 ) (under theGet ground) off: Kencho mae ( 県庁前 ) (for Plazathe stations) Bus Stop #11 JR Nara Staton, To: Todaiji Culture Center (Art Exhibit Venue) New Public Hall Nara East (from the venues) Bus Terminal・Bus Route #70 (Rokujoyama:2 六条山 ) or #97 (Horyuji: Bus Stop: prefectural ・Bus Route #2 (City circular bus outbound line: 市内循環・外回り ) Entrance Kintetsu Ken Shinkokaido Office Seven-Eleven 法隆寺 ) Building Nara National Museum Get off: Daibutsuden Kasuga Taisha mae ( 大仏殿春日大社前 ) (from the stations) JR Nara Station Get on: Todaiji Daibutsuden ( 東大寺大仏殿 ) or Bus Stop: Daibutsuden ・Bus Route #70 (Kasuga Taisha Honden: 春日大社本殿) or #97 (Kasuga Taisha Honden: 春日大社本殿) 6 Ken Shinkokaido ( 県新公会堂 ) Kasuga Taisha mae (from the stations) Bus Stop: Ken Shinkokaido Get off: Todaiji Daibutsuden ( 東大寺大仏殿 ) Get off: Kencho mae ( 県庁前 ) (for the stations) To: Nara PrefecturalCultural Hall (Keynotes & MMGC venue) To: Hotel Nikko Nara (Banquet Venue) ・Bus Route #2 (City circular bus outbound line: 市内循環・外回り ), #70 (Kasuga Taisha Honden: 春日 ・Bus Route #1 (City circular bus inbound line: 市内循環・内回り ) 大社本殿 ), or #97 (Kasuga Taisha Honden: 春日大社本殿 ) Get on: Todaiji Daibutsuden Kokuritsuhakubutsukan ( 東大寺大仏殿・国立博物館 ) Get off: Kencho mae ( 県庁前 ) Get off: JR Nara eki (JR 奈良駅 ) Nara Prefectural・Bus Route New #70 Public (Rokujoyama: Hall 六条山 ) or #97 (Horyuji: 法隆寺 ) From Kintetsu Nara Station Todaiji JR Nara Station Kintetsu Nara Station CultureGet Center on: Todaiji Daibutsuden ( 東大寺大仏殿Nara) or Prefectural Ken Shinkokaido Cultural Hall ( 県新公会堂 ) All of the following buses depart from bus stop #1. (Art ExhibitionGet off: JR Nara eki (JR 奈良駅 ) Bus Stop #1 Venue) Bus Stop: Hotel Nikko To: JR Nara StationTodaiji Daibutsuden To: Nara PrefecturalNara New Public Hall Bus Stop #1 (for the venues) 1 Bus Stop: (for the venues) (from the stations) Nara prefectural (Main Conference(banquet venue) Venue) Todaiji・ Bus Daibutsuden Route #1 (City circular bus inbound line: 市内循環・内回りCultural Hall ) or #55, #56, #57, #59, #61, #62, 5 Kokuritsuhakubutsukan Nara prefectural Bus Stop for 市内 (for #120,the stations) #122, #123, #124 (JR Nara eki：JR 奈良駅 ) JR Nara Staton ・Bus Route #2 (City circularWest bus outbound line: New Public Hall Entrance Kintetsu Nara Station Yume-Kaze (Main Conf. Venue) Bus Stop東大寺大仏殿・国立博物館 from 循環・外回り ) (under the ground) Get on:Plaza Todaiji Daibutsuden Kokuritsuhakubutsukan ( ) Bus Stop #11 JR Nara Staton, Get off: Daibutsuden Kasuga Taisha mae ( 大仏殿春 Get off: JR Nara eki (JR 奈良駅 ) New Public Hall Nara East (from the venues) Bus Terminal 2 Bus Stop: prefectural 日大社前 ) Entrance Kintetsu To: Kintetsu NaraKen Station Shinkokaido Office Seven-Eleven Building Nara National Museum ・Bus Route #70 (Kasuga Taisha Honden: 春日大社本 All of the buses from(from Todaijithe stations) Daibutsuden Kokuritsuhakubutsukan stop at Kintetsu Nara Station. JR Nara Station Bus Stop: Daibutsuden 殿 ) or #97 (Kasuga Taisha Honden: 春日大社本殿 ) 6 KasugaGet Taisha on: maeTodaiji Daibutsuden Kokuritsuhakubutsukan ( 東大寺大仏殿・国立博物館 ) 県新公会堂 (fromGet the stations)off: KintetsuBus Nara Stop: ekiKen (Shinkokaido近鉄奈良駅 ) Get off: Ken Shinkokaido ( ) (for the stations) 20 21 Todaiji Culture Center
International Hall Floor Plan: Nara Prefectural New Public Hall FirstFloor Floor Plan: Nara Prefectural Cultural Hall Basement Floor First Floor International Hall First Floor Garden Garden Entrance Garden Entrance
Restaurant Drawing Room Conf. Room Gold Bell Hall Meeting 1 Room 1 Noh Theater
Meeting Conf. Room Room 2 2 Registration Desk Stage
Coffee Service Lunch Box Entrance Second Floor Meeting Second Floor Coffee Service International Hall Room A
Foyer Coffee Shop Museum Coffee Shop Service
Special Entrance Drawing Room Conf. Room Meeting 3 Room 3 Reception Hall
Meeting Conf. Room Lobby Small Hall Room 4 4 Multimedia Art Exhibition 2012 Eternal / Moment
Entrance 22 23 Todaiji Culture Center Floor Plan: Todaiji Culture Center Lunch Guide First Floor Basement Floor Lunch Vouchers: First Floor Lunch vouchers are included in the conference kit. First Floor Garden - Each voucher can either be Garden Entrance Garden Entrance a) exchanged with a lunch box sold at New Public Hall or Restaurant b) used at restaurants in Yume-Kaze Plaza (http://www.yume-kaze.com/en.php) Drawing during workshops and the main conference (Oct. 29–Nov. 2). Room - Good for the day printed on the voucher (1 voucher / day). Conf. Room Gold Bell Hall Meeting - In Yume-Kaze Plaza, one voucher covers at most 1,500 Yen worth of payment, so you will need to 1 Noh Theater Room 1 pay for the difference if any. Basement Floor - Change will not be given. Meeting Conf. Room Registration Desk Room 2 2 Eating Place: The 2nd floor of New Public Hall (8 tables and 80 seats) is available for eating lunch boxes. Also feel free to eat in the park around the New Public Hall. Eating and drinking in the Noh theater is prohibited, so please refrain from using that area. Coffee Service Lunch Box Entrance Meeting Second Floor Coffee Service Room A Todaiji Culture Center (Art Exhibit Venue) Foyer Coffee Shop Museum Coffee Shop Service Todaiji Nandaimon Gate
Special Entrance Drawing Room Conf. Room Meeting 3 Yume-Kaze Plaza Nara Prefectural New Public Hall Room 3 Reception Hall (Main Conf. Venue)
Meeting Conf. Room Small Hall Room 4 4 Multimedia Art Exhibition 2012 Eternal / Moment Nara National Museum
24 25 Message from the General Chairs The 20th Anniversary Keynote Talk and 20th Anniversary Panel: This year celebrates the 20th Anniversary of ACM Multimedia, which was first initiated by the ACM We are delighted to welcome you to 20th ACM International Conference on Multimedia, ACM SIGMM in 1993. To mark this auspicious occasion, the conference features a 20th Anniversary Multimedia 2012, which is held from October 29th to November 2nd, 2012 in Nara, Japan. Welcome Keynote Talk and a 20th Anniversary Panel. These two events reflect on major milestones and to Japan’s ancient capital, the cradle of Japanese culture and final destination of the Silk Road. achievements in multimedia as well as discuss promising ideas and directions for the future.
Like the Silk Road of ancient times, multimedia today provides a medium allowing the diverse Innovations for this Year’s Conference: exchange of ideas across many fields including signal processing, information retrieval, machine In attempt to continuously improve ACM Multimedia and ensure its vibrant role for the multimedia learning, content analysis, networking, applications, human-centered systems, art and education and community, we have made a number of enhancements for this year’s conference: many more. Because of this confluence, multimedia has become one of the fastest growing and most interesting areas in Computer Science. It is again in 2012 that Nara, Japan is a final destination, this • The Technical Program Committee defined eleven Technical Areas for major focus for this time for sharing ideas in multimedia. year’s conference, including introducing new Technical Areas for Multimedia Activity and Event Understanding and Social Media to reflect their growing interest and promise. ACM Multimedia is the premier conference and worldwide event bringing together multimedia • Technical Short Papers are presented as plenary posters to make them more visible at this year’s experts and practitioners across academia and industry. The central feature of the conference, which conference, which reflects the growing quality of short papers. continues this year as in every year since its inception, is the outstanding Technical Program. This • Plenary sessions bring singular focus to conference activities in the morning sessions each day, year’s conference features both oral and poster presentations covering all aspects of the multimedia and afternoon sessions are held in parallel to allow pursuit of more specialized interests at the field chosen through a highly selective review process. Notably, this year’s conference includes special conference. Technical Program activities recognizing the 20th anniversary of ACM Multimedia. • Workshops and Tutorials are held on separate days from the main conference in order to reduce conflict with the regular Technical Program. In addition to the Technical Program, this year’s conference features a diverse range of activities • Since Workshops are important seeds for the next generation of multimedia, two complementary including Panels, Demonstrations and Tutorials. Additionally, a wide array of Workshops brings focus workshop registrations are provided for invited talks of each workshop to encourage participation of on new topics for investigation. The conference features also special sessions on Brave New Ideas, a notable speakers. Grand Challenge contest and Open Source Software Competition and includes a Doctoral Symposium • The Multimedia Art Exhibition features both invited and selected artists and is open for two weeks for mentoring graduate students. Finally, the conference provides a rich Multimedia Art Exhibition in the satellite venue close to the main conference with good public access, which allows stimulation to stimulate artists and researchers alike to meet and discover the frontiers of multimedia artistic broadly to visitors to Nara. communication! • Following the last year’s precedent, Tutorials are made free for all participants. • Recognizing that students are the lifeblood of our next generation of multimedia thinkers, this year’s Student Travel Grant is greatly expanded.
We hope these innovations make for a special conference this year.
26 27 Message from the Technical Program Chairs We greatly acknowledge those who have contributed to the success of ACM Multimedia 2012. We thank the many paper authors and proposal contributors for the various technical and program We are very pleased to be able to present an exciting technical program at ACM Multimedia 2012 components. We thank the large number of volunteers, including the Organizing Committee members in Nara, Japan. The outcome of the work of the Technical Program Committee (TPC) is of course and Technical Program Committee members who worked very hard to create this year’s outstanding entirely depending on the quantity and quality of submitted papers, which was excellent in 2012. conference. Every aspect of the conference was also aided by local committee members, mainly Following the guidelines of the ACM Multimedia Review Committee, the conference is structured from the Kansai area in Japan, to whom we are very grateful. We thank also ACM staff and Sheridan into 11 Areas, with a two-tier TPC, a double-blind review process, and a target acceptance rate of 20% Printing Company for their constant support. for long papers and 30% for short papers.
Finally, we thank our many supporters from Japan and around the world who generously supported Based on the experience from last year’s ACM Multimedia and the responses to our “Call for Areas” ACM Multimedia 2012. They include FXPAL, Google, HUAWEI, IBM Research, NTT DOCOMO, that we issued to the community, we selected the following Areas for ACM Multimedia 2012: (1) Technicolor, DeNA, HP, KDDI R&D Labs, Microsoft Research, Mitsubishi Electric, OMRON, Media Content Analysis and Processing, (2) Multimedia Activity and Event Understanding, (3) Panasonic, SHARP, YAHOO! LABS, Facebook, foo.log, Fuji Xerox, GREE, IBM Japan, Multimedia Search and Retrieval, (4) Mobile and Location-Based Media, (5) Social Media, (6) NETCOMPASS, Nikon, NTT DATA, TOSHIBA, YAHOO! JAPAN, ARUBA and CTC. Other Multimedia Systems and Middleware, (7) Media Transport and Sharing, (8) Multimedia Security and generous support was kindly provided by JSPS, KDDI Foundation, Nara Visitors Bureau, Springer, Forensics, (9) Multimedia Authoring, Production and Consumption, (10) Multimedia Interaction and Telecommunication Advancement Foundation. Applications, (11) Multimedia Art, Entertainment and Culture. Enjoy ACM Multimedia 2012! The two-tier TPC was staffed in a two stage process: first we invited for each area in between two to four Area Chairs, and together with the Area Chairs we invited for the 11 Areas the TPC members. ACM Multimedia 2012 General Chairs The number of Area Chairs and TPC members per Area was related to the estimated numbers of submissions to the Areas. The response to the Call for Papers in form of long and short papers was Kiyoharu Aizawa Noboru Babaguchi John R. Smith overwhelming. Out of all received papers, 331 and 407 papers went through review process for full The University of Tokyo, Osaka University, Japan IBM T. J. Watson Research Center, Japan United States of America and short paper track, respectively. The distribution to the different Areas was as expected unbalanced, ranging from the most popular Areas 1 and 10 with 78 and 54 long paper submissions, to the least popular Areas 8 and 9 with 11 and 14 long paper submissions, respectively.
Each submission was reviewed by at least three TPC members with very few exceptions. The authors of long papers received the reviews and wrote a rebuttal. The reviewers had an on-line discussion of the submissions, their reviews, and the rebuttal comments from the authors. Based on this on-line process, the Area Chairs wrote a meta-review for each paper before the physical TPC meeting at IBM T. J. Watson Research Center Hawthorn on June 16 and 17.
28 29 ■Submitted Papers ■Accepted Papers ■Acceptance Rate（％） All accepted long papers were shepherded by Area Chairs or TPC members to achieve the highest 120 possible quality for the camera-ready version of the papers. As such, we are now able to present this high quality Technical Program and want to thank all authors, TPC members, and Area Chairs for 100 their dedication and hard work.
80 We hope to see you in Nara!
60 ACM Multimedia 2012 Technical Program Chairs 40 Shin’ichi Satoh Thomas Plagemann Xian-Sheng Hua Rong Yan 20 National Institute of University of Oslo, Microsoft, United States Facebook, United States Informatics, Japan Norway of America of America
Number of Papers and Acceptance Rate 0 LS LS LS LS LS LS LS LS LS LS LS (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) (11) Area and Paper Type (L: Long, S: Short)
On the first day of the TPC meeting, the Area Chairs, Technical Program Chairs, and General Chairs worked in breakout sessions and plenary sessions to select the papers to be accepted – except conflict- of-interest papers that were co-authored by Area Chairs. To seek for the fairness, no submissions were made by the General Chairs and Technical Program Chairs. For the selection process, the papers themselves, (meta-) reviews, on-line discussions and authors’ rebuttal comments were considered. On the second day, the General Chairs and the TP Chairs finalized the technical program. One important part of this task was discussions and decisions for conflict-of-interest papers. The set of accepted papers results in an overall acceptance rate for long paper of 20.2% and for short papers of 31.2%. Finally, the set of 67 accepted long papers were structured into 17 oral sessions, including the Best Paper session. The Best Paper session comprises four papers from four different areas which compete for the Best Paper Award of ACM Multimedia 2012. The quality of these papers and their diversity promises that this session will be one of the highlights at the conference.
30 31 Message from the ACM SIGMM Chair I wish to thank many members of the SIGMM community for the interesting and innovative ideas to ACM Multimedia 2012 is a continuation of an outstanding tradition to present best innovative work celebrate the ACM Multimedia 20th anniversary, but special thanks goes to Malcolm Slaney, Kiyo in the area of multimedia systems, content, applications, and interfaces, taking a very broad view Aizawa, Noboru Babaguchi, John Smith, Rainer Lienhart, Mohan Kankanhalli, Ramesh Jain, Ralf of what is happening in the multimedia area. This year’s ACM Multimedia 2012 is held in Nara, Steinmetz, Lawrence Rowe, Dick Bulterman, and our ACM SIGMM coordinator, Fran Spinola. Japan, October 29–November 2, and it represents a very special occasion, since it marks the 20th anniversary of the ACM International Conference of Multimedia (ACM Multimedia) venue. The first ACM Multimedia conference was presented in Anaheim, California, USA, August 1–6, 1993. Since ACM Multimedia 2012 SIGMM Chair then the ACM Special interest Group in Multimedia (SIGMM) has been a leader in the international Klara Nahrstedt multimedia community, annually sponsoring the worldwide premier event in the field. The ACM Multimedia Conference consistently presents the most original, intriguing and important work in its discipline. During the ACM Multimedia 2012 conference, we celebrate the 20th anniversary of the conference with an exciting program, but especially in this ‘Message from the SIGMM chair’ I want to stress two important events that are specifically designed to look back, reflect and consider new multimedia opportunities:
• The Panel “Coulda, Woulda, Shoulda: 20 Years of Multimedia Opportunities” is moderated by Klara Nahrstedt and Malcolm Slaney, and hosts four distinguished panelists, Lawrence Rowe, Ramesh Jain, Ralf Steinmetz, and Dick Bulterman. These pioneers discuss the exciting opportunities and accomplishments they have witnessed within the multimedia community during their 20 years in the field. They also take note of opportunities missed and express their enthusiasm about those still to come (http://www.acmmm12.org/panel-sessions/). • The Special Issue on the “20th Anniversary of ACM SIGMM Multimedia” appears in the leading multimedia journal, the ACM Transactions on Multimedia Computing, Communications and Applications (TOMMCAP) in 2013, where historical views of multimedia technologies are to be presented together with the impact of past inventions on current and future multimedia technologies. The special issue is led by the Guest Editors, Klara Nahrstedt, Rainer Lienhart and Malcolm Slaney, with extensive support from the TOMCCAP Editor-in-Chief Ralf Steinmetz (http://tomccap.acm. org/TOMCCAP-CFP-2012-v2.pdf).
