ICME 2002 Program

 

Tuesday August 27

POSTER SESSION TueAmPO1: Content Delivery Networks and Media on Demand
Date: 27.08.2002, 9:00-11.00, CO Hall
Chair: Alexandros Eleftheriadis, Columbia University, USA
*
SCALABLE MULTIMEDIA CONTENT DELIVERY ON INTERNET
Chi-Hung Chi, Yang Cao, National University of Singapore, Singapore
*
LOAD SHARING BASED ON POPULARITY IN DISTRIBUTED VIDEO ON DEMAND SYSTEMS
Sonia Gonzalez, Angeles Navarro, Juan Lopez, Emilio Zapata, University of Malaga, Spain
*
HIERARCHICAL ADAPTIVE CONTROL PROTOCOL FOR VIDEO STREAMING OVER INTERNET
Linsong Cai, Wael Badawy, Xiao Liu, U. of Calgary, CANADA
*
A COST-EFFECTIVE DISTRIBUTED ARCHITECTURE FOR LARGE-SCALE VIDEO-ON-DEMAND
Fernando Cores, Ana Ripoll, Emilio Luque, University Autonoma of Barcelona, Spain
*
A SCALABLE ON-DEMAND VIDEO DELIVERY PARADIGM
Su-Jun Ma, Min-You Wu, Wei Shu, The University of New Mexico, USA
*
OPTIMIZING SERVER I/O FOR MULTIMEDIA PRESENTATIONS
Ahmed Mostefaoui, LIFC, France; Lionel Brunie, LISI, France
*
AN ANALYSIS OF THE MAIN FACTORS ON THE PERFORMANCE OF RELIABLE MULTICAST
Yantao Pan, School of Computer, P.R. China; Hongxia Wang, Dept. Mathematics, P.R. China; Guohui Li, Hui Wang, Defeng Wu, the Multimedia R&D Center, P.R. China
*
BRINGING STUDIO QUALITY VIDEO-CONFERENCES TO WIDE AREA IP NETWORKS WITH AN ADAPTATION LAYER TRANSLATOR (ALX)
Ruibiao Qiu, Fred Kuhns, Jerome Cox, Applied Research Lab, Washington University, USA; Craig Horn, Erlang Technology Inc., USA
*
CALL ADMISSION CONTROL ALGORITHMS FOR DS-CDMA CELLULAR NETWORKS SUPPORTING MULTIMEDIA SERVICES
Derong Liu, Yi Zhang, University of Illinois, USA