32 33 MM 2012 Conference Organization
General Chairs: David A. Shamma (Yahoo! Research, US) Noboru Babaguchi (Osaka University, JP) Kiyoharu Aizawa (The University of Tokyo, JP) Technical Demonstration Chairs: John Smith (IBM, US) Qi Tian (University of Texas at San Antonio, US) Hirokazu Kato (Nara Institute of Science & Technology, JP) Technical Program Chairs: Shin’ichi Satoh (National Institute of Informatics, JP) Open Source Software Competition Chairs: Thomas Plagemann (University of Oslo, NO) Daniel Gatica Perez (IDIAP Research Institute, CH) Xian-Sheng Hua (Microsoft, US) Masanori Sano (Japan Broadcasting Corporation, JP) Rong Yan (Facebook, US) Video Program Chairs: Local Arrangements Chairs: Tao Mei (Microsoft Research Asia, CN) Tomio Echigo (Osaka Electro-Communication University, JP) Koichi Shinoda (Tokyo Institute of Technology, JP) Naoko Nitta (Osaka University, JP) Doctoral Symposium Chairs: Twentieth Anniversary Liaison: Chong-Wah Ngo (City University of Hong Kong, HK) Ramesh Jain (University of California at Irvine, US) Keiji Yanai (The University of Electro-Communications, JP) Malcolm Slaney (Yahoo! Research, US) Tutorials Chairs: Panels Chairs: Susanne Boll (University of Oldenburg, DE) Yong Rui (Microsoft Research, CN) Changsheng Xu (Chinese Academy of Sciences, CN) Shih-Fu Chang (Columbia University, US) Workshop Chairs: Brave New Ideas Program Chairs: Jiebo Luo (University of Rochester, US) Alejandro Jaimes (Yahoo! Research, ES) Svetha Venkatesh (Deakin University, AU) Tat-Seng Chua (National University of Singapore, SG) Industrial Liaison: Multimedia Grand Challenge Chairs: Minoru Etoh (NTT Docomo, JP) Marcel Worring (University of Amsterdam, NL) Yoichiro Miyake (Square Enix, JP) Yushi Jing (Google Research, US) Go Irie (Nippon Telegraph & Telephone Corporation, JP) Web & Social Media Chairs: Ichiro Ide (Nagoya University, JP) Multimedia Art Program Chairs: Ikki Ohmukai (National Institute of Informatics, JP) Tomoe Moriyama (Museum of Contemporary Art Tokyo, JP) Duy-Dinh Le (National Institute of Informatics, JP) Hideyuki Ando (Osaka University, JP) Takatsugu Hirayama (Nagoya University, JP) Aisling Kelliher (Arizona State University, US) 34 35 Technical Program Area Chairs
Publicity Chairs: Area Chairs: K. Selcuk Candan (Arizona State University, US) Liangliang Cao (IBM, US) Michael S. Lew (Leiden University, NL) Mark Liao (Academia Sinica, TW) Scott Craver (SUNY Binghamton, US) Yong Man Ro (Korea Advanced Institute of Science & Technology, KR) Gerald Friedland (International Computer Science Institute / University of California at Berkeley, US) Alex Hauptmann (Carnegie Mellon University, US) Steven Hoi (Nanyang Technological University, SG) Finance Chair: Shigeyuki Sakazawa (KDDI R&D Labs, JP) Winston Hsu (National Taiwan University, TW) Gang Hua (Steven's Institute of Technology, US) History Preservation Chairs: Benoit Huet (Eurecom, France) Alberto del Bimbo (University of Firenze, IT) Hirokazu Kato (Nara Institute of Science and Technology, JP) Sethuraman Panchanathan (Arizona State University, US) Yiannis Kompatsiaris (Informatics and Telematics Institute (CERTH-ITI), GR) Baochun Li (University of Toronto, CA) Publication Chairs: Jiebo Luo (University of Rochester, US) Hiroshi Mo (National Institute of Informatics, JP) Tao Mei (Microsoft Research Asia, CN) Chamin Morikawa (The University of Tokyo, JP) Frank Nack (University of Amsterdam, NL) Yuichi Nakamura (Kyoto University, JP) SIGMM Chair: Klara Nahrstedt (University of Illinois at Urbana-Champaign, US) Chong-Wah Ngo (City University of Hong Kong, HK) Ansgar Scherp (University of Koblenz-Landau, DE) SIGMM Director of Conferences: Nicu Sebe (University of Trento, IT) Mohan S. Kankanhalli (National University of Singapore, SG) Doree Seligmann (Avaya, US) David Shamma (Yahoo! Research, US) Local Arrangements Committee: Heng T Shen (The University of Queensland, AU) Hitoshi Habe (Kinki University, JP) Cees Snoek (University of Amsterdam, US) Sei Ikeda (Osaka University, JP) Qi Tian (University of Texas at San Antonio, US) Yoshimichi Ito (Osaka University, JP) Nalini Venkatasubrahanian (University of California at Irvine, US) Norihiko Kawai (Nara Institute of Science and Technology, JP) Kazuaki Kondo (Kyoto University, JP) Zhen Wen (IBM T.J. Watson Research Center, US) Yuta Nakashima (Nara Institute of Science and Technology, JP) Marcel Worring (Universiteit van Amsterdam, NL) Atsushi Nakazawa (Osaka University, JP) Lexing Xie (The Australian National University, AU) Takafumi Taketomi (Nara Institute of Science and Technology, JP) Shuicheng Yan (National University of Singapore, SG) Yuki Uranishi (Osaka University, JP) Wenjun Zeng (University of Missouri, US) ACMMM2012 logo design: Yasuhito Nagahara Lei Zhang (Microsoft Research Asia, CN) "FUROSHIKI" font design: Sagabon Font project 36 37 20th Anniversary Keynote Talk Masahiro Fujita is currently Vice President of System and Software Technology Platform at Sony Corporation, Tokyo, Japan. Future Direction of Digital Content He received a B.A. in Electronics and Communications from Waseda University, Tokyo, in 1981, and an M.S.in Electrical Masahiro Fujita (Sony Corporation, JP) Engineering from University of California Irvine, in 1989.
Abstract: He joined Sony Corporation in 1981, and worked for development of a spread spectrum communication system, which was We review the history and trends of multimedia technologies, especially focusing on audio & video used in a receiver of global positioning system for a car navigation, and for VLBI (Very Long Baseline Interferometetry) for a products. Our lifestyles have been changing according to the developments of these technologies. We earth quake forecast system. From 1988, he became a graduate student of University of California, Irvine, and studied artificial forecast the direction of multimedia technologies and our lifestyles in future. neural networks for visual perception. After he returned to Sony, he started the Robot Entertainment project from 1993, and developed the entertainment robot AIBO, which started to sell in 1999. After the AIBO project, he has been in charge of We can guess that the future direction of audio & video is going to higher and higher fidelity. Display development for cognitive part of a small humanoid robot QRIO. In 1998 he proposed to establish RoboCup four-legged robot devices will be larger and flexible. In addition, wearable devices will be popular as consumer products. league using AIBO as platform, which was one of 4 official physical robot leagues in RoboCup until 2007. It will be achieved by printing manufacture technologies. These devices and high fidelity content will realize immersive super reality. In 2008 he became a president of System Technologies Laboratories, Sony Corporation, where he led incorporating intelligent functions for Sony products and services, such as personalized recommendation, augmented reality (SmartAR), and so on. While we will enjoy the traditional audio & video content with the immersive super reality, we will use more social media by which realtime & global human-human interaction will be realized. We will be able to utilize other people’s knowledge and decisions in realtime using the interactive & immersive super reality.
In addition to the social networks with humans, sensor & actuator networks will also be globally established. This will extend our perception and decision abilities. We will find new problems with the distributed sensor & actuator networks, which we did not find with our ordinary perceptions. Using interactive & immersive super reality, we will collaboratively solve personal daily problems as well as global problems.
Thus, in future we will realize collaborative community with interactive & immersive super reality. In the community we will enjoy entertainment content and will solve many problems collaboratively. This community itself will be the content in the future.
38 39 20th Anniversary Panel Plenary Talk Coulda, Woulda, Shoulda: 20 Years of Multimedia Opportunities Decoding Visual Experience from the Human Brain Yukiyasu Kamitani (ATR Computational Neuroscience Laboratories, JP) Organizers: Klara Nahrstedt (University of Illinois at Urbana-Champaign, US) Malcolm Slaney (Microsoft, US) Abstract: Panelists: Dick Bulterman (CWI / Vrije University, NL) Brain activity can be seen as “codes” that encode mental states. Recent advances in human Ramesh Jain (University of California, Irvine, US) neuroimaging such as functional magnetic resonance imaging (fMRI) have revealed brain regions Larry Rowe (University of California, Berkeley / FXPAL, US) that encode specific behavior and cognition. Despite the wide-spread use of human neuroimaging, Ralf Steinmetz (Darmstadt University of Technology, DE) its potential to read out, or “decode”, mental contents from brain activity has not been fully explored. Abstract: In this talk, I present methods for decoding visual representations from fMRI activity patterns In August 1–6, 1993, the ACM Special Interest Group in Multimedia (SIGMM) came together based on machine learning techniques. I show how early visual features represented in “subvoxel” in Anaheim, California, to talk about challenges, solutions, and results related to digital images, neural structures could be decoded from ensemble fMRI responses. Decoding of stimulus features audio, video, graphics, and multimedia. The initial Anaheim conference, chaired by the General is extended to the method for neural mind-reading, which attempts to predict a person’s subjective Chair J.J. Garcia-Luna-Aceves, started a strong tradition of annual conference meetings for the state using a decoder trained with unambiguous stimulus presentation. We then discuss a modular SIGMM community and this became the SIGMM’s premier multimedia conference event, the ACM decoding approach, in which a wide variety of percepts can be decoded by combining the outputs of International Conference on Multimedia (ACM Multimedia). multiple decoder modules. On the basis of this approach, we were able to reconstruct arbitrary visual images using the decoder trained on fMRI responses to only several hundred random images. Finally, The last 20 years has seen numerous interesting, innovative, engineering multimedia challenges, I discuss potential applications of neural decoding to brain-based communications. solutions, results, opportunities, failures and successes. The agenda of the annual meetings include problems in multimedia synchronization, multicasting, streaming, peer-to-peer, storage, multimedia Yukiyasu Kamitani is currently the head of Department of Neuroinformatics at ATR Computational Neuroscience scheduling, quality of service, content analysis, human interfaces quality of experiences, applications Laboratories, Kyoto, Japan, and a Professor at Nara Institute of Science and Technology (NAIST). He received B.A. in such as video conferencing, authoring, tele-presence, video-on-demand, games, and many others. Cognitive Science from University of Tokyo in 1993, M.S. in Philosophy of Science from University of Tokyo in 1995, and Ph.D. in Computation and Neural Systems from California Institute of Technology in 2001. He continued his research in We have seen many generations of multimedia researchers, from industry and academia, bring to cognitive and computational neuroscience as a research fellow at Beth Israel Deaconess Medical Center (Harvard Medical the conference new and different insights to problems of the time. We have seen new multimedia School), and as a research staff member at Princeton University. In 2004, he joined ATR Computational Neuroscience companies start and grow in the multimedia area, including Google, Yahoo!, YouTube, Akamai and Laboratories, where he currently works on neural decoding of human brain signals. He was named Research Leader in Neural Facebook. We have seen existing companies — such as Sony, Toshiba, Philips, IBM, Microsoft, HP, Imaging on the 2005 “Scientific American 50.” Apple — change their focus to include digital media including. We have seen multimedia companies merge including AltaVista, Inktomi and others. The bottom line is that the ACM Multimedia conference venue has seen many multimedia opportunities over the 20 years. The aim of this panel is to look back at the various multimedia opportunities over the 20 years, and encourage a discussion what did we do, what could we have done, and what should we have done with the multimedia opportunities. 40 41 Industrial Exhibits Oct. 29, 2012 Workshops, Tutorials, Reception Location: Nara Prefectural New Public Hall, Reception Hall and Meeting Room 2 10:00–17:30 Workshop SAM International Workshop on Socially-Aware Multimedia (SAM 2012) ………………………………………… ▶ 44 1. Mitsubishi Electric Nara Prefectural New Public Hall, Noh Theater HEVC Real-time Decoder for UHDTV 09:30–17:30 Oct. 29 2. Panasonic Workshop CrowdMM International ACM Workshop on Crowdsourcing for Multimedia 2012 …………………………………………………………………………………………………………………………………… Personal Content Management and Search System for Web-Service Application (CrowdMM 2012) ▶ 47 Todaiji Culture Center, Gold Bell Hall 3. FXPAL 09:30–13:00 Video Manga: Interactive Video Summaries Tutorial 1T1 - Interacting with Image Collections - Visualisation and Browsing of Image Repositories …… ▶ 49 MixPad: Augmenting Interactive Paper with Mice & Keyboards Nara Prefectural New Public Hall, Conference Room 1 4. HP Labs Speaker: Gerald Schaefer (Loughborough University, UK) …… Mobile Clipper Tutorial 2T2 - Dynamic Adaptive Streaming over HTTP - From Content Creation to Consumption ▶ 49 Nara Prefectural New Public Hall, Conference Room 2 5. KDDI R&D Laboratories Speakers: Christian Timmerer (Alpen-Adria-Univ. Klagenfurt, AT) Content Production Technology of Free-viewpoint Media Applicable for Virtual Stadium Carsten Griwodz (Simula Research Laboratory, NO) ………………………………… 6. NTT Docomo Tutorial 3T3 - A Human-Centered Perspective on Multimedia Data Science ▶ 51 Real-time Text Translation Application for Camera Previews of Smartphone for Travelers Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Speaker: Alejandro Jaimes (Yahoo! Research, ES) 7. DeNA 13:00–14:30 About DeNA Technology Journal of Multimedia Editorial Board Meeting (By invitation) 8. OMRON 14:00–17:30 Natural User Interface Technology of OKAO Vision Tutorial 4T4 - Continuous Analysis of Emotions for Multimedia Applications …………………………………▶ 52 9. SHARP & NHK Nara Prefectural New Public Hall, Conference Room 1 SUPER Hi-VISION 8Kx4K LCD Speakers: Hatice Gunes (Queen Mary, University of London, UK) Björn Schuller (Technische University Munchen, DE) Tutorial 5T5 - Privacy Concerns in Multimedia and Their Solutions ………………………………………………………▶ 53 Nara Prefectural New Public Hall, Conference Room 2 Speaker: Gerald Friedland (ICSI / University of California, Berkeley, US) Tutorial 6T6 - Multimedia Recommendation …………………………………………………………………………………………………………▶ 54 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Speakers: Jialie Shen (Singapore Management University, SG) Meng Wang (Hefei University of Technology, CN) Shuicheng Yan (National University of Singapore, SG) Peng Cui (Tsinghua University, CN) 10:00–17:00 Multimedia Art Exhibition 2012 Eternal / Moment ………………………………………………………………………………………… ▶ 3 Todaiji Culture Center, Small Hall 42 43 Full-day Workshop SAM 10:00–17:30 11:50–12:00 What Fresh Media Are You Looking For? Retrieving Media Items from International Workshop on Socially-Aware Multimedia Multiple Social Networks (SAM 2012) Giuseppe Rizzo, Thomas Steiner, Raphaél Troncy, Ruben Verborgh, José Luis Redondo Garcia Oct. 29 Workshop Chairs: Pablo Cesar (CWI, NL) Oct. 29 12:00–12:15 Discussion & Wrap-up David A. Shamma (Yahoo! Research, US) David A. Shamma Doug Williams (BT Research & Technology, UK) Cees G.M. Snoek (University of Amsterdam, NL) 12:15–12:20 Short Break Location: Nara Prefectural New Public Hall, Noh Theater 12:20–13:00 Invited Talk Note: Twitter tag #sam2012 3D Teleimmersion for Remote Injury Assessment Klara Nahrstedt 13:00–14:00 Lunch Break 10:00–10:15 Welcome Address Pablo Cesar, Ian Kegel, David A. Shamma Session 2: Social Interactions 10:15–10:55 Keynote Talk Session Chair: Ian Kegel (BT Research & Technology, UK) Massive Change: How Social Media Can Enable a Sustainable World 14:00–14:50 Hari Sundaram 10:55–11:25 Coffee Break 14:00–14:05 Introduction to the session Ian Kegel Session 1: Socially-Aware Multimedia Retrieval 14:05–14:15 Session Chair: David A. Shamma (Yahoo! Research, US) Automatic Orchestration of Video Streams to Enhance Group Communication 11:25–12:15 Manolis Falelakis, Martin Groen, Michael Frantzis, Rene Kaiser, Marian Ursu 14:15–14:25 Qualitative Assessment of Contemporary Media Sharing Practices and Their 11:25–11:30 Introduction to the session Relationship to the sMS Platform David A. Shamma Maarten Wijnants, Wim Lamotte, Jonas De Meulenaere, Wendy Van den Broeck 11:30–11:40 Towards Data-driven Estimation of Image Tag Relevance using Visually 14:25–14:35 Media-based Social Interaction Patterns: A Case Study in an Online Civic Similar and Dissimilar Folksonomy Images Mobilization Sihyoung Lee, Wesley De Neve, Yong Man Ro Maria da Graça Campos Pimentel, Alan Keller Gomes 11:40–11:50 Gathering Training Sample Automatically for Social Event Visual Modeling 14:35–14:50 Discussion & Wrap-up Xueliang Liu, Benoit Huet Ian Kegel
44 45 14:50–14:55 Short Break Full-day Workshop CrowdMM 09:30–17:30 14:55–15:35 Keynote Talk Social.Media.Meaning International ACM Workshop on Crowdsourcing for Multimedia 2012 Elizabeth Churchill (CrowdMM 2012)
Oct. 29 15:35–16:05 Coffee Break Workshop Chairs: Wei-Ta Chu (National Chung Cheng University, TW) Oct. 29 Martha Larson (Delft University of Technology, NL) Session 3: Theories and New Perspectives Wei Tsang Ooi (National University of Singapore, SG) Session Chair: Pablo Cesar (CWI, NL) Kuan-Ta Chen (Academia Sinica, TW) 16:05–16:55 Location: Todaiji Culture Center, Gold Bell Hall
16:05–16:10 Introduction to the Session Pablo Cesar 09:30–09:40 Opening Remarks
16:10–16:20 Highly-Personal Multimedia: Supporting the User-in-the-Small 09:40–10:30 Keynote Dick C.A. Bulterman PodCastle and Songle: Crowdsourcing-Based Web Services for Spoken Content 16:20–16:30 Social Media is History Retrieval and Active Music Listening Frank Nack Masataka Goto 16:30–16:40 Funniest Thing I've Seen Since [href="http://flic.kr/p/KGEGB"]: Shifting 10:30–11:00 Coffee Break Perspectives from Multimedia Artefacts to Utterances Brett Adams, Dinh Phung, Svetha Venkatesh Session 1: Annotation 11:00–11:50 16:40–16:55 Discussion & Wrap-up Pablo Cesar 11:00–11:25 Tagging Tagged Images: On the Impact of Existing Annotations on Image Tagging César Moltedo, Hernán Astudillo, Marcelo Mendoza Session 4: Discussion, Concluding Remarks and Sake Session Chairs: Pablo Cesar (CWI, NL) 11:25–11:50 Ground Truth Generation in Medical Imaging: A Crowdsourcing based Iterative Approach Ian Kegel (BT Research & Technology, UK) Antonio Foncubierta Rodríguez, Henning Müller David A. Shamma (Yahoo! Research, US) 16:55–17:30 Session 2 : Short Papers 11:50–12:30
11:50–12:00 Crowdsourcing in Emotion Studies across Time and Culture Marwa Mahmoud, Tadas Baltrusaitis, Peter Robinson 12:00–12:10 A Closer Look at Photographers' Intentions: a Test Data Set Mathias Lux, Mario Taschwer, Oge Marques
46 47 12:10–12:20 Crowdsourcing User Interactions within Web Video through Pulse Modeling Tutorial T1 09:30–13:00 Markos Avlonitis, Konstantinos Chorianopoulos, David Ayman Shamma 12:20–12:30 Crowdsourced User Interface Testing for Multimedia Applications Interacting with Image Collections Raynor Vliegendhart, Eelco Dolstra, Johan Pouwelse – Visualisation and Browsing of Image Repositories
Oct. 29 Poster session: Oct. 29 Speaker: Gerald Schaefer (Loughborough University, UK) 12:30–13:00 Location: Nara Prefectural New Public Hall, Conference Room 1 Note: http://www-staff.lboro.ac.uk/~cogs/talks/MM2012/mm2012tutorial.html 13:00–14:00 Lunch Abstract: Session 3: Evaluation In this tutorial we will look at a variety of techniques and methods for effective and intuitive image 14:00–15:15 database visualisation and browsing. While interaction with traditional image retrieval systems can lead to a confusing and frustrating user experience, image browsing systems attempt to provide the 14:00–14:25 Pushing the Limits of Mechanical Turk: Qualifying the Crowd for Video Geolocation user with an intuitive interface to manage potentially large image databases. Luke Gottlieb, Jaeyoung Choi, Pascal Kelm, Thomas Sikora, Gerald Friedland 14:25–14:50 Crowdsourcing Micro-Level Multimedia Annotations: The Challenges of In the tutorial we will look at how image databases are visualised in the three main approaches of Evaluation and Interface mapping-based, clustering-based and graph-based image database navigation systems, how intuitive Sunghyun Park, Gelareh Mohammadi, Ron Artstein, Louis-Philippe Morency browsing operations are supported, how image databases can be browsed employing non-desktop 14:50–15:15 Crowdsourcing Approach for Evaluation of Privacy Filters in Video Surveillance systems (such as VR hardware, or mobile devices), and how the effectiveness of image browsing Pavel Korshunov, Shuting Cai, Touradj Ebrahimi systems can be evaluated.
15:15–15:40 Coffee Break
Session 4: Novel Applications 15:40–16:30
15:40–16:05 Tag Suggestion on YouTube by Personalizing Content-based Auto-Annotation Dominik Henter, Damian Borth, Adrian Ulges 16:05–16:30 Enhancing Online 3D Products through Crowdsourcing Thi Phuong Nghiem, Axel Carlier, Geraldine Morin, Vincent Charvillat
Session 5: Panel Discussion 16:30–17:25
17:25–17:30 Concluding Remarks 48 49 Tutorial T2 09:30–13:00 Tutorial T3 09:30–13:00 Dynamic Adaptive Streaming over HTTP – From Content Creation to A Human-Centered Perspective on Multimedia Data Science Consumption Speaker: Alejandro Jaimes (Yahoo! Research, ES) Oct. 29 Speakers: Christian Timmerer (Alpen-Adria-University Klagenfurt, AT) Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Oct. 29 Carsten Griwodz (Simula Research Laboratory, NO) Location: Nara Prefectural New Public Hall, Conference Room 2 Abstract: In recent years, the amount of data available for analysis has exploded. This is creating many Abstract: new opportunities for research, particularly in the field of social media. Given the importance of In this tutorial we present dynamic adaptive streaming over HTTP ranging from content creation to multimedia content in social media, there is no doubt that the two fields go hand in hand. A lot of the consumption. It particular, it provides an overview of the recently ratified MPEG-DASH standard, sharing and activity on the web currently occurs around multimedia materials. People often share how to create content to be delivered using DASH, its consumption, and the evaluation thereof with images, videos, and links to multimedia content. Arguably, the social media phenomenon is having respect to competing industry solutions. The tutorial can be roughly clustered into three parts. In part I a strong impact on multimedia, and is creating opportunities for many new applications built around we will provide an introduction to DASH, part II covers content creation, delivery, and consumption, sharing of multimedia content. It is therefore clear that gaining a deep understanding of data in the and, finally, part III deals with the evaluation of existing (open source) MPEG-DASH implementations social media context can have a strong impact on the multimedia field as a whole. compared to state-of-art deployed industry solutions. This tutorial will focus on analyzing user behavior through large-scale data analysis. This includes discovering and leveraging search and navigation patterns, understanding how elements of interaction impact behavior, and how we can use controlled experiments in combination with user studies and other techniques to gain insights into human behavior with a particular emphasis on multimedia, particularly in the context of social media.
50 51 Tutorial T4 14:00–17:30 Tutorial T5 14:00–17:30 Continuous Analysis of Emotions for Multimedia Applications Privacy Concerns in Multimedia and Their Solutions
Speakers: Hatice Gunes (Queen Mary, University of London, UK) Speaker: Gerald Friedland (ICSI / University of California, Berkeley, US) Oct. 29 Björn Schuller (Technische University Munchen, DE) Location: Nara Prefectural New Public Hall, Conference Room 2 Oct. 29 Location: Nara Prefectural New Public Hall, Conference Room 1
Abstract: Abstract: Multimedia content is loaded with emotion: In speech, music, sound, text, and video. People in video or The growth of multimedia as demonstrated by social networking sites such as Facebook and YouTube audio media naturally communicate subtle emotions and affective states by means of language, vocal combined with advances in multimedia retrieval (geo-tagging, web search, face recognition, speaker intonation, facial expression, hand gesture, head movement, body movement and posture, and possess a verification, location estimation, etc.) provides novel opportunities for the unethical use of multimedia. refined mechanism for understanding and interpreting information conveyed by these behavioral cues. In small scale or in isolation multimedia analytics have always been a powerful but reasonably Enabling automatic and continuous emotion analysis in multimedia applications would be extremely contained privacy threat. However, when linked together and used on an Internet scale, the threat can beneficial for personalized and emotion-sensitive multimedia content analysis and processing, implicit be enormous and pervasive. At the same time, some of the solutions to security and privacy concerns tagging, multimedia event understanding, search and retrieval, multimedia interaction and digital art are really simple and follow a limited set of basic principles, which, when already obeyed in the early installations, etc. Therefore, this tutorial aims to become the initial but crucial step toward bringing stages of the development of a system can avoid large unresolvable issues later. Many of them are together researchers from two very relevant yet disconnected fields of research and practice: affective well known in the security and privacy communities but not so much in the multimedia community. computing and multimedia. The objective of this tutorial is to introduce interested multimedia students and researchers who are not specialized in security and privacy issues into the thinking of a security and privacy researcher. The tutorial aims to give a comprehensive introduction to automatic, dimensional and continuous analysis of emotions and affective signals, and provide indicators and examples of how the current developments The tutorial will be a vivid class with many examples based on material developed for a CS294 course in this field can be utilized to enhance a broad range of multimedia applications. More specifically, this at the EECS department of UC Berkeley. Using real-world examples and their consequences, the tutorial aims at: tutorial will focus on privacy and security threats induced by modern social networking practices in combination with multimedia retrieval. 1) Introducing the existing efforts and major accomplishments in automatic, dimensional and continuous analysis of emotions from multiple cues and modalities; 2) Demonstrating the practical aspects, available frameworks, tools, databases, and automatic analyzers, that can be easily used by multimedia researchers around the world; 3) Encouraging the integration of the recent developments in the field into multimedia applications, and inter-disciplinary cross-fertilization of affective computing and multimedia research fields.
The tutorial will also focus on providing a broad overview of recent algorithms and methodology, and predict potential oncoming trends for relevant multimedia applications. The presenters will draw on the most recent developments from the Journal Special Issues they have guest edited and the workshops they organized.
52 53 Tutorial T6 14:00–17:30 Reception 17:45–20:00 Multimedia Recommendation Location: Nara Prefectural New Public Hall, Garden Sake (rice wine） provided by ASAHI-SHUZO SAKE BREWING CO., LTD. Speakers: Jialie Shen (Singapore Management University, SG) Oct. 29 Meng Wang (Hefei University of Technology, CN) Oct. 29 Shuicheng Yan (National University of Singapore, SG) Peng Cui (Tsinghua University, CN) Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4
Abstract: Due to the rapid growth of online multimedia information, the problem of information overload has become more and more serious in recent decades. To address this problem, various multimedia recommendation technologies have been developed by different research communities (e.g., multimedia systems, information retrieval, and machine learning). Meanwhile, many commercial web systems (e.g., Flickr, Youtube, and Last.fm) have successfully applied recommendation techniques to provide users personalized multimedia content and services in a convenient and flexible way.
While several tutorials and courses were dedicated to multimedia search in the last few years, to the best of our knowledge, the tutorial should be the pioneering one solely focusing on multimedia recommendation technologies and their applications on various domains and media content. We plan to summarize the research along this direction and provide a good balance between theoretical methodologies and real system development (including several industrial approaches). It includes:
• Introducing why accurate recommendation system is important for web scale multimedia retrieval and sharing Examining current commercial systems and research prototypes, focusing on comparing the advantages and the disadvantages of the various strategies and schemes for different types of media documents (e.g., image, video and audio). • Discussing and reviewing various limitations of the current generation of recommendation systems. • Reviewing key challenges and technical issues in building recommendation systems and we explore some of the ways that how recommendation techniques can be used to improve different kinds of retrieval or sharing tasks over large scale collections in long run. • Discussing a few promising research directions and exploring potential solutions. • Make predictions about the road that lies ahead for the scholars in MM and other related communities.
54 55 Oct. 30, 2012 Main Conference Day 1
09:00–09:30 15:20–17:00 …………………………………………………………………………………………………………………………………………………………………………… Opening ▶ 58 Oral Session OS4 Large Scale Search ………………………………………………………………………………………………………………… ▶ 67 Nara Prefectural New Public Hall, Noh Theater Nara Prefectural New Public Hall, Noh Theater Oral Session OS5 Person and Face Analysis …………………………………………………………………………………………………… ▶ 67 Nara Prefectural New Public Hall, Conference Room 1 09:30–11:10 Oral Session OS6 Video Distribution …………………………………………………………………………………………………………………… ▶ 67 Best Paper Candidate Session ……………………………………………………………………………………………………………………………………PL1 ▶ 58 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Nara Prefectural New Public Hall, Noh Theater Panel Discussion PA1 Content is Dead; Long Live Content! ……………………………………………………………… ▶ 68 Oct. 30 Oct. 30 Nara Prefectural New Public Hall, Conference Room 2
11:10–17:00 (Core Time: 11:10–12:40） Poster Session 1 PS1…………………………………………………………………………………………………………………………………………………………………… ▶ 59 17:45–18:45 Nara Prefectural New Public Hall, Reception Hall 20th Anniversary Keynote Talk ……………………………………………………………………………………………………………………………………PL2 ▶ 69 Technical Demo Session 1TD1 ……………………………………………………………………………………………………………………………………………… ▶ 63 Nara Prefectural Cultural Hall, International Hall Nara Prefectural New Public Hall, Reception Hall and Foyer Future Direction of Digital Content Masahiro Fujita (Sony Corporation, JP)
11:40–13:10 TOMCCAP Editorial Board Meeting (By invitation) 10:00–17:00 Todaiji Culture Center, Meeting Room A Multimedia Art Exhibition 2012 Eternal / Moment ………………………………………………………………………………………… ▶ 3 Todaiji Culture Center, Small Hall
13:10–14:50 Oral Session OS1 Content-Based Image Retrieval …………………………………………………………………………………… ▶ 65 Nara Prefectural New Public Hall, Noh Theater Oral Session OS2 Audio and Music ……………………………………………………………………………………………………………………… ▶ 65 Nara Prefectural New Public Hall, Conference Room 1 Oral Session OS3 Video Applications ………………………………………………………………………………………………………………… ▶ 66 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Brave New Ideas Program ………………………………………………………………………………………………………………………………………………BNI ▶ 66 Nara Prefectural New Public Hall, Conference Room 2
56 57 Opening 09:00–09:30 Core-Time for Posters and Technical Demos 11:10–12:40
Noboru Babaguchi (Osaka University, JP) Location: Nara Prefectural New Public Hall, Reception Hall and Foyer Kiyoharu Aizawa (The University of Tokyo, JP) John Smith (IBM, US) Each poster and technical demo session has a core-time. During the core-time, presenters will be Location: Nara Prefectural New Public Hall, Noh Theater available in front of their posters. Each full paper (oral) presentation is also available as a poster for better interaction with the authors. Oct. 30 Oct. 30
Best Paper Candidate Session PL1 09:30–11:10
Session Chair: John Smith (IBM, US) Location: Nara Prefectural New Public Hall, Noh Theater
09:30–09:55 Finding Perfect Rendezvous On the Go: Accurate Mobile Visual Localization and Its Applications to Routing Heng Liu, Tao Mei, Jiebo Luo, Houqiang Li, Shipeng Li 09:55–10:20 Right Buddy Makes the Difference: an Early Exploration of Social Relation Analysis in Multimedia Applications Jitao Sang, Changsheng Xu 10:20–10:45 Propagation-Based Social-Aware Replication for Social Video Contents Zhi Wang, Lifeng Sun, Xiangwen Chen, Wenwu Zhu, Jiangchuan Liu, Minghua Chen, Shiqiang Yang 10:45–11:10 Action Recognition for Human-Marionette Interaction Shih-Yao Lin, Chuen-kai Shie, Shen-chi Chen, Yi-Ping Hung
58 59 Poster Session PS1 11:10–17:00 15. Color Transfer Based on Multiscale Gradient-aware Decomposition and Color Distribution Mapping Session Chair: Tat -Seng Chua (National University of Singapore, SG) Zhuo Su, Daiguo Deng, Xue Yang, Xiaonan Luo Location: Nara Prefectural New Public Hall, Reception Hall 16. On Sparse and Low-Rank Matrix Decomposition for Singing Voice Separation Yi-Hsuan Yang 1. Video Saliency Detection in the Compressed Domain 17. Memorable Basis: Towards Human-Centralized Sparse Representation Yuming Fang, Weisi Lin, Zhenzhong Chen, Chia-Ming Tsai, Chia-Wen Lin Xiaoshuai Sun, Hongxun Yao 2. A Robust and Efficient Shot Boundary Detection Approach Based on Fisher Criterion 18. Detecting Text in the Real World Chi Zhang, Weiqiang Wang Trung Q. Phan, Palaiahnakote Shivakumara, Chew Lim Tan 3. A Genetic Algorithm for Audio Retargeting 19. Face Image Super-Resolution via Nearest Feature Line Stephan Wenger, Marcus Magnor Zhen Han, Junjun Jiang, Ruimin Hu, Tao Lu, Kebin Huang Oct. 30 Oct. 30