POSTER SESSION TueAmPO2: Video Processing I
Date: 27.08.2002, 9:00-11.00, CO Hall
Chair: Ligang Lu, IBM Research, USA
*
AUTOMATIC TOPIC IDENTIFICATION IN MULTIMEDIA BROADCAST DATA
Uri Iurgel, Steffen Werner, Andreas Kosmala, Gerhard Rigoll, GM University Duisburg, Germany
*
AN OBJECT DETECTION METHOD FOR DESCRIBING SOCCER GAMES FROM VIDEO
Okihisa Utsumi, Koichi Miura, The University of Tokyo, Japan; Ichiro Ide, National Institute of Informatics, Japan; Shuichi Sakai, Hidehiko Tanaka, The University of Tokyo, Japan
*
AUTOMATIC VIDEO SUMMARIZATION BY USING COLOR AND UTTERANCE INFORMATION
Kenichi Fujimura, Koichiro Honda, Graduate School of Science and Technology, Kobe University, Japan; Kuniaki Uehara, Department of Computer and Systems Engineering of Kobe University, Japan
*
VIDEO CLUSTERING USING SPATIO-TEMPORAL IMAGE WITH FIXED LENGTH
Hirotsugu Okamoto, Yukinobu Yasugi, Noboru Babaguchi, Tadahiro Kitahashi, Osaka University, Japan
*
AN INTEGRATED CORRELATION MEASURE FOR SEMANTIC VIDEO SEGMENTATION
Xiaoye Lu, Department of Computer Science, Fudan University, P.R.China; Yu-Fei Ma, Hong-Jiang Zhang, Microsoft Research Asia, P.R.China; Lide Wu, Department of Computer Science, Fudan University, P.R.China
*
FULL-REFERENCE VIDEO QUALITY ASSESSMENT CONSIDERING STRUCTURAL DISTORTION AND NO-REFERENCE QUALITY EVALUATION OF MPEG VIDEO
Ligang Lu, IBM T.J. Watson Research Center, USA; Zhou Wang, Dept. of ECE, Univ. of Texas at Austin, USA; Alan C. Bovik, Dept. of ECE Univ. Taxes at Austin, USA; Jack Kouloheris, IBM T.J. Watson Research Center, USA
*
A UNIFIED APPROACH TO RECONSTRUCTION AND MODIFICATION OF MOTION AND IMAGE DATA
Ik Soo Lim, Daniel Thalmann, EPFL, Switzerland
*
NEWS VIDEO ANALYSIS BASED ON IDENTICAL SHOT DETECTION
Shin'ichi Satoh, National Institute of Informatics, Japan
*
THE SEGMENTATION OF NEWS VIDEO INTO STORY UNITS
Lekha Chaisorn, Tat-Seng Chua, SoC, National University of Singapore, Singapore; Chin-Hui Lee, School of Computing/National University of Singapore, Singapore
*
ANALYSIS AND ENHANCEMENT OF VIDEOS OF ELECTRONIC SLIDE PRESENTATIONS
Tiecheng Liu, Dept. of Computer Science, Columbia University, US.; Rune Hjelsvold, Siemens Corporate Research, US.; John Kender, Dept. of Compuer Science, Columbia University, U.S.
*
AUTOMATIC DISTINCTION OF CAMERA AND OBJECT MOTIONS IN VIDEO SEQUENCES
JungHwan Oh, Praveen Sankuratri, Computer Science & Eng., University of Texas at Arlington, U.S.A.
*
VIDEO TEXT EXTRACTION USING TEMPORAL FEATURE VECTORS
Xiaoou Tang, Bo Luo, The Chinese University of Hong Kong, Hong Kong; Hongjiang Zhang, Microsoft Research Asia, China
*
ROBUST CLUSTERING-BASED VIDEO-SUMMARIZATION WITH INTEGRATION OF DOMAIN-KNOWLEDGE
Dirk Farin, Wolfgang Effelsberg, University of Mannheim, Germany; Peter De With, University of Technology, Eindhoven, Netherlands
*
INTERACTIVE ADAPTIVE MOVIE ANNOTATION
Jeroen Vendrig, Marcel Worring, MediaMill/University of Amsterdam, Netherlands
*
 
FACIAL ACTION RECOGNITION IN FACE PROFILE IMAGE SEQUENCES
Maja Pantic, Delft University of Technology, Mediamatics Dept., Netherlands; Ioannis Patras, University of Amsterdam, Computer Science Dept., Netherlands; Leon Rothkrantz, Delft University of Technology, Mediamatics Dept., Netherlands


POSTER SESSION TueAmPO3: Music Analysis and Retrieval I
Date: 27.08.2002, 9:00-11.00, CO Hall
Chair: Rainer Lienhart, Intel, USA
*
MUSIC STYLE MINING AND CLASSIFICATION BY MELODY
Man-Kwan Shan, Fang-Fei Kuo, Mao-Fu Chen, Department of Computer Science, National Cheng Chi University, Taiwan, ROC
*
FAST MUSIC RETRIEVAL USING POLYPHONIC BINARY FEATURE VECTORS
Hidehisa Nagano, Kunio Kashino, NTT Communication Science Laboratories, NTT Corporation, Japan; Hiroshi Murase, NTT Communication Science Laboratories, NTT Corpor, Japan
*
SCALING UP MUSIC PLAYLIST GENERATION
Jean-Julien Aucouturier, Francois Pachet, SONY CSL, France
*
PITCH DETECTION OF MUSICAL SOUNDS USING ADAPTIVE COMB FILTERS CONTROLLED BY TIME DELAY
Yoshiaki Tadokoro, Wataru Matsumoto, Michiru Yamaguchi, Toyohashi University of Technology, Japan
*
MUSIC TYPE CLASSIFICATION BY SPECTRAL CONTRAST FEATURE
Dan-Ning Jiang, Tsinghua University, China; Lie Lu, Hong-Jiang Zhang, Microsoft Research Asia, China; Jian-Hua Tao, Lian-Hong Cai, Tsinghua University, China
*
AUTOMATIC MUSIC SUMMARIZATION BASED ON TEMPORAL, SPECTRAL AND CEPSTRAL FEATURES
Changsheng Xu, Yongwei Zhu, Qi Tian, Laboratories for Information Technology, Singapore
*
POPULARITY-ADAPTIVE INDEX SCHEME FOR FAST MUSIC RETRIEVAL
DongMoon Park, EenJun Hwang, Ajou University, SOUTH KOREA
*
EXECUTION AND SYNCHRONISATION OF MUSIC SCORE PAGES
P. Bellini, I. Bruno, P. Nesi, Univ. Florence, Italy; M. B. Spinu, Univ. Firenze, EXITECH, Italy