4. Seam Carving with Forward Gradient Difference Maps 20. Modalities Consensus for Multi-Modal Constraint Propagation Hyeonwoo Noh, Bohyung Han Zhenyong Fu, Hongtao Lu, Horace H.S. Ip, Zhiwu Lu 5. Surveillance Video Coding via Low-Rank and Sparse Decomposition 21. Joint Semantic Segmentation by Searching for Compatible-Competitive References Chongyu Chen, Jianfei Cai, Weisi Lin, Guangming Shi Ping Luo, Xiaogang Wang, Liang Lin, Xiaoou Tang 6. Enhanced Extraction of Moving Objects in Variable Bit-Rate Video Streams 22. An Effective Multi-Clue Fusion Approach for Web Video Topic Detection Jui-Yu Yen, Bo-Hao Chen, Shih-Chia Huang Tianlong Chen, Chunxi Liu, Qingming Huang 7. Context-aware Affective Images Classification based on Bilayer Sparse Representation 23. 3D Fingertip and Palm Tracking in Depth Image Sequences Bing Li, Weihua Xiong, Weiming Hu, Xinmiao Ding Hui Liang, Junsong Yuan, Daniel Thalmann 8. Gabor-Based Gradient Orientation Pyramid for Kinship Verification Under Uncontrolled Environments 24. From Speech to Personality: Mapping Voice Quality and Intonation into Personality Differences Xiuzhuang Zhou, Jiwen Lu, Junlin Hu, Yuanyuan Shang Gelareh Mohammadi, Antonio Origlia, Maurizio Filippone, Alessandro Vinciarelli 9. Robust Stroke-based Video Animation via Layered Motion and Correspondence 25. Predicting the Conflict Level in Television Political Debates: an Approach Based on Tao Lin, Liang Lin, Qing Wang Crowdsourcing, Nonverbal Communication and Gaussian Processes 10. Texture Optimization for Seamless View Synthesis Through Energy Minimization Samuel Kim, Maurizio Filippone, Fabio Valente, Alessandro Vinciarelli Wenxiu Sun, Oscar C. Au, Lingfeng Xu, Yujun Li, Wei Hu, Zhiding Yu 26. Using Structural Patches Tiling to Guide Human Head-Shoulder Segmentation 11. Semi-Supervised Multi-Instance Multi-Label Learning for Video Annotation Task Pengyang Bu, Nan Wang, Haizhou Ai Xin-Shun Xu, Yuan Jiang, Xiangyang Xue, Zhi-Hua Zhou 27. Video Object Segmentation with Shortest Path 12. Geo-Location Inference on News Articles via Multimodal pLSA Bao Zhang, Handong Zhao, Xiaochun Cao Youjie Zhou, Jiebo Luo 28. Video Object Cosegmentation 13. A Method for Detecting Salient Regions using Integrated Features Ding-Jie Chen, Hwann-Tzong Chen, Long-Wen Chang Zhendong Mao, Yongdong Zhang, Ke Gao, DongMing Zhang 29. Community as a Connector: Associating Faces with Celebrity Names in Web Videos 14. Deep Nonlinear Metric Learning with Independent Subspace Analysis for Face Verification Zhineng Chen, Chong-Wah Ngo, Juan Cao, Wei Zhang Xinyuan Cai, Chunheng Wang, Baihua Xiao, Xue Chen, Ji Zhou 60 61 Technical Demo Session TD1 11:10–17:00 30. Comparison of Prediction-based Fusion and Feature-level Fusion across Different Learning Methods Stavros Petridis, Sanjay Bilakhia, Maja Pantic Session Chair: Hirokazu Kato (NAIST, JP) 31. Depth Estimation for Semi-Automatic 2D to 3D Conversion Location: Nara Prefectural New Public Hall, Reception Hall and Foyer Richard Rzeszutek, Raymond Phan, Dimitrios Androutsos 32. Predicting Domain Adaptivity: Redo or Recycle? 1. Face Replacement with Large-pose Differences Ting Yao, Chong-Wah Ngo, Shiai Zhu Yuan Lin, Qian Lin, Feng Tang, Shengjin Wang 33. Music/Speech Classification Using High-level Features Derived from FMRI Brain Imaging 2. TouchPaper: Making Print Interactive Xi Jiang, Tuo Zhang, Xintao Hu, Lie Lu, Junwei Han, Lei Guo, Tianming Liu Feng Tang, Hao Tang, Danien R. Tretter, Qian Lin 34. Bilingual Analysis of Song Lyrics and Audio Words 3. QuickToon: A Real-Time Video Stylization and Sharing System on General Processors Jen-Yu Liu, Chin-Chia Yeh, Yi-Hsuan Yang, Yuan-Ching Teng Hongsheng Yang, Huanliang Sun, Jiangbo Lu Oct. 30 Oct. 30
35. Self-Paced Dictionary Learning for Image Classification 4. Sketch2Tag: Automatic Hand-Drawn Sketch Recognition Ye Tang, Yu-Bin Yang, Yang Gao Zhenbang Sun, Changhu Wang, Liqing Zhang, Lei Zhang 36. Cross Matching of Music and Image 5. A Rapid Flower/Leaf Recognition System Xixuan Wu, Yu Qiao, Xiaogang Wang, Xiaoou Tang Xianbiao Qi, Rong Xiao, Lei Zhang, Chun-Guang Li 37. Name That Room: Room identification using acoustic features in a recording Nils Peters, Howard Lei, Gerald Friedland 6. A Tool for Automatic Cinemagraphs Mei-Chen Yeh, Po-Yi Li 38. Enhancing Visual Dominance by Semantics-Preserving Image Recomposition Lai-Kuan Wong, Kok-Lim Wong 7. Actions Speak Louder than Words: Searching Human Action Video Based on Body Movement Yan-Ching Lin, Min-Chun Hu, Wen-Huang Cheng, Yung-Huan Hsieh, Hong-Ming Chen 39. Image Tag Re-ranking by Coupled Probability Transition Jie Xiao, Wengang Zhou, Xia Li, Meng Wang, Qi Tian 8. Action Tutor : Real-Time Exemplar-based Sequential Movement Assessment with Kinect Sensor Chi-Wen Chen, Min-Chun Hu, Wen-Huang Cheng, Che-Han Chang, Jui-Hsin Lai, Ja-Ling Wu 40. Low Rank Metric Learning for Social Image Retrieval Zechao Li, Jing Liu, Yu Jiang, Jinhui Tang, Hanqing Lu 9. Jiku Live: A Live Zoomable Video Streaming System 41. Can we Understand van Gogh's Mood? Learning to Infer Affects from Images in Social Networks Arash Shafiei, Quang M. K. Ngo, Ravindra Guntur, Mukesh K. Saini, Cong Pang, Wei-Tsang Ooi Jia Jia, Sen Wu, Xiaohui Wang, Peiyun Hu, Lianhong Cai, Jie Tang 10. Smart VideoCooKing: A Multimedia Cooking Recipe Browsing Application on Portable Devices 42. Social Tag Alignment with Image Regions by Sparse Reconstructions Keisuke Doman, Cheng Ying Kuai, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase Yang Liu, Jing Liu, Zechao Li, Biao Niu, Hanqing Lu 11. Through the Looking Glass: Mirror Worlds for Augmented Awareness & Capability 43. Social Event Detection: Finding Events through the Social Interaction Graph Don Kimber, Jun Shingu, Jim Vaughan, David Arendash, David Lee, Maribeth Back Yanxiang Wang, Hari Sundaram, Lexing Xie 12. LikeLines: Collecting Timecode-level Feedback for Web Videos through User Interactions Raynor Vliegendhart, Martha Larson, Alan Hanjalic 13. Exploring and Browsing Photos through Characteristic Geographic Tag Regions Bart Thomee, Adam Rae 62 63 Oral Session OS1 13:10–14:50 14. Rapid Object Search Engine for Contextual Advertisement Yuning Jiang, Junsong Yuan, Jingjing Meng Content-Based Image Retrieval
15. Multi-View Video Contents Viewing System by Synchronized Multi-view Streaming Architecture Session Chair: Benoit Huet (EURECOM, FR) Takafumi Marutani, Kenji Mase, Toshiaki Fujii, Tetsuya Kawamoto Location: Nara Prefectural New Public Hall, Noh Theater 16. X-Large Virtual Workspaces for Projector Phones through Peephole Interaction Bonifaz Kaufmann, Martin Hitz 13:10–13:35 A Bag-of-Objects Retrieval Model for Web Image Search 17. Demo: Virtual Director for Live Event Broadcast Yang Yang, Linjun Yang, Gangshan Wu, Shipeng Li Rene Kaiser. Wolfgang Weiss, Malte Borsum, Axel Kochale, Mrco Masetti, Valentina Zampichelli 13:35–14:00 Harvesting Visual Concepts for Image Search with Complex Queries Liqiang Nie, Shuicheng Yan, Meng Wang, Richang Hong, Tat-Seng Chua 18. Fly-through Heijo Palace Site: Historical Tourism System Using Augmented Telepresence Oct. 30 Oct. 30 Fumio Okura, Masayuki Kanbara, Naokazu Yokoya 14:00–14:25 Exploiting Visual Word Co-occurrence for Image Retrieval Miaojing Shi, Xinghai Sun, Dacheng Tao, Chao Xu 19. Mobile Multimedia Presentation in Self-Forming Mobile Device Groups: Ad-hoc Networks in Practice Kevin Collins, Noel E. O’Conner, Gabriel M. Muntean 14:25–14:50 Attribute Feedback Hangwang Zhang, Zheng-Jun Zha, Shuicheng Yan, Jingwen Bian, Tat-Seng Chua 20. Eyeke: What You Hear is What You See Takeshi Okunaka, Yoshinobu Tonomura 21. System for Creating Slideshows Based On People and Their Emotions Oral Session OS2 13:10–14:50 Vassilios Vonikakis, Stefan Winkler 22. gTravel: An Global Social Travel System Audio and Music Richong Zhang, Xiaohui Guo, Hailong Sun, Jinpeng Huai, Xudong Liu Session Chair: Gerald Friedland (ICSI UC Berkeley, US) Location: Nara Prefectural New Public Hall, Conference Room 1
13:10–13:35 The Acoustic Emotion Gaussians Model for Emotion-Based Music Annotation and Retrieval Ju-Chiang Wang, Yi-Hsuan Yang, Hsin-Min Wang, Shyh-Kang Jeng 13:35–14:00 Context-Aware Mobile Music Recommendation for Daily Activities Xinxi Wang, David Rosenblum, Ye Wang 14:00–14:25 MusicScore: Mobile Music Composition for Practice and Fun Zimu Liu, Yuan Feng, Baochun Li 14:25–14:50 Modeling the QoE of Rate Changes in SKYPE/SILK VoIP Calls Chien-nan Chen, Cing-yu Chu, Su-ling Yeh, Hao-hua Chu, Polly Huang
64 65 Oral Session OS3 13:10–14:50 Oral Session OS4 15:20–17:00 Video Applications Large Scale Search
Session Chair: Alexander G. Hauptmann (Carnegie Mellon University, US) Session Chair: Chong-Wah Ngo (City University of Hong Kong, HK) Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Location: Nara Prefectural New Public Hall, Noh Theater
13:10–13:35 PaperVideo: Interacting with Videos on Multiple Paper-like Displays 15:20–15:45 Scalar Quantization for Large Scale Image Search Roman Lissermann, Simon Olberding, Benjamin Petry, Max Mühlhäuser, Jürgen Steimle Wengang Zhou, Yijuan Lu, Houqiang Li, Qi Tian 13:35–14:00 MoViMash: Online Mobile Video Mashup 15:45–16:10 Query-driven Iterated Neighborhood Graph Search for Large Scale Indexing Mukesh K. Saini, Raghudeep Gadde, Shuicheng Yan, Wei-Tsang Ooi Jindong Wang, Shipeng Li Oct. 30 Oct. 30 14:00–14:25 An Interactive System of Stereoscopic Video Conversion 16:10–16:35 SymCity: Feature Selection by Symmetry for Large Scale Image Retrieval Zhebin Zhang, Chen Zhou, Bo Xin, Yizhou Wang, Wen Gao Giorgos Tolias, Yannis Kalantidis, Yannis Avrithis 14:25–14:50 Enabling "Togetherness" in High-Quality Domestic Video Conferencing 16:35–17:00 Embedding Spatial Context Information into Inverted File for Large-scale Image Ian Kegel, Pablo Cesar, Jack Jansen, Dick Bulterman, Tim Stevens, Joke Kort, Retrieval Nikolaus Farber Zhen Liu, Houqiang Li, Wengang Zhou, Qi Tian
Brave New Ideas Program BNI 13:10–14:50 Oral Session OS5 15:20–17:00 Session Chairs: Alejandro Jaimes (Yahoo! Research, ES) Person and Face Analysis Tat-Seng Chua (National University of Singapore, SG) Location: Nara Prefectural New Public Hall, Conference Room 2 Session Chair: Nicu Sebe (University of Trento, IT) Location: Nara Prefectural New Public Hall, Conference Room 1 13:10–13:35 Situation Recognition: An Evolving Problem for Heterogeneous Dynamic Big Multimedia Data 15:20–15:45 A Smile Can Reveal Your Age: Enabling Facial Dynamics in Age Estimation Vivek K. Singh, Mingyan Gao, Ramesh Jain Hamdi Dibeklioglu, Theo Gevers, Albert A. Salah, Roberto Valenti 13:35–14:00 Distributional Semantics with Eyes: Using Image Analysis to Improve 15:45–16:10 Unsupervised Face-Name Association via Commute Distance Computational Representations of Word Meaning Jiajun Bu, Bin Xu, Chenxia Wu, Chun Chen, Jianke Zhu, Deng Cai, Xiaofei He Elia Bruni, Jasper Uijlings, Marco Baroni, Nicu Sebe 16:10–16:35 On Shape and the Computability of Emotions 14:00–14:25 Towards Indexing Representative Images on the Web Xin Lu, Poonam Suryanarayan, Reginald B. Adams Jr., Jia Li, Michelle G. Xin-Jing Wang, Zheng Xu, Lei Zhang, Ce Liu, Yong Rui Newman, James Z. Wang 14:25–14:50 Intent and its Discontents: The User at the Wheel of the Online Video Search Engine 16:35–17:00 Sense Beauty via Face, Dressing, and/or Voice Alan Hanjalic, Christoph Kofler, Martha Larson Tam V. Nguyen, Si Liu, Binbing Ni, Jun Tan, Yong Rui, Shuicheng Yan
66 67 Oral Session OS6 15:20–17:00 20th Anniversary Keynote Talk PL2 17:45–18:45
Video Distribution Session Chair: Noboru Babaguchi (Osaka University, JP) Location: Nara Prefectural Cultural Hall, International Hall Session Chair: Vera Goebel (University of Oslo, NO) Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4 17:45–18:45 Future Direction of Digital Content Masahiro Fujita (Sony Corporation, JP) 15:20–15:45 Leveraging Social Network Concepts for Efficient Peer-to-Peer Live Streaming See pp. 38–39 for details. Systems Haiying Shen, Ze Li, Hailang Wang, Jin Li 15:45–16:10 Jetway: Minimizing Costs on Inter-Datacenter Video Traffic Oct. 30 Oct. 30
Yuan Feng, Baochun Li, Bo Li 16:10–16:35 Control of Distributed Servers for Quality-Fair Delivery of Multiple Video Streams Nesrine Changuel, Bessem Sayadi, Michel Kieffer 16:35–17:00 GreenTube: Power Optimization for Mobile Video Streaming via Dynamic Cache Management Xin Li, Mian Dong, Zhan Ma, Felix C. A. Fernandes Panel Discussion PA1 15:20–17:00
Session Chairs: Lexing Xie (Australian National University, AU) David A. Shamma (Yahoo! Research, US) Cees Snoek (University of Amsterdam, NL) Location: Nara Prefectural New Public Hall, Conference Room 2
15:20–17:00 Content is Dead; Long Live Content! Susanne Boll, Tat-Seng Chua, Minoru “Mick” Etoh, Malcolm Slaney, Yong Rui
68 69 Oct. 31, 2012 Main Conference Day 2 Industrial Exhibits …………………………………………………………………………………………………………………………………………………………………IE ▶ 42 Nara Prefectural New Public Hall, Reception Hall and Meeting Room 2 09:00–09:40 SIGMM Technical Achievement Award 2012 …………………………………………………………………………………………………PL3 ▶ 72 14:20–15:50 Nara Prefectural New Public Hall, Noh Theater …………………………………………………………………………………………………………………………OSSC ▶ Reflections from an Industrial Perspective Open Source Software Competition 81 HongJiang Zhang Nara Prefectural New Public Hall, Conference Room 2
09:40–10:00 14:20–16:00 ……………………………………………………………………………………………………………………………… SIGMM Ph. D. Thesis Award 2012 …………………………………………………………………………………………………………………………PL4 ▶ 72 Oral Session OS7 Visual Search ▶ 82 Nara Prefectural New Public Hall, Noh Theater Nara Prefectural New Public Hall, Noh Theater Identifying and Incorporating Human Psycho-physical Factors along with Oral Session OS8 Human-centric Media …………………………………………………………………………………………………………… ▶ 83 Traditional QOS to Improve Experience Nara Prefectural New Public Hall, Conference Room 1 Wanming Wu Oral Session OS9 Presentation and Organization ………………………………………………………………………………………… ▶ 84 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 10:20–12:20 20th Anniversary Panel ……………………………………………………………………………………………………………………………………………………PL5 ▶ 73 16:30–17:45 Nara Prefectural New Public Hall, Noh Theater Oral Session OS10 Haptics …………………………………………………………………………………………………………………………………………… ▶ 85
Oct. 31 Coulda, Woulda, Shoulda: 20 Years of Multimedia Opportunities Oct. 31 Nara Prefectural New Public Hall, Noh Theater
12:20–13:50 16:30–18:10 MM12-MM13 Meeting (By invitation) Oral Session OS11 Event Recognition …………………………………………………………………………………………………………………… ▶ 85 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Nara Prefectural New Public Hall, Conference Room 1 Oral Session OS12 Semantic Tagging ……………………………………………………………………………………………………………………… ▶ 86 12:40–13:50 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 ACM MM Women's Luncheon ……………………………………………………………………………………………………………………………………… ▶ 74 SIGMM Business Meeting ……………………………………………………………………………………………………………………………………………… ▶ 86 Todaiji Culture Center, Meeting Room A Nara Prefectural New Public Hall, Conference Room 2
12:50–18:10 (Core Time:12:50–14:20) 18:45–19:45 …………………………………………………………………………………………………………………………………………………………………………… Poster Session 2 …………………………………………………………………………………………………………………………………………………………………PS2 ▶ 75 Noh Play ▶ 87 Nara Prefectural New Public Hall, Reception Hall Nara Prefectural New Public Hall, Noh Theater Technical Demo Session 2 ……………………………………………………………………………………………………………………………………………TD2 ▶ 78 Nara Prefectural New Public Hall, Foyer 10:00–17:00 ……………………………………………………………………………………………………………………………………………………………………… Video Program VP ▶ 80 Multimedia Art Exhibition 2012 Eternal / Moment ………………………………………………………………………………………… ▶ 3 Nara Prefectural New Public Hall, Reception Hall Todaiji Culture Center, Small Hall 70 71 SIGMM Technical Achievement Award 2012 PL3 09:00–09:40 20th Anniversary Panel PL5 10:20–12:20
Session Chair: Rainer Lienhart (Universitat Augsburg, DE) Session Chairs: Klara Nahrstedt (University of Illinois at Urbana-Champaign, US) Location: Nara Prefectural New Public Hall, Noh Theater Malcolm Slaney (Microsoft, US) Location: Nara Prefectural New Public Hall, Noh Theater 09:00–09:40 Reflections from an Industrial Perspective HongJiang Zhang 10:20–12:20 Coulda, Woulda, Shoulda: 20 Years of Multimedia Opportunities Dick Bulterman, Ramesh Jain, Lawrence Rowe, Ralf Steinmetz See p.40 for details.