POSTER SESSION TueAmPO4: Robust Media Communications
Date: 27.08.2002, 9:00-11.00, CO Hall
Chair: Michel Barlaud, Univ. of Nice, France
*
ERROR DETECTION IN A COMPRESSED VIDEO USING FRAGILE WATERMARKING
Younghooi Hwang, Sungkyunkwan University, Korea; Byeungwoo Jeon, Sungkyunkwan University, korea
*
EFFICIENT HYBRID VIDEO CODERS WITH SPATIAL AND TEMPORAL SCALABILITY
Marek Domanski, Slawomir Mackowiak, Lukasz Blaszak, Adam Luczak, Poznan University of Technology, Poland
*
REPAIR OPTIONS FOR 3-D WIREFRAME MODEL ANIMATION SEQUENCES
Socrates Varakliotis, Stephen Hailes, UCL - Computer Science, United Kingdom; Joern Ostermann, AT&T Labs - Research, USA
*
PERCEPTUAL CLASSIFICATION OF MPEG VIDEO FOR DIFFERENTIATED-SERVICES COMMUNICATIONS
Fabio De Vito, Laura Farinetti, Politecnico di Torino, Italy; Juan Carlos De Martin, IRITI-CNR, Politecnico di Torino, Italy
*
ERROR CONCEALMENT FOR FINE GRANULARITY SCALABLE VIDEO TRANSMISSION
Hua Cai, HKUST, Hong Kong SAR, P.R.C; Jacky Shen, Feng Wu, Shipeng Li, Microsoft Research Asia, China; Bing Zeng, HKUST, Hong Kong SAR, P.R. China
*
BIT-PLANE ERROR RECOVERY VIA CROSS SUBBAND FOR IMAGE TRASMISSION IN JPEG2000
Pei-Jun Lee, Liang-Gee Chen, Dept. of E.E., National Taiwan University, Taiwan
*
MAP-BASED POST PROCESSING OF VIDEO SEQUENCES USING 3-D HUBER-MARKOV RANDOM FIELD MODELS
Zhen Li, Edward J. Delp, Purdue University, USA
*
AN IMPROVED ALGORITHM FOR REMOVING IMPULSE NOISE BASED ON LONG-RANGE CORRELATION IN AN IMAGE
Yik-Hing Fung, Yuk-Hee Chan, The Hong Kong Polytechnic University, Hong Kong
*
A HYBRID ALGORITHM FOR THE REMOVAL OF BLOCKING ARTIFACTS
George Triantafyllidis, Dimitrios Tzovaras, Dimitrios Sampson, Michael Strintzis, Informatics and Telematics Institute, Greece
*
POSTPROCESSING ALGORITHM IN BLOCK-BASED CODED IMAGES USING WAVELET TRANSFORM AND ADAPTIVE MLP
Kee-Koo Kwon, Byung-Ju Kim, Suk-Hwan Lee, Kuhn-Il Lee, Jong-Won Lee, Seong-Geun Kwon, Kyungpook National University, Republic of Korea
*
ADAPTIVE UNEQUAL ERROR CONTROL FOR VIDEO OVER THE INTERNET
Zhengguo Li, Center for Signal Processing, Singapore; Nam Ling, Santa Clara University, USA; Ce Zhue, Xiaokang Yang, Genan Feng, Si Wu, Feng Pan, Center for Signal Processing, Singapore