SIGMM Ph. D. Thesis Award 2012 PL4 09:40–10:00 Oct. 31 Oct. 31
Session Chair: Svetha Venkatesh (Deakin University, AU) Location: Nara Prefectural New Public Hall, Noh Theater
09:40–10:00 Identifying and Incorporating Human Psycho-physical Factors along with Traditional QOS to Improve Experience Wanming Wu
72 73 ACM MM Women's Luncheon 12:40–13:50 Poster Session 2 PS2 12:50–18:10
Organizers: Susanne Boll (University of Oldenburg, DE) Session Chair: Liangliang Cao (IBM T. J. Watson Research Center, US) Klara Nahrstedt (University of Illinois at Urbana-Champaign, US) Location: Nara Prefectural New Public Hall, Reception Hall Svetha Venkatesh (Deakin University, AU) Location: Todaiji Culture Center, Meeting Room A 1. Visual Query Attributes Suggestion Jingwen Bian, Zheng-Jun Zha, Hanwang Zhang, Qi Tian, Tat-Seng Chua The Women’s luncheon at ACM MM 2012 will provide a great venue to meet and exchange with 2. Attribute-assisted Reranking for Web Image Retrieval women in the multimedia community. This year we will invite leading women in multimedia to act as Junjie Cai, Zheng-Jun Zha, Wengang Zhou, Qi Tian table heads and lead the discussions, We are looking forward to an exciting meeting with discussions from multimedia to work-life-balance. 3. Query Expansion Enhancement by Fast Binary Matching Xia Li, Wengang Zhou, Jinhui Tang, Qi Tian Note: Please pick up your lunch box at the main venue and bring it to the meeting room. Lunch is not 4. Compact Kernel Hashing with Multiple Features prepared at the room. Xianglong Liu, Junfeng He, Di Liu, Bo Lang 5. Similar Image Search with a Tiny Bag-of-delegates Representation Weiwen Tu, Rong Pan, Jingdong Wang 6. Online Non-feedback Image Re-ranking via Dominant Data Selection Chen Cao, Shifeng Chen, Yuhong Li, Jianzhuang Liu Core-Time for Posters, Technical Demos, Video Program and Industrial Exhibits 12:50–14:20 Oct. 31 7. Optimal Semi-Supervised Metric Learning for Image Retrieval Oct. 31 Kun Zhao, Wei Liu, Jianzhuang Liu Location: Nara Prefectural New Public Hall, Reception Hall and Foyer 8. View-based 3D Object Retrieval by Bipartite Graph Matching Each poster and technical demo session has a core-time. During the core-time, presenters will be Yue Wen, Yue Gao, Richang Hong, Huanbo Luan, Qiong Liu, Jialie Shen, Rongrong Ji available in front of their posters. 9. Local Geometry Adaptive Manifold Re-ranking for Shape-based 3D Object Retrieval Each full paper (oral) presentation is also available as a poster for better interaction with the authors. Ryutarou Ohbuchi, Yukinori Kurita 10. DLMSearch: Diversified Landmark Search by Photo Junfeng Ye, Jia Chen, Zejia Chen, Yihe Zhu, Shenghua Bao, Zhong Su, Yong Yu 11. Fast Semantic Image Retrieval based on Random Forest Hao Fu, Guoping Qiu 12. Sketch-based Image Retrieval on Mobile Devices Using Compact Hash Bits Kai-Yu Tseng, Yen-Liang Lin, Yu-Hsiu Chen, Winston H. Hsu 13. Towards Relevance and Saliency Ranking of Image Tags Songhe Feng, Congyan Lang, Bing Li 14. Mobile-Based Advertisement Information Retrieval from Images and Websites Yi-Feng Pan, Jian Sun, Siyuan Chen, Yuan He, Yingju Xia, Jun Sun, Satoshi Naoi 74 75 15. A User Study on Image Browsing on Touchscreens 30. PRiSMA: Searching Images in Parallel David Ahlström, Marco A. Hudelist, Klaus Schoeffmann, Gerald Schaefer Pancho Tolchinsky, Luca Chiarandini, Alejandro Jaimes 16. Discriminative ICA Model with Reconstruction Constraint for Image Classification 31. Local Visual Words Coding for Low Bit Rate Mobile Visual Search Yanhui Xiao, Zhenfeng Zhu, Shikui Wei, Yao Zhao Yue Wu, Shiyang Lu, Tao Mei, Jian Zhang, Shipeng Li 17. Search Web Images Using Objects, Backgrounds and Conditions 32. Virtual Reference View Generation for CBIR-based Visual Pose Estimation Jiemi Zhang, Chenxia Wu, Deng Cai Robert Huitl, Georg Schroth, Sebastian Hilsenbeck, Florian Schweiger, Eckehard Steinbach 18. Sparsity Cue in Image Copy Detection 33. Detecting the Directions of Viewing Landmarks for Recommendation by Large-scale User- Huan-Cheng Hsu, Chun-Rong Huang, Chun-Shien Lu contributed Photos 19. Near-Duplicate Video Retrieval Based on Clustering by Multiple Sequence Alignment Yen-Ta Huang, Kuan-Ting Chen, Liang-Chi Hsieh, Winston Hsu, Ya-Fan Su Yandan Wang, Mohammed Belkhatir, Bashar Tahayna 34. Efficient Mobile Landmark Recognition Based on Saliency-Aware Scalable Vocabulary Tree 20. Neighborhood Preserving Hashing for Fast Similarity Search Kim-Hui Yap, Zhen Li, Da-Jiang Zhang, Zhan-Ke Ng Cong Liu, Hefei Ling, Fuhao Zou, Lingyu Yan 35. Client-side Backprojection of Presentation Slides into Educational Video 21. Face Photo Retrieval by Sketch Example Yekaterina Kharitonova, Qiyam Tung, Alexander Danehy, Alon Efrat, Kobus Barnard Hamed Kiani Galoogahi, Terence Sim 36. A Study on the User Perception to Color Variations 22. Geometric Context-Preserving Progressive Transmission in Mobile Visual Search Marco V. Bernardo, Antonio M.G. Pinheiro, Manuela Pereira, Paulo Torrão Fiadeiro Junhai Xia, Ke Gao, Dongming Zhang, Zhendong Mao 37. Parallel Deblocking Filtering in H.264/AVC using Multiple CPUs and GPUs Oct. 31 Oct. 31 23. Supervised Cross-collection Topic Modeling Bart Pieters, Charles Hollemeersch, Jan De Cock, Wesley De Neve, Peter Lambert, Rik Van de Walle Haidong Gao, Siliang Tang, Yin Zhang, Dapeng Jiang, Fei Wu, Yueting Zhuang 38. Energy-Aware Adaptations in Mobile 3D Graphics 24. PDSS: Patch-Descriptor-Similarity Space for Effective Face Verification Mohammad Hosseini, Alexandra Fedorova, Joseph Peters, Shervin Shirmohammadi Xiaohua Zhai, Yuxin Peng, Jianguo Xiao 39. ITEM: Immersive Telepresence for Entertainment and Meeting with Commodity Setup 25. Correlation-based burstiness for logo retrieval Viet Anh Nguyen, Tien Dung Vu, Hongsheng Yang, Jiangbo Lu, Minh N. Do Jerome Revaud, Matthijs Douze, Cordelia Schmid 40. Reducing Cross-Group Traffic with Cooperative Streaming Architecture Zhijie Shen, Roger Zimmermann 26. Large-Scale Simultaneous Multi-Object Recognition and Localization via Bottom Up Search-Based Approach 41. QoE-based Opportunistic Transmission for Video Broadcasting in Heterogeneous Circumstance Chun-Che Wu, Yin-Hsi Kuo, Winston Hsu Wen Ji, Zhu Li, Yiqiang Chen 27. Sketch-based Image Retrieval on Large Scale Database 42. ROI-Based Protection Scheme for High Definition Interactive Video Applications Rong Zhou, Liuli Chen, Liqing Zhang Kiana Calagari, Mohammad Reza Pakravan, Shervin Shirmohammadi 28. Dynamic Vocabularies for Web-based Concept Detection by Trend Discovery 43. Advanced Downlink LTE Radio Resource Management for HTTP-Streaming Damian Borth, Adrian Ulges, Thomas M. Breuel Thomas Wirth, Yago Sánchez, Bernd Holfeld, Thomas Schierl 29. Coherent Image Selection Using a Fast Approximation to the Generalized Traveling Salesman Problem Meng Wang, Prakash Ishwar, Janusz Konrad, Cenk Gazen, Rohit Saboo
76 77 Technical Demo Session 2 TD2 12:50–18:10 12. Use of Invisible Noise Signals to Prevent Privacy Invasion through Face Recognition from Session Chair: Qi Tian (University of Texas at San Antonio, US) Camera Images Location: Nara Prefectural New Public Hall, Foyer Takayuki Yamada, Seiichi Gohshi, Isao Echizen
1. Interactive Music Video Application for Smartphones Based on Free-viewpoint Video and 13. DVS: A Dynamic Multi-Video Summarization System of Sensor-rich Videos in Geo-Space Audio Rendering Ying Zhang, Roger Zimmermann Toshiharu Horiuchi, Hiroshi Sankoh, Tsuneo Kato, Sei Naito 14. Motch: An Automatic Motion Type Characterization System for Sensor-rich Videos 2. Abnormal Behavior Recognition System for ATM Monitoring by RGB-D Camera Guanfeng Wang, Beomjoo Seo, Roger Zimmermann Fan Liu, Jinhui Tang, Ruizhen Zhao, Zhenmin Tang 15. Hummi-Com: Humming-based Music Composition System 3. Interactive Photomosaic System Using GPU Tetsuo Kitahara, Syohei Kimura, Yuu Suzuki, Tomofumi Suzuki Makoto Fujisawa, Toshiyuki Amano, Takafumi Taketomi, Goshiro Yamamoto, Yuki Uranishi, Jun Miyazaki 4. PhacePhinder: Harnessing Social Networks to Build Social Face Databases for Mobile Devices Mark Bloess, Heung-Nam Kim, Abdulmotaleb El Saddik 5. Real-time Multiple Object Instances Detection Chengli Xie, Jinqiao Wang, Yifan Zhang, Hanqing Lu 6. One Shot Learning Gesture Recognition with Kinect Sensor Oct. 31 Oct. 31 Di Wu, Fan Zhu, Ling Shao, Hui Zhang 7. Interactive Exploration of Large Remote Image Databases William Plant, Gerald Shaeffer 8. Scenario-Driven Interactive Panorama Video Delivery: Promptly Watch and Share Enjoyable Parts of an Event Daisuke Ochi, Hideaki Kimata, Hajime Noto; Akira Kojima 9. MOGAT: A Cloud-based Mobile Game System with Auditory Training for Children with Cochlear Implants Yinsheng Zhou, Toni-Jan Keith Palma Monserrat, Ye Wang 10. A Domain-Specific Music Search Engine for Gait Training Zhonghua Li, Ye Wang 11. A Daily, Activity-Aware, Mobile Music Recommender System Xinxi Wang, Ye Wang, David Rosenblum
78 79 Video Program VP 12:50–18:10 Open Source Software Competition OSSC 14:20–15:50
Session Chair: Tao Mei (Microsoft Research Asia, CN) Session Chair: Masanori Sano (Japan Broadcasting Corporation (NHK), JP) Location: Nara Prefectural New Public Hall, Reception Hall Location: Nara Prefectural New Public Hall, Conference Room 2
1. A Real-Time System for Capturing HDR Videos 14:20–14:35 Bob: a Free Signal Processing and Machine Learning Toolbox for Researchers Benjamin Guthier, Stephan Kopf, Wolfgang Effelsberg Andre Anjos, Laurent El-Shafey, Roy Wallace, Manuel Guenther, Christopher McCool, Sebastien Marcel 2. High Dynamic Range (HDR) Video Image Processing for Digital Glass Raymond Chun Hing Lo, Steve Mann, Jason Huang, Valmiki Rampersad, Tao Ai 14:35–14:50 DisplayCast: a High Performance Screen Sharing System for Intranets Surendar Chandra, Lawrence A. Rowe 3. Immersive Multiplayer Tennis with Microsoft Kinect and Body Sensor Networks Suraj Raghuraman, Karthik Venkatraman, Zhanyu Wang, Jian Wu, Jacob Clements, Reza Lotfian, 14:50–15:05 UltraGrid: Low-Latency High-Quality Video Transmissions on Commodity Balakrishnan Prabhakaran, Xiaohu Guo, Roozbeh Jafari, Klara Nahrstedt Hardware Petr Holub, Jiri Matela, Martin Pulec, Martin Srom 15:05–15:20 Video Hyperlinking: Libraries and Tools for Threading and Visualizing Large Video Collection Lei Pang, Wei Zhang, Hung-Khoon Tan, Chong-Wah Ngo 15:20–15:35 XKin - eXtendable Hand Pose and Gesture Recognition Library for Kinect
Oct. 31 Fabrizio Pedersoli, Nicola Adami, Sergio Benini, Riccardo Leonardi Oct. 31
15:35–15:50 A Toolset for the Authoring, Simulation, and Rendering of Sensory Experiences Markus Waltl, Benjamin Rainer, Christian Timmerer, Hermann Hellwagner
80 81 Oral Session OS7 14:20–16:00 Oral Session OS8 14:20–16:00 Visual Search Human-centric Media
Session Chair: Qi Tian (University of Texas at San Antonio, US) Session Chair: Frank Nack (University of Amsterdam, NL) Location: Nara Prefectural New Public Hall, Noh Theater Location: Nara Prefectural New Public Hall, Conference Room 1
14:20–14:45 A Multimedia Analytics Framework for Browsing Image Collections in Digital Forensics 14:20–14:45 Don't Ask Me What I'm Like, Just Watch and Listen Marcel Worring, Andreas Engl, Camelia Smeria Ruchir Srivastava, Jiashi Feng, Sujoy roy, Shuicheng Yan, Terence Sim 14:45–15:10 Submodular Video Hashing: A Unified Framework towards Video Pooling and 14:45–15:10 Controlling Urban Lighting by Human Motion Patterns results from a full Indexing Scale Experiment Liangliang Cao, Zhenguo Li, Yadong Mu, Shih-Fu Chang Esben S. Poulson, Hans J. Anderson, Ole B. Jensen, Rikke Gade, Tobias 15:10–15:35 Exploratory Search of Long Surveillance Videos Thyrrestrup, Thomas B. Moesland Gregory D. Castanon, Andre L. Caron, Venkatesh Saligrama, Pierre-marc Jodoin 15:10–15:35 In the Eye of the Beholder: Employing Statistical Analysis and Eye Tracking 15:35–16:00 When Video Search Goes Wrong: Predicting Query Failure Using Search for Analyzing Abstract Paintings Engine Logs and Visual Search Results Victoria Yanulevskaya, Jasper Ujilings, Ella Bruni, Andreza Sartori, Elisa Zamboni, Christoph Kofler, Linjun Yang, Martha Larson, Tao Mei, Alan Hanjalic, Shipeng Li Francesca Bacci, David Melcher, Nicu Sebe 15:35–16:00 Online Crowdsourcing Subjective Image Quality Assessment Oct. 31 Oct. 31
Qianqian Xu, Qinming huang, Yuan Yao
82 83 Oral Session OS9 14:20–16:00 Oral Session OS10 16:30–17:45 Presentation and Organization Haptics
Session Chair: Heng Tao Shen (The University of Queensland, AU) Session Chair: Yuichi Nakamura (Kyoto University, JP) Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Location: Nara Prefectural New Public Hall, Noh Theater
14:20–14:45 Image Colorization Using Similar Images 16:30–16:55 Low Bitrate Source-filter Model Based Compression of Vibrotactile Texture Raj K. Gupta, Alex Y. Chia, Deepu Rajan, Ee S. Ng, Huang Zhiyong Signals in Haptic Teleoperation 14:45–15:10 Semi-Automated Magazine Layout Using Content-based Image Features Rahul Chaudhari, Burak Cizmeci, Katherine J. Kuchenbecker, Seungmoon Choi, Mikko Kuhna, Ida-Maria Kivelä, Pirkko Oittinen Eckehard Steinbach 15:10–15:35 Understanding Screen Contents for Building a High Performance, Real Time 16:55–17:20 Vibrotactile Feedback of Motor Performance Errors for Enhancing Motor Learning Screen Sharing System Troy L. McDaniel, Morris Goldberg, Shantanu Bala, Bijan Fakhri, Sethuraman Surendar chandra, Jacob T. Biehl, John Boreczky, Scott Carter, Lawrence A. Rowe Panchanathan 15:35–16:00 El-pincel - A Painter Cloud Service for Greener Web Pages 17:20–17:45 MOGAT: Mobile Games with Auditory Training for Children with Cochlear Implants Anand Bhojan, Lee Kee Chong, Ee-Chien Chang, Mun Choon Chan, Ananda L. Yinsheng Zhou, Khe Chai Sim, Patsy Tan, Ye Wang Akkihebbal, Wei-Tsang Ooi Oral Session OS11 16:30–18:10 Oct. 31 Oct. 31
Event Recognition Session Chair: Ansgar Scherp (University of Koblenz-Landau, DE) Location: Nara Prefectural New Public Hall, Conference Room 1
16:30–16:55 Visual Knowledge Transfer among Multiple Cameras for People Counting with Occlusion Handling Min-Fang Weng, Yen-Yu Lin, Nick C. Tang, Hong-yuan M. Liao 16:55–17:20 Leveraging High-Level and Low-Level Features for Multimedia Event Detection Lu Jiang, Alexander G. Hauptmann, Guang Xiang 17:20–17:45 Interactive Data-Driven Discovery of Temporal Behavior Models from Events In Media Streams Chreston Miller, Francis Quek 17:45–18:10 Knowledge Adaptation for Ad Hoc Multimedia Event Detection with Few Examplars Zhigang Ma, Yi Yang, Yang Cai, Nicu Sebe, Alexander G. Haptmann 84 85 Oral Session OS12 16:30-18:10 Noh Play 18:45-19:45 Semantic Tagging Location: Nara Prefectural New Public Hall, Noh Theater Session Chair: Lexing Xie (Australian National University, AU) Noh is a classical Japanese performance form that originates in the 14th century. Together with Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Kyogen, its dual art, it was listed as an "Intangible Cultural Heritage" by UNESCO in 2001.
16:30–16:55 Multi-View Learning from Imperfect Tagging Noh ( 能 ) literary means "skill" or "talent", and combines elements of dance, drama, Zhongang Qi, Ming Yang, Zhongfei (Mark) Zhang, Zhengyou Zhang music and poetry into one highly aesthetic stage art. 16:55–17:20 Joint Statistical Analysis of Images and Keywords with Applications in Semantic The professional artists, mainly men, have handed down the art among family Image Enhancement members for numerous generations. Albrecht Lindner, Appu Shaji, Nicolas Bonnier, Sabine Süsstrunk 17:20–17:45 Image Annotation by Semantic Sparse Recoding of Visual Content Title of the play: Hagoromo ( 羽衣 : The robe of feathers) The story has a wide circulation Wikipedia: Zhiwu Lu, Yuxin Peng all over the world as the "swan legend". http://en.wikipedia.org/ 17:45–18:10 Annotating Web Images using NOVA: NOn-conVex group spArsity wiki/Noh Players: Ryosuke Ido, Ryoichi Arimatsu, Ichikazu Sugi, Kichibei Hayashi, Yasuhiro Fei Wu, Ying Yuan, Yong Rui, Shuicheng Yan, Yueting Zhuang Ishii, Mitsunori Maegawa, Naoyoshi Umewaka, Kazuo Ido, Dai Hayashimoto, Masayuki Yamanaka, Tetsuro Imamura, Tomohiko Ueno, Yusuke Ueno, SIGMM Business Meeting 16:30-18:10 Oct. 31 Oct. 31
Yuichiro Umewaka Location: Nara Prefectural New Public Hall, Conference Room 2
The ACM Special Interest Group (SIG) in Multimedia (SIGMM) meets every year at the ACM Wikipedia: Multimedia conference for an annual business meeting. The goal is to inform all members of SIGMM http://en.wikipedia.org/ and all participants of the ACM Multimedia Conference 2012 about major achievements, initiatives, wiki/Hagoromo_(play) events, open issues that came up during the fiscal year of July 2011–June 2012, and about future directions that SIGMM is planning for the multimedia community. SIGMM open issues, future directions and bids for ACM Multimedia 2015 will be extensively discussed. We encourage all SIGMM members and participants of ACM MM'12 to attend the business meeting.
86 87 Nov. 1, 2012 Main Conference Day 3
09:00–10:00 14:15–15:55 Plenary Talk ………………………………………………………………………………………………………………………………………………………………………………PL6 ▶ 90 Oral Session: Image Analysis ……………………………………………………………………………………………………………………………………OS13 ▶ 101 Nara Prefectural Cultural Hall, International Hall Nara Prefectural New Public Hall, Conference Room 1 Decoding Visual Experience from the Human Brain Oral Session: Mobile Systems ……………………………………………………………………………………………………………………………………OS14 ▶ 101 Yukiyasu Kamitani (ATR Computational Neuroscience Laboratories, JP) Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Doctoral Symposium Best Paper Session …………………………………………………………………………………………………………DS1 ▶ 102 Nara Prefectural New Public Hall, Conference Room 2 10:00–12:00 Multimedia Grand Challenge Solutions …………………………………………………………………………………………………………………PL7 ▶ 91 Nara Prefectural Cultural Hall, International Hall 16:25–18:05 12:15–13:45 Oral Session: Image Content Analysis …………………………………………………………………………………………………………………OS15 ▶ 103 Multimedia Systems Journal Editorial Board Meeting (By invitation) Nara Prefectural New Public Hall, Conference Room 1 Todaiji Culture Center, Meeting Room A Oral Session: Social Media …………………………………………………………………………………………………………………………………………OS16 ▶ 104 Nara Prefectural New Public Hall, Conference Rooms 3 and 4 Doctoral Symposium Oral Paper Session ……………………………………………………………………………………………………………DS2 ▶ 105 12:45–18:05 (Core Time: 12:45–14:15） Nara Prefectural New Public Hall, Conference Room 2 Poster Session 3 ……………………………………………………………………………………………………………………………………………………………………PS3 ▶ 96 Nara Prefectural New Public Hall, Reception Hall ……………………………………………………………………………………………………………………………………………… 19:00–21:00 Technical Demo Session 3 TD3 ▶ 99 Conference Banquet ………………………………………………………………………………………………………………………………………………………… ▶ 106 Nov. 1 Nov. Nara Prefectural New Public Hall, Foyer 1 Nov.
Industrial Exhibits ………………………………………………………………………………………………………………………………………………………………IE ▶ 42 Hotel Nikko Nara, Hiten & Hagoromo Ballrooms Nara Prefectural New Public Hall, Reception Hall and Meeting Room 2 10:00–17:00
………………………………………………………………………………………… 12:45–18:05 Multimedia Art Exhibition 2012 Eternal / Moment ▶ 3 Todaiji Culture Center, Small Hall Doctoral Symposium Poster Session ………………………………………………………………………………………………………………………DSP ▶ 94 Nara Prefectural New Public Hall, Reception Hall
88 89 Plenary Talk PL6 09:00–10:00 Multimedia Grand Challenge Solutions PL7 10:00–12:00
Session Chair: Kiyoharu Aizawa (The University of Tokyo, JP) Session Chairs: Marcel Worring (University of Amsterdam, NL) Location: Nara Prefectural Cultural Hall, International Hall Yushi Jing (Google Research, US) Location: Nara Prefectural Cultural Hall, International Hall 09:00–10:00 Decoding Visual Experience from the Human Brain Yukiyasu Kamitani (ATR Computational Neuroscience Laboratories, JP) Visual-based Transmedia Events Detection See p.41 for details. Alexis Joly, Julien Champ, Pierre Letessier, Nicolas Hervé, Olivier Buisson, Marie-Luce Viaud Technicolor Challenge: An Event Classification Framework by Probabilistic Context Modeling of Multimodal Features Hsuan-Sheng Chen, Wen-Jiin Tsai TWIPIX: A Web Magazine Curated from Social Media Romil Bansal, Radhika Kumaran, Diwakar Mahajan, Arpit Khurdiya, Lipika Dey, Hiranmay Ghosh Multimedia News Digger on Emerging Topics from Social Streams Bing-Kun Bao, Weiqing Min, Jitao Sang, Changsheng Xu Analyzing Social Media via Event Facets Zhiyu Wang, Peng Cui, Lexing Xie, Hao Chen, Wenwu Zhu, Shiqiang Yang Automatic Cinemagraphs for Ranking Beautiful Scenes Yin-Tzu Chan, Hao-Chen Hsu, Po-Yi Li, Mei-Chen Yeh "Where is the Interestingness?" Retrieving Appealing Video Scenes by Learning Flickr-based Graded Judgments Miriam Redi, Bernard Merialdo Scaring or Pleasing: Exploit Emotional Impact of An Image Bing Li, Songhe Feng, Weihua Xiong, Weiming Hu Nov. 1 Nov. 1 Nov.
Classification of Photos based on Good Feelings Mathias Lux, Mario Taschwer, Oge Marques Understanding the Emotional Impact of Images Xiaohui Wang, Jia Jia, Peiyun Hu, Sen Wu, Jie Tang, Lianhong Cai Emotion-based Associative Sequence of Family Photos Vassilios Vonikakis, Stefan Winkler Evaluating User's Energy Consumption using Kinect Based Skeleton Tracking Zhenbao Liu, Sicong Tang, Hongliang Qin, Shuhui Bu
90 91 Core-Time for Posters, Technical Demos and Industrial Exhibits 12:45–14:15 Analysis of Dance Movements using Gaussian Processes Antoine Liutkus, Angelique Dremeau, Dimitrios Alexiadis, Slim Essid, Petros Daras Location: Nara Prefectural New Public Hall, Reception Hall and Foyer Automatic Music Soundtrack Generation for Outdoor Videos from Contextual Sensor Information Yi Yu, Zhijie Shen, Roger Zimmermann Each poster and technical demo session has a core-time. During the core-time, presenters will be available in front of their posters. The Acousticvisual Emotion Guassians Model for Automatic Generation of Music Video Each full paper (oral) presentation is also available as a poster for better interaction with the authors. Ju-Chiang Wang, Yi-Hsuan Yang, I-Hong Jhuo, Yen-Yu Lin, Hsin-Min Wang Automatic Music Video Generation: Cross Matching of Music and Image Xixuan Wu, Bing Xu, Yu Qiao, Xiaoou Tang MuseSync: Standing on the Shoulders of Hollywood Cynthia C. S. Liem, Alessio Bazzica, Alan Hanjalic Nov. 1 Nov. 1 Nov.
92 93 Doctoral Symposium Poster Session DSP 12:45–14:15 12. What You See Is What You Should Get Session Chairs: Chong-Wah Ngo (City University of Hong Kong, HK) Velibor Adzic Keiji Yanai (University of Electro-Communication, JP) Location: Nara Prefectural New Public Hall, Reception Hall 13. Challenges in Supporting Non-linear and Non-Continuous Media Access in P2P Systems Zhen Wei Zhao (Note: these posters will be displayed at this venue during all three main conference days.) 14. An Adaptive Framework for Scalable Multi-view Video Coding for the H.264/AVC Standard 1. People Search and Activity Mining in Large-Scale Community-Contributed Photos Hoda Roodaki Yan-Ying Chen 15. Distributed Video Coding with Improved Side Information Refinement and Parallelized 2. Upper Body Gestures in Lecture Videos: Indexing and Correlating to Pedagogical Significance Architecture Design John R. Zhang Yun-Chung Shen 3. Making Use of Eye Tracking Information in Image Collection Creation and Region Annotation 16. 3D Multimedia Signal Processing Tina Walber Yu-Hsun Lin 4. Investigating 3D Model and Part Information for Improving Content-based and Attribute- based Object Retrieval Yen-Liang Lin 5. Collective Search and Recommendation in Social Media Jitao Sang 6. Semantic Awareness for Automatic Image Interpretation Albrecht Lindner 7. Trajectory Signature for Action Recognition in Video Nicolas Ballas, Bertrand Delezoide, Françoise Prêteux 8. Interactive Data-Driven Search and Discovery of Temporal Behavior Patterns from Media Streams Nov. 1 Nov. 1 Nov.
Chreston Miller 9. Modeling Video Viewing Behaviors for Viewer State Estimation Ryo Yonetani 10. 3D Photo Browsing for Future Mobile Devices Shahrouz Yousefi 11. Spacetime Freeview Generation Using Image-based Rendering, Relighting, and Augmented Telepresence Fumio Okura
94 95 Poster Session 3 PS3 12:45–18:05 15. Breaking Row-Column Shuffle Based Image Cipher Session Chair: Sethuraman Panchanathan (Arizona State University, US) Weihai Li, Yupeng Yan, Nenghai Yu Location: Nara Prefectural New Public Hall, Reception Hall 16. On the Music Content Authentication Wei Li, Bilei Zhu, Zhurong Wang 1. Touch Saliency 17. Secure Cloud-based Medical Data Visualization Mengdi Xu, Bingbing Ni, Jian Dong, Zhongyang Huang, Meng Wang, Shuicheng Yan Manoranjan Mohanty, Pradeep Atrey, Wei Tsang Ooi 2. Robust Cross-Media Transfer for Visual Event Detection 18. State-based Steganography in Low Bit Rate Speech Yang Yang, Yi Yang, Zi Huang, Jiajun Liu, Zhigang Ma Ke Zhou, Jin Liu, Hui Tian, Chunhua Li 3. Predicting Human Activities using Spatio-Temporal Structure of Interest Points 19. Markov-based Image Forensics for Photographic Copying from Printed Picture Gang Yu, Junsong Yuan, Zicheng Liu Jing Yin, Yanmei Fang 4. Human Action Recognition and Retrieval Using Sole Depth Information 20. Secure Content Sharing for Social Network Using Fingerprinting and Encryption in the TSH Yan-Ching Lin, Min-Chun Hu, Wen-Huang Cheng, Yung-Huan Hsieh, Hong-Ming Chen Transform Domain 5. Recognizing Actions Using Depth Motion Maps-based Histograms of Oriented Gradients Conghuan Ye, Hefei Ling, Fuhao Zou, Cong Liu Xiaodong Yang, Chenyang Zhang, YingLi Tian 21. Conversationally-inspired Stylometric Features for Authorship Attribution in Instant Messaging 6. Activity-Based Person Identification Using Sparse Coding and Discriminative Metric Learning Marco Cristani, Giorgio Roffo, Cristina Segalin, Loris Bazzani, Alessandro Vinciarelli, Vittorio Murino Jiwen Lu, Junlin Hu, Xiuzhuang Zhou, Yuanyuan Shang 22. Dynamic Camera Calibration Method for Free-viewpoint Experience in Sport Videos 7. Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition Hiroshi Sankoh, Masaru Sugano, Sei Naito Tim Althoff, Hyun Oh Song, Trevor Darrell 23. Improving Dense Image Correspondence Estimation with Interactive User Guidance 8. A New Heat-Map-based Algorithm for Human Group Activity Recognition Kai Ruhl, Benjamin Hell, Felix Klose, Christian Lipski, Soeren Petersen, Marcus Magnor Hang Chu, Weiyao Lin, Jianxin Wu, Xingtong Zhou, Yuanzhe Chen, Hongxiang Li 24. Personalized Video Recommendation Through Tripartite Graph Propagation 9. Multimedia Event Recounting with Concept based Representation Bisheng Chen, Jingdong Wang, Qinghua Huang, Tao Mei Qian Yu, Jingen Liu, Hui Cheng, Ajay Divakaran, Harpreet Sawhney 25. Clothing Genre Classification by Exploiting the Style Elements 10. What is Happening: Annotating Images with Verbs Shintami C. Hidayati, Wen-Huang Cheng, Kai-Lung Hua Nov. 1 Nov. 1 Nov.
Gang Tian, Genliang Guan, Zhiyong Wang, Dagan Feng 26. AttachedShock: Facilitating Moving Targets Acquisition on Augmented Reality Devices using 11. Hybrid Generative-Discriminative Recognition of Human Action in 3D Joint Space Goal-crossing Actions Zhe Wu, Xiong Li, Xu Zhao, Yuncai Liu Chuang-Wen You, Yung-Huan Hsieh, Wen-Huang Cheng 12. Parsing Collective Behaviors by Hierarchical Model with Varying Structure 27. MixPad: Augmenting Interactive Paper with Mice & Keyboards for Cross-media and Fine- Cong Zhang, Xiaokang Yang, Jun Zhu, Weiyao Lin grained Interaction with Documents 13. Toward Next Generation Coaching Tools for Court Based Racquet Sports Xin Yang, Chunyuan Liao, Qiong Liu Damien Connaghan, Noel O'Connor 28. Detecting Rule of Simplicity from Photos 14. Predicting Participants in Public Events using Stock Photos Long Mai, Hoang Le, Yuzhen Niu, Yu-Chi Lai, Feng Liu Neil O'Hare, Luca Maria Aiello, Alejandro Jaimes 96 97 Technical Demo Session 3 TD3 12:45–18:05 29. An Approach to Automatic Construction of Cinemagraphs Mei-Chen Yeh, Po-Yi Li Session Chair: Hirokazu Kato (NAIST, JP) 30. Human-Computer Dance Interaction with Realtime Accelerometer Control Location: Nara Prefectural New Public Hall, Foyer Takuya Yasunaga, Atsushi Nakazawa, Haruo Takemura 31. Robust AAM-Based Audio-Visual Speech Recognition against Face Direction Changes 1. Browse-to-Search Yuto Komai, Nan Yang, Tetsuya Takiguchi, Yasuo Ariki Shiyang Lu, Tao Mei, Jingdong Wang, Jian Zhang, Zhiyong Wang, David D. Feng, Jian-Tao Sun, Shipeng Li 32. A Study on Making Camera Trajectory from Panorama Watching Manipulation 2. Scalable Similar Image Search by Joint Indices Daisuke Ochi, Hideaki Kimata, Hajime Noto, Akira Kojima Jing Wang, Jingdong Wang, Xian-Sheng Hua, Shipeng Li 33. Drive Video Summarization based on Double Articulation Structure of Driving Behavior 3. Color Filter for Image Search Kazuhito Takenaka, Takashi Bando, Shogo Nagasaka, Tadahiro Taniguchi Peng Wang, Dongqing Zhang, Jingdong Wang, Zhong Wu, Xian-Sheng Hua, Shipeng Li 34. Interactive Multimodal Social Robot for Improving Quality of Care of Elderly in Australian 4. StoViz : Story Visualization of TV Series Nursing Homes Philippe Ercolessi, Hervé Bredin, Christine Sénac Rajiv Khosla, Mei-Tai Chu, Reza Kachouie, Keiji Yamada, Fujita Yoshihiro, Tomoharu Yamaguchi 5. 3DME: 3D Media Express from RGB-D Images 35. Plug&Touch: A Mobile Interaction Solution for Large Display via Vision-Based Hand Gesture Tam V. Nguyen, Lusong Li, Jun Tan, Shuicheng Yan Detection 6. "Hi, Magic Closet, Tell Me What to Wear!" Lei Xu, Yikai Fang, Kongqiao Wang, Jiangwei Li Si Liu, Tam V. Nguyen, Jiashi Feng, Meng Wang, Shuicheng Yan 36. Ulcer Detection in Wireless Capsule Endoscopy Videos Yingju Chen, Jeongkyu Lee 7. Street-to-Shop: Cross-Scenario Clothing Retrieval via Parts Alignment and Auxiliary Set Si Liu, Zheng Song, Meng Wang, Changsheng Xu, Hanqing Lu, Shuicheng Yan 37. Critical Gameplay: Designing Games to Critique Convention Lindsay D. Grace 8. Searching for Diversified Landmarks by Photo Junfeng Ye, Jia Chen, Zejia Chen, Yihe Zhu, Shenghua Bao, Zhong Su, Yong Yu 38. Smooth and Efficient Crowd Transformation Mingliang Xu, Yunpeng Wu, Yangdong Ye 9. Attribute Feedback Hanwang Zhang, Zheng-jun Zha, Jingwen Bian, Yue Gao, Huanbo Luan, Tat-seng Chua Nov. 1 Nov. 1 Nov.
39. Augmented Reality Card Game based on User-specific Information Control
Seiko Myojin, Arata Sato, Nobutaka Shimada 10. Personal Photo Indexing 40. Indoor and Outdoor Profiling of Users in Multimedia Installations Ivan Tankoyeu, Julian Stöttinger, Javier Paniagua, Fausto, Giunchiglia Gianpaolo D'Amico, Alberto Del Bimbo, Andrea Ferracani, Lea Landucci, Daniele Pezzatini 11. Guess What You Draw: Interactive Contour-based Image Retrieval on a Million-Scale Database 41. Digiti Sonus: An Interactive Fingerprint Sonification Rong Zhou, Liuli Chen, Liqing Zhang Yoon Chung Han, Byeong-jun Han 12. FashionAsk: Pushing Community Answers to Your Fingertips 42. Extending the Life Log to Non-human Subjects: Ambient Storytelling for Human-Object Wei Zhang, Lei Pang, Chong-wah Ngo Relationships Joshua McVeigh-Schultz, Jen Stein, Jeff Watson, Scott Fisher 13. A Fast Video Event Recognition System and Its Application to Video Search Yu-Gang Jiang, Qi Dai, Yin bing Zheng, Xiangyang Xue, Jie Liu, Dong Wang 98 99 Oral Session OS13 14:15–15:55 14. Social and Automatic Annotation of Videos for Semantic Profiling and Content Discovery Marco Bertini, Alberto Del Bimbo, Andrea Ferracani, Daniele Pezzatini Image Analysis Session Chair: Shuicheng Yan (National University of Singapore, SG) Location: Nara Prefectural New Public Hall, Conference Room 1
14:15–14:40 Query-Adaptive Shape Topic Mining for Hand-Drawn Sketch Recognition Zhenbang Sun, Changhu Wang, Liqing Zhang, Lei Zhang 14:40–15:05 Correlated Attribute Transfer with Multi-task Graph-Guided Fusion Yahong Han, Fei Wu, Xinyan Lu, Qi Tian, Yueting Zhuan, Jiebo Luo 15:05–15:30 Spatial Pooling of Heterogeneous Features for Image Applications Lingxi Xie, Qi Tian, Bo Zhang 15:30–15:55 Efficient Image Annotation for Automatic Sentence Generation Yoshitaka Ushiku, Tatsuya Harada, Yasuo Kuniyoshi
Oral Session OS14 14:15–15:55 Mobile Systems Session Chair: Tao Mei (Microsoft Research Asia, CN) Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4
14:15–14:40 Dinner of Luciérnaga-An interactive Play with iPhone App in Theater Nov. 1 Nov. 1 Nov.
Yu-Chuan Tseng, Yi-Ching Huang, Kuan-Ying Wu, Chi-Ping Ching 14:40–15:05 Accelerating SURF Detector on Mobile Devices Xin Yang, Kwang-ting (Tim) Cheng 15:05–15:30 IMShare: Instantly Sharing Your Mobile Images by Search-based Reconstruction Lican Dai, Huanjing Yue, Xiaoyan Sun, Feng Wu 15:30–15:55 Discovering and Ranking Areas of Interest with Geo-tagged Images and Check-ins Jiajun Liu, Zi Huang, Lei Chen, Heng Tao Shen, Zhixian Yan
100 101 Doctoral Symposium Best Paper Session DS1 14:15–15:55 Oral Session OS15 16:25–18:05 Session Chairs: Chong-Wah Ngo (City University of Hong Kong, HK) Image Content Analysis Keiji Yanai (University of Electro-Communication, JP) Location: Nara Prefectural New Public Hall, Conference Room 2 Session Chair: Winston Hsu (National Taiwan University, TW) Location: Nara Prefectural New Public Hall, Conference Room 1 14:15–14:40 People Search and Activity Mining in Large-Scale Community-Contributed Photos Yan-Ying Chen 16:25–16:50 Scalable Mining of Small Visual Objects Pierre Letessier, Olivier Buisson, Alexis Joly 14:40–15:05 Upper Body Gestures in Lecture Videos: Indexing and Correlating to Pedagogical Significance 16:50–17:15 Snap-and-Ask: Answering Multimodal Question by Naming Visual Instance John R. Zhang Wei Zhang, Lei Pang, Chong-Wah Ngo 15:05–15:30 Modeling Video Viewing Behaviors for Viewer State Estimation 17:15–17:40 “Hi, Magic Closet, Tell Me What to Wear!” Ryo Yonetani Si Liu, Jiashi Feng, Zheng Song, Tianzhu Zhang, Hanqing Lu, Changsheng Xu, Shuicheng Yan 15:30–15:55 Challenges in Supporting Non-linear and Non-Continuous Media Access in P2P Systems 17:40–18:05 Constraint-Optimized Keypoint Inhibition/Insertion Attack: Security Threat Zhen Wei Zhao to Scale-Space Image Feature Extraction Chun-Shien Lu, Chao-Yung Hsu Nov. 1 Nov. 1 Nov.
102 103 Oral Session OS16 16:25–18:05 Doctoral Symposium Oral Paper Session DS2 16:25–18:05 Social Media Session Chairs: Chong-Wah Ngo (City University of Hong Kong, HK) Keiji Yanai (University of Electro-Communication, JP) Session Chair: Bernard Merialdo (Institut EURECOM, FR) Location: Nara Prefectural New Public Hall, Conference Room 2 Location: Nara Prefectural New Public Hall, Conference Rooms 3 and 4 16:25–16:45 3D Photo Browsing for Future Mobile Devices 16:25–16:50 Mining In-Class Social Networks for Large-Scale Pedagogical Analysis Shahrouz Yousefi Xiao-Yong Wei, Zhen-Qun Yang 16:45–17:05 Making Use of Eye Tracking Information in Image Collection Creation and 16:50–17:15 SocialTransfer: Cross-Domain Transfer Learning from Social Streams for Region Annotation Media Applications Tina Walber Suman D. Roy, Tao Mei, Wenjun Zeng, Shipeng Li 17:05–17:25 Investigating 3D Model and Part Information for Improving Content-based 17:15–17:40 Hybrid Social Media Network and Attribute-based Object Retrieval Dong Liu, Guangnan Ye, Ching-Ting Chen, Shuicheng Yan, Shih-Fu Chang Yen-Liang Lin 17:40–18:05 Discovering Informative Social Subgraphs and Predicting Pairwise 17:25–17:45 An Adaptive Framework for Scalable Multi-view Video Coding for the H.264/ Relationships from Group Photos Yan-Ying Chen, Winston H. Hsu, Hong-Yuan M. Liao AVC Standard Hoda Roodaki 17:45–18:05 Distributed Video Coding with Improved Side Information Refinement and Parallelized Architecture Design Yun-Chung Shen Nov. 1 Nov. 1 Nov.
104 105 Conference Banquet 19:00–21:00 Nov. 2, 2012 Workshops Location: Hotel Nikko Nara, Hiten & Hagoromo Ballrooms (see p.4) 09:00–17:00 Workshop MIRUM 2nd International ACM Workshop on Music Information Retrieval Only for participants registered under regular registration or those who have purchased banquet with User-Centered and Multimodal Strategies (MIRUM 2012) ……………………………… ▶ 108 tickets. Nara Prefectural New Public Hall, Conference Room 3 Shuttle buses are available (see p.19). Workshop MAED 1st ACM International Workshop on Multimedia Analysis for Ecological Data (MAED 2012) ……………………………………………………………………………………………………………………………………… ▶ 110 Todaiji Culture Center, Gold Bell Hall 09:00–12:30 Workshop CBMAS-EH 1st ACM Multimedia Workshop on Cloud-Based Multimedia Applications and Services for E-Health (CBMAS-EH 2012) ……………………………………………………………………… ▶ 113 Nara Prefectural New Public Hall, Conference Room 1 Workshop UXeLATE 1st ACM International Workshop on User Experience in e-Learning and Augmented Technologies in Education (UXeLATE 2012) ……………………………………………… ▶ 115 Nara Prefectural New Public Hall, Conference Room 2 09:00–12:45 Workshop AMVA 1st ACM International Workshop on Audio and Multimedia Methods for Large Scale Video Analysis (AMVA 2012) ………………………………………………………………………………… ▶ 117 Nara Prefectural New Public Hall, Noh Theater 09:00–13:00 Workshop PATCH Personalized Access to Cultural Heritage: Multimedia by the Crowd, for the Crowd (PATCH 2012) …………………………………………………………………………………………………………………… ▶ 119 Nara Prefectural New Public Hall, Conference Room 4 13:30–17:00 GeoMM
Nov. 1 Nov. Workshop 1st ACM International Workshop on Geotagging and Its Applications in
Multimedia (GeoMM 2012) ……………………………………………………………………………………………………………… ▶ 120 Nara Prefectural New Public Hall, Noh Theater Workshop IMMPD The 2nd ACM International Workshop on Interactive Multimedia on Mobile and Portable Devices (IMMPD 2012) ………………………………………………………………………… ▶ 122 Nara Prefectural New Public Hall, Conference Room 1 Workshop CEA The 4th Workshop on Multimedia for Cooking and Eating Activities (CEA 2012) …▶ 124 Nara Prefectural New Public Hall, Conference Room 4 Nov. 2 Nov.
10:00–17:00 Multimedia Art Exhibition 2012 Eternal / Moment ………………………………………………………………………………………… ▶ 3 Todaiji Culture Center, Small Hall 106 107 Full-day Workshop MIRUM 09:00–17:00 11:10–11:30 Learning and Extraction of Violin Instrumental Controls from Audio Signal Alfonso Perez Carrillo, Marcelo M. Wanderley 2nd International ACM Workshop on Music Information Retrieval with 11:35–11.55 Inferring Personal Traits from Music Listening History User-Centered and Multimodal Strategies Jen-yu Liu, Yi-Hsuan Yang (MIRUM 2012) 12:00–12:20 Who Influence the Music Tastes of Adolescents? A Study on Interpersonal Influence in Social Networks Workshop Chairs: Cynthia C. S. Liem (Delft University of Technology, NL) Audrey Laplante Meinard Müller (University of Bonn & MPI Informatik, DE) 12:20–13:30 Lunch Steven K. Tjoa (iZotope, Inc., US) George Tzanetakis (University of Victoria, CA) Session 3 Location: Nara Prefectural New Public Hall, Conference Room 3 Session Chair: Steven K. Tjoa (iZotope, Inc., US) 13:30–15:15
Session 1 13:30–14:30 Keynote address Session Chair: Takuya Fujishima (Yamaha Corporation, JP) When Music, Information Technology, and Medicine Meet 09:00–10:15 Ye Wang 14:30–14:50 Perceptual Tempo Estimation using GMM-Regression 09:00–09:05 Welcome and opening remarks Geoffroy Peeters, Joachim Flocon-Cholet Cynthia C. S. Liem 14:55–15:15 Novelty Measures as Cues for Temporal Salience in Audio Similarity 09:05–09:25 Fast Intra-Collection Audio Matching Mark B. Cartwright, Bryan Pardo Verena Thomas, Sebastian Ewert, Michael Clausen 15:15–15:45 Coffee Break 09:30–09:50 An Analysis of the GTZAN Music Genre Dataset Bob L. Sturm Session 4 09:55–10:15 Building a Personalized Audio Equalizer Interface with Transfer Learning Session Chair: Masataka Goto (AIST, JP) and Active Learning 15:45–17:00 Bryan Pardo, David Little, Darren Gergle 10:15–10:45 Coffee Break 15:45–16:05 Personalized Music Emotion Classification via Active Learning Dan Su, Pascale Fung Session 2 16:10–16:30 Exploring the Relationship between Categorical and Dimensional Emotion Session Chair: Cynthia C. S. Liem (Delft University of Technology, NL) Semantics of Music 10:45–12:20 Ju-Chiang Wang, Yi-Hsuan Yang, Kaichun Chang, Hsin-Min Wang 16:35–16:55 Two Systems for Automatic Music Genre Recognition: What Are They Really Recognizing?
Nov. 2 Nov. Bob L. Sturm 2 Nov. 10:45–11:05
Knowledge-based Music Retrieval for Places of Interest Marius Kaminskas, Ignacio Fernández-Tobías, Francesco Ricci, Iván Cantador 16:55–17:00 Closing remarks Steven K. Tjoa 108 109 Full-day Workshop MAED 09:00–17:00 11:15–11:45 Identification of Great Apes Using Gabor Features and Locality Preserving Projections 1st ACM International Workshop on Multimedia Analysis for Ecological Data Alexander Loos (MAED 2012) 11:45–12:15 Texture Recognition for Frog Identification Flavio Cannavò, Giuseppe Nunnari, Izzet Kale, F. Boray Tek Workshop Chairs: Concetto Spampinato (University of Catania, IT) 12:15–12:45 Event Detection in Underwater Domain by Exploiting Fish Trajectory Clustering Vasileios Mezaris (Centre for Research and Technology Hellas, GR) Simone Palazzo, Concetto Spampinato, Cigdem Beyan Jacco von Ossenbruggen (CWI, NL) Location: Todaiji Culture Center, Gold Bell Hall 12:45–13:30 Lunch
Keynote Address 09:00–09:15 Welcome Session Chair: Vasileios Mezaris (Centre for Research and Technology Hellas, GR) Concetto Spampinato Vasileios Mezaris 13:30–14:30 Multimedia Challenges in Sensing the Environment Alan Smeaton Session 1: Environment monitoring and habitat classification Session Chair: Concetto Spampinato (University of Catania, IT) Session 3: Short Paper/Poster Session 09:15–10:45 Session Chair: Concetto Spampinato (University of Catania, IT) 14:30–16:45 09:15–09:45 Grass, Scrub, Trees and Random Forest Mercedes Torres, Guoping Qiu 14:30–15:00 Spotlight presentations of Short Papers 09.45–10:15 Visibility Cameras: Where and How to Look Authors of short papers will present a 1-slide, 5-minute talk to advertise their poster. Nathan Graves, Shawn Newsam 15:00–15:30 Coffee Break 10:15–10:45 Environmental Data Extraction from Multimedia Resources 15:30–16:45 Poster presentation of Short Papers Anastasia Moumtzidou, Victor Epitropou, Stefanos Vrochidis, Sascha Voth, Anastasios Bassoukos, Kostas Karatzas, Jürgen Moßgraber, Ioannis Kompatsiaris, Ari Karppinen, Jaakko Kukkonen 1. Plant Leaves Morphological Categorization with Shared Nearest Neighbours Clustering 10:45–11:15 Coffee Break Hamzaoui Amel, Alexis Joly, Hervé Goëau 2. Multi-organ plant identification Session 2: Animal identification and behavior-based event detection Hervé Goëau, Pierre Bonnet, Julien Barbe, Vera Bakic, Alexis Joly, Jean-François Molino, Daniel Session Chair: Vasileios Mezaris (Centre for Research and Technology Hellas, GR) Barthélémy, Nozha Boujemaa
Nov. 2 Nov. 11:15–12:45 3. A Semantic Based Retrieval System of Arctic Animal Images 2 Nov.
Carmelo Pino, Daniela Giordano, Giuseppe Santoro
110 111 Half-day Workshop CBMAS-EH 09:00–12:30 4. An Environmental Search Engine based on Interactive Visual Classification Stefanos Vrochidis, Harald Bosch, Anastasia Moumtzidou, Florian Heimerl, Thomas Ertl, Ioannis 1st ACM Multimedia Workshop on Cloud-Based Multimedia Applications Kompatsiaris and Services for E-Health 5. A Visual Sensing Platform for Creating A Smarter Multi-Modal Marine Monitoring Network (CBMAS-EH 2012) Dian Zhang, Edel O'Connor, Kevin McGuinness, Noel Edward O'Connor, Fiona Regan, Alan Smeaton Workshop Chairs: Mohammed Shamim Hossain (King Saud University, SA) Abdulmotaleb El Saddik (University of Ottawa, CA) 6. Quantitative Performance Analysis of Object Detection Algorithms on Underwater Video Location: Footage Nara Prefectural New Public Hall, Conference Room 1 Isaak Kavasidis, Simone Palazzo
09:00–09:05 Welcome 16:45–17:00 Concluding Remarks Abdulmotaleb El Saddik Concetto Spampinato, Vasileios Mezaris 09:05–09:55 Keynote Cloud-based Games for Health – Serious Games and Social Media as Multimedia Technologies for Healthcare Dr.-Ing. Stefan Göbel 09:55–10:15 An Efficient Block Classification for Multimedia Service in Mobile Cloud Computing An Thuy Nguyen, Tien-Dung Nguyen, Seungkon Ko, Eui-Nam Huh 10:15–10:45 Coffee Break
Session 1: Cloud media technologies for health care Session Chair: Mohammed Shamim Hossain (King Saud University, SA) 10:45–12:30
10:45–11:10 Differential Time-shared Virtual Machine Multiplexing for Handling QoS Variation in Clouds Md.Mahfuzur Rahman, Ruppa Thulasiram, Peter Graham 11:10–11:35 A Cloud-Based Serious Games Framework for Obesity Mohammad Mehedi Hassan, M. Shamim Hossain, Atif Alamri, Mohammed Anwar Hossain, Muhammad Al-Qurishi, Yousuf Aldukhayyil, Dewan Tanvir Ahmed Nov. 2 Nov. 2 Nov.
11:35–12:00 2D to 3D Video Conversion Based on Color Segmentation and High Quality Motion Information Yu Zhang, Xuezhi Xiang, Jiying Zhao 112 113 Half-day Workshop UXeLATE 09:00–12:30 12:00–12:25 Hiding Depth Information into H.264 Compressed Video Using Reversible Watermarking 1st ACM International Workshop on User Experience in e-Learning Wenyi Wang, Jiying Zhao, Wa James Tam, Filippo Speranza and Augmented Technologies in Education 12:25–12:30 Concluding Remarks (UXeLATE 2012) Mohammed Shamim Hossain Workshop Chair: David Fonseca Escudero (La Salle University, ES) Location: Nara Prefectural New Public Hall, Conference Room 2
09:00–09:05 Welcome David Fonseca Escudero 09:05–09:45 Keynote Person-Centered Accessible Technologies: Improved Usability and Adaptation through Inspirations from Disability Research. Sethuraman Panchanathan
Session 1: Oral Session: Session Chair: M. Shamim Hossain (King Saud University, SA) 09:45–10:25 09:45–10:05 WikiNect: Towards a Gestural Writing System for Kinetic Museum Wikis Alexander Mehler, Andy Lücking 10:05–10:25 Arm Gesture Variations during Presentations are Correlated with Conjunctions Indicating Contrast John Zhang, John Kender 10:25–10:55 Coffee Break
Session 2: Oral Session: Session Chair: M. Shamim Hossain (King Saud University, SA) 10:55–12:30 10:55–11:15 Joint Spaces Between Schools and Museums via Virtual Worlds. A Case Atudy Luis A. Hernandez Ibañez, Viviana Barneche Nay Nov. 2 Nov. 2 Nov.
11:15–11:35 Emergency Medicine Training with Gesture Driven Interactive 3D Simulations Giovanna Bartoli, Alberto Del Bimbo, Martino Faconti, Andrea Ferracani, Daniele Pezzatini, Lorenzo Seidenari, Felipe Zilleruelo 114 115 Half-day Workshop AMVA 09:00–12:45 11:35–11:55 Glooveth: Healthy Living with an Innovative Gameplay Enric Macías López, Oscar García Pañella, Emiliano Labrador, Pau Moreno Font, 1st ACM International Workshop on Audio and Multimedia Methods Maria Montserrat Presno for Large Scale Video Analysis 11:55–12:15 Developing an Augmented Reality application in the framework of Architecture (AMVA 2012) Degree (INVITED PAPER) Albert Sanchez, Ernest Redondo, David Fonseca Workshop Chairs: Gerald Friedland (ICSI / UC Berkeley, US) 12:15–12:30 Concluding Remarks and Discussion Time Daniel P. W. Ellis (Columbia University, US) Florian Metze (CMU, US) Albert Sánchez, David Fonseca Escudero Location: Nara Prefectural New Public Hall, Noh Theater Notes: URL: http://amva2012.icsi.berkeley.edu
09:00–09:05 Welcome Gerald Friedland 09:05–09:50 Keynote Speech Technology Plays a Key Role in Video Semantic Indexing Koichi Shinoda
Session 1: Audio Approaches Session Chair: Gerald Friedland (ICSI / UC Berkeley, US) 10:00–11:10
10:00–10:20 Hierarchical Framework for Plot De-interlacing of TV Series Based on Speakers, Dialogues and Images Philippe Ercolessi, Christine Senac, Sandrine Mouysset, Hervé Bredin 10:25–10:45 Supervised Acoustic Concept Extraction for Multimedia Event Detection Stephanie L. Pancoast, Murat Akbacak, Michelle H. Sanchez 10:50–11:10 Short User-generated Videos Classification Using Accompanied Audio Categories Jinlin Guo, Cathal Gurrin Nov. 2 Nov. 2 Nov.
11:10–11:30 Coffee Break
116 117 Half-day Workshop PATCH 09:00–13:00 Session 2: Multimedia Approaches Session Chair: Gerald Friedland (ICSI / UC Berkeley, US) Personalized Access to Cultural Heritage: Multimedia by the Crowd, 11:30–12:15 for the Crowd (PATCH 2012) 11:30–11:50 Pornography Detection in Video Benefits (a lot) from a Multi-modal Approach Adrian Ulges, Christian Schulze, Damian Borth, Armin Stahl Workshop Chairs: Johan Oomen (Netherlands Institute for Sound and Vision, NL) 11:55–12:15 There is No Data Like Less Data: Percepts for Video Concept Detection on Lora Aroyo (VU University Amsterdam, NL) Consumer-Produced Media Stéphane Marchand-Maillet (University of Geneva, CH) Benjamin Elizalde, Gerald Friedland, Howard Lei, Ajay Divakaran Jeremy Douglass (U. California San Diego, US) Location: Nara Prefectural New Public Hall, Conference Room 4 Notes: Twitter tag #patch2012 Session 3: Audio Analysis for Consumer and other Industrial Applications Session Session Chair: Ajay Divakaran (SRI / Sarnoff, US) Welcome 12:15–12:45 09:15–09:20 Workshop Chiars Panelists: Malcolm Slaney (Microsoft Conversational Systems Laboratory, US) Martha Larson, (TU Delft, NL) 09:20–09.50 Mobile Augmented Reality for Interpretation of Archaeological Sites Rozhen Kamal Mohammed-Amin, Richard M. Levy, Jeffrey Edwin Boyd Yasushi Ishikawa, (Mitsubishi Electric, JP) 10:00–10:30 Space-38: New Media Heritage Place for the Unification of South and North Korea Gi Sook Oh, Doo Young Kwon 10:30–11:00 Attracting Individuals and Crowds with Multimedia and a Virtual Artifact During a Museum at Night Ewa Lukasik 11:00–11:15 Coffee Break 11.15–11.45 Augmented Reality for Virtual Renovation Liraz Mor, Richard M. Levy, Jeffrey Edwin Boyd 11.45–12.15 Linked Television Heritage Vassilis Tzouvaras, Jean-Pierre Evain, Nikolaos Simou, Athanasios Drosopoulos 12.15–12.45 Significance of Visual Interfaces in Institutional and User-Generated Databases with Category Structures Alkim Almila Akdag Salah, Andrea Scharnhorst, Olav ten Bosch, Peter Doorn, Lev Nov. 2 Nov. 2 Nov.
Manovich, Albert Salah, Jay Chow 12.45–13.00 Antiques Interactive Lotte Belice Baltussen, Johan Oomen 118 119 Half-day Workshop GeoMM 13:30–17:00
1st ACM International Workshop on Geotagging and Its Applications 2. Sight Surfers: 360º Videos and Maps Navigation in Multimedia Gonçalo Noronha, Carlos Álvares, Teresa Chambe (GeoMM 2012) 3. The Movie Mashup Application MoMa: Geolocalizing and Finding Movies Jean-Marc Finsterwald, Gregory Grefenstette, Julien Law-To, Hugues Bouchard, Amar-Djalil Workshop Chairs: Liangliang Cao (IBM Watson Research Center, US) Mezaour Gerald Friedland (International Computer Science Institute, US) Martha Larson (Delft University of Technology, NL) 15:00–15:15 Coffee Break Location: Nara Prefectural New Public Hall, Noh Theater 15:15–15:40 Invited talk: Geo-Locating photos and Videos over Urban and natural Terrain Hui Chen 13:30–13:35 Welcome Liangliang Cao Session 3: Oral Session: Geotags and People 15:40–16:20 13:35–14:00 Keynote State of the Geotag: Where Are We? 15:40–16:00 Adam Rae Find You Wherever You Are: Geographic Location and Environment Context- Based Pedestrian Detection Yuan Liu, Zhongchao Shi, Gang Wang, Haike Guan Session 1: Oral Session: New Perspectives on Places 14:00–14:40 16:00–16:20 Gender-based Models of Location from Flickr Neil O'Hare, Vanessa Murdock 14:00–14:20 Exploring Geotagged Images for Land-Use Classification 16:20–16:30 Coffee break Daniel Leung, Shawn Newsam 14:20–14:40 Conjunctive Ranking Function using Geographic Distance and Image Distance Session 4: Panel: Future of GeoTagged Multimedia for Geotagged Image Retrieval 16:30–17:00 Junzo Kamahara, Takashi Nagamatsu, Naoki Tanaka 17:00 Concluding Remarks Session 2: Poster session: Geolocations and Applications 14:40–15:00
1. Toponym-based Geotagging for Observing Precipitation from Social and Scientific Data Streams
Nov. 2 Nov. Asanobu Kitamoto, Takeshi Sagara 2 Nov.
120 121 Half-day Workshop IMMPD 13:30–17:00 Session 2: Oral Session 2 The 2nd ACM International Workshop on Interactive Multimedia on Session Chair: Minoru Etoh (NTT DOCOMO, JP) Mobile and Portable Devices 16:00–17:00 (IMMPD 2012) 16:00–16:20 Mining for Motivation: Using a Single Wearable Accelerometer to Detect People’s Workshop Chairs: Ling Shao (The University of Sheffield, UK) Interests Caifeng Shan (Philips Research, NL) Gwenn Englebienne, Hayley Hung Minoru Etoh (NTT DOCOMO, JP) 16:20–16:40 Real-time Mobile Recipe Recommendation System Using Food Ingredient Location: Nara Prefectural New Public Hall, Conference Room 1 Recognition Takuma Maruyama, Yoshiyuki Kawano, Keiji Yanai Detailed Program: 16:40–17:00 Effective Browsing of Long Audio Recordings Camille Goudeseune 13:30–13:35 Welcome Minoru Etoh 13:35–14:30 Keynote Emerging Challenges and Opportunities in Exploiting Mobile Photos and Videos Winston Hsu
Session 1: Oral Session 1 Session Chair: Minoru Etoh (NTT DOCOMO, JP) 14:30–15:30
14:30–14:50 Enabling Portable Animation Browsing by Transforming Animations into Comics Wei-Ta Chu, Hsing-Han Wang 14:50–15:10 Error-tolerant Interactive Image Segmentation by Using Dynamic and Iterated Graph-Cuts Ozan Sener, Kemal Ugur, A. Aydin Alatan 15:10–15:30 Augmented Poselets for Human Body Pose Inference by a Probabilistic Graphical Model Pol Cirujeda, Xavier Binefa 15:30–16:00 Coffee Break Nov. 2 Nov. 2 Nov.
122 123 Half-day Workshop CEA 13:30–17:00 Session 2: Poster session The 4th Workshop on Multimedia for Cooking and Eating Activities Session Chair: Yoko Yamakata (Kyoto University, JP) (CEA 2012) 15:00–16:00
Workshop Chairs: Mutsuo Sano (Osaka Institute of Technology, JP) 1. Cooking Rehabilitation Support for Self-reliance of Cognitive Dysfunction Patients Ichiro Ide (Nagoya University, JP) Miyawaki Kenzaburo, Mutsuo Sano Yoko Yamakata (Kyoto University, JP) 2. Table Talk Enhancer: A Tabletop System for Enhancing and Balancing Mealtime Conversations Takuya Funatomi (Kyoto University, JP) using Utterance Rates Kenzaburo Miyawaki (Osaka Institute of Technology, JP) Kyohei Ogawa, Yukari Hori, Toshiki Takeuchi, Takuji Narumi, Tomohiro Tanigawa, Michitaka Hirose Kazuaki Kondo (Kyoto University, JP) 3. Influences of a Robot’s Presence and Speeches in a Cooking Support System Location: Nara Prefectural New Public Hall, Conference Room 4 Yu Suzuki, Haruka Shinkou, Hirotada Ueda Notes: URL: http://www.ccm.media.kyoto-u.ac.jp/CEA2012/ 4. Cooking Gesture Recognition Using Local Feature and Depth Image Detailed Program: Yanli Ji, Yoshiyasu Ko, Atsushi Shimada, Hajime Nagahara, Rin-ichiro Taniguchi 5. Food Menu Selection Support System: Considering Constraint Conditions for Safe Dietary Life 13:30–13:40 Opening Session Kayo Iizuka, Takuya Okawada, Kouki Matsuyama, Sui Kurihashi, Yasuki Iizuka Mutsuo Sano 6. BioloGeek, An Intelligent System for Service Mashups Tuned for Recipe Processing and Rendering Mariano Belaunde, Frédérique Pinson, Nicolas Pellen Session 1: Oral Session 7. Laser-Cooking: A Novel Culinary Technique for Dry Heating using Laser Cutter and Vision Technology Session Chair: Daisuke Deguchi (Nagoya University, JP) Kentaro Fukuchi, Kazuhiro Jo, Akifumi Tomiyama, Shunsuke Takao 13:40 - 14:55 8. Recipe sub-goals and graphs: An evaluation by cooks Lucy Buykx 13:40–14:05 Intelligent Menu Planning: Recommending Sets of Recipes by Ingredients Fang-Fei Kuo, Cheng-Te Li, Man-Kwan Shan Session 3: Invited Talk 14:05–14:30 Food Region Segmentation in Meal Images Using Touch Points Session Chair: Mutsuo Sano (Osaka Institute of Technology, JP） Chamin Morikawa, Haruki Sugiyama, Kiyoharu Aizawa 16:00–16:50 14:30–14:55 Recognizing Ingredients at Cutting Process by Integrating Multimodal Features Atsushi Hashimoto, Jin Inoue, Kazuaki Nakamura, Takuya Funatomi, Mayumi 16:00–16:50 Food Education and Design based on Japanese Food Culture Ueda, Yoko Yamakata, Michihiko Minoh Kimiko Ohtani 16:50–17:00 Closing Session Best Paper Award Ceremony Mutsuo Sano Nov. 2 Nov. 2 Nov.
Session Chair: Ichiro Ide (Nagoya University, JP) 14:55–15:00
124 125 Places of Interest Yakushiji Temple（薬師寺） World Heritages etc. Two three-storied pagodas (the East Pagoda and the West Pagoda) are placed centering around the Golden Hall (Main Todaiji Temple（東大寺） Hall) and Lecture Hall. The arrangement of the temple Todaiji Temple, known for its “Daibutsu-san,” or "Great buildings is so unique that the style of this temple is called Buddha", is a representative temple in Nara, with an imposing “Yakushiji Style”. appearance of the largest wooden structure in the world. 1 minute’ walk from Kintetsu Nishinokyo Station. 0.7km from Main Conf. Venue. WWW: http://www.nara-yakushiji.com/ 0.3km from Art Exhibition Venue. Wikipedia: http://en.wikipedia.org/wiki/Yakushi-ji 15 minutes’ walk from Kintetsu Nara Station, or 5 minutes’ walk from the bus stop Daibutsuden Kasuga Taisha Mae of Loop Line Bus of the city. WWW: http://www.todaiji.or.jp/ Horyuji Temple（法隆寺） Wikipedia: http://en.wikipedia.org/wiki/Tōdai-ji The temple is the world’s oldest wooden structure and it has over 2,300 national treasures and important properties. This Kofukuji Temple（興福寺） was the first location in Japan to be designated by UNESCO The Kofukuji Temple is one of the seven biggest temples of as a World Heritage Site. Nara, which has developed through the closest relationship 20 minutes’ walk from JR Horyuji Station. with the town of Nara. You can see many national treasures WWW: http://www.horyuji.or.jp/horyuji_e.htm including the standing dry lacquered figure of “Ashura.” Wikipedia: http://en.wikipedia.org/wiki/Hōryū-ji 1km from Main Conf. Venue. 0.5km from Keynotes & MMGC Venue. Events 5 minutes’ walk from Kintetsu Nara Station. 正倉院） WWW: http://www.kohfukuji.com/english.html Shosoin Exhibition（ Wikipedia: http://en.wikipedia.org/wiki/Kofuku-ji Shosoin is a repository for treasures, in which cultural artifacts that were brought to Japan over the Silk Road from Persia, India, and China in the 8th century are housed. Some of them are displayed at Kasuga Taisha Shrine（春日大社） Shosoin Exhibition held every autumn at Nara National Museum. In this year, Shosoin Exhibition will The Shrine lies in a primeval forest of cedars and a kind be held from October 27th to November 12th. of Chinese black pines. The brilliant vermillon edifices are Nara National Museum is 10 minutes’ walk from the main conference venue. beautifully contrasted with their surrounding greenery. Shosoin Exhibition: http://www.narahaku.go.jp/english/exhibition/2012toku/shosoin/2012 0.6km from Main Conf. Venue. shosoin_e.html 10 minutes’ walk from the bus stop Kasuga Taisha Omote Sando Shosoin (Wikipedia): http://en.wikipedia.org/wiki/Shōsōin of Loop Line Bus of the city. WWW: http://www.kasugataisha.or.jp/ Wikipedia: http://en.wikipedia.org/wiki/Kasuga-taisha
126 127 Sponsors
WiFi Providers
Supporters 表紙案 A