POSTER SESSION TueAmPO5: Indexing and Retrieval
Date: 27.08.2002, 9:00-11.00, CO Hall
Chair: Pierre Vandergheynst, EPFL, Switzerland
*
ROTATION INVARIANT TEXTURE FEATURE FOR CONTENT BASED IMAGE RETRIEVAL
Chi-Man Pun, University of Macau, Macau; Moon-Chuen Lee, The Chinese University of Hong Kong, Hong Kong
*
TEMPLATE-BASED IMAGE RETRIEVAL
JunWei Hsieh, YuanZe University, YuanZe University, Taiwan; Eric Grimson, AI lab., MIT, MIT, USA
*
PERCEPTUAL KNOWLEDGE CONSTRUCTION FROM ANNOTATED IMAGE COLLECTIONS
Ana Benitez, Shih-Fu Chang, Columbia University, USA
*
SPATIAL AND FEATURE NORMALIZATION FOR CONTENT-BASED RETRIEVAL
John Smith, Paul Natsev, IBM, USA
*
CATEGORY-BASED SEARCH USING METADATABASE IN IMAGE RETRIEVAL
Yimin Wu, Aidong Zhang, Department of Computer Science and Engineering, SUNY at Buffalo, USA
*
EXTENDING IMAGE RETRIEVAL WITH GROUP-ORIENTED INTERFACE
Munehiro Nakazato, Thomas Huang, University of Illinois at Urbana-Champaign, USA
*
IMPROVING RETRIEVAL PERFORMANCE OF ZERNIKE MOMENT DESCRIPTOR ON AFFINED SHAPES
Dengsheng Zhang, Guojun Lu, Monash University, Australia
*
EFFECTIVE IMAGE ANNOTATION VIA ACTIVE LEARNING
Gerard Sychay, Edward Chang, Kingshy Goh, University of California Santa Barbara, United States
*
IMAGE INDEXING AND RETRIEVAL USING VISUAL KEYWORD HISTOGRAMS
Joo-Hwee Lim, Laboratories for IT, Singapore; Jesse S. Jin, University of New South Wales, Australia
*
RETRIEVAL OF ARTICULATE OBJECTS FROM IMAGES AND VIDEO USING INVARIANT SIGNATURES
Ronald Alferez, Yuan-Fang Wang, University of California, Santa Barbara, U.S.A.
*
AUTOMATIC FEEDBACK FOR CONTENT BASED IMAGE RETRIEVAL ON THE WEB
Y. Alp Aslandogan, The University of Texas at Arlington, U.S.A.; Clement T. Yu, The University of Illinois at Chicago, U.S.A.
*
THE ROLE OF SAMPLE DISTRIBUTION IN RELEVANCE FEEDBACK FOR CONTENT BASED IMAGE RETRIEVAL
Hong Wu, National Lab of Pattern Recognition, P.R. China; Hanqing Lu, Songde Ma, National Lab of Pattern Recognition, P.R.China
*
GAUSSIAN MIXTURE MODEL FOR RELEVANCE FEEDBACK IN IMAGE RETRIEVAL
Fang Qian, Tsinghua University, P.R.China; Mingjing Li, Lei Zhang, Hong-Jiang Zhang, Microsoft Research Asia, P.R.China; Bo Zhang, Tsinghua University, P.R.China
*
DESCRIPTION OF 3D-SHAPE USING A COMPLEX FUNCTION ON THE SPHERE
Dejan Vranic, University of Konstanz, Germany; Dietmar Saupe, University of Leipzig, Germany
*
PREDICTING FACE MOVEMENTS FROM SPEECH ACOUSTICS USING SPECTRAL DYNAMICS
Jintao Jiang, Abeer Alwan, University of California at Los Angeles, USA; Lynne Bernstein, Edward Auer, House Ear Institute, USA; Patricia Keating, University of California at Los Angeles, USA


ORAL SESSION TueAmOR1: Media on Demand
Date: 27.08.2002, 11.00-13.00, CO 1
Chair: Lisa Amini, IBM Research, USA
11:00   STUDY OF A SERVER-LESS ARCHITECTURE FOR VIDEO-ON-DEMAND APPLICATIONS
Jack Y. B. Lee, Raymond W. T. Leung, The Chinese University of Hong Kong, Hong Kong
11:20   ASSIGNMENT OF MOVIES TO HETEROGENEOUS VIDEO SERVERS
Yiu-Wing Leung, Ricky Yuen-Tan Hou, Hong Kong Baptist University, Hong Kong
11:40   A HYBRID BUFFER CACHE MANAGEMENT SCHEME FOR VOD SERVER
Yeonseung Ryu, Hallym University, South Korea; Kyongwoon Cho, Seoul National University, South Korea; Youjip Won, Hanyang University, South Korea; Kern Koh, Seoul National University, South Korea
12:00   A CHANNEL-BASED HEURISTIC DISTRIBUTION PROTOCOL FOR VIDEO-ON-DEMAND
Qiong Zhang, Jehan-Francois Paris, University of Houston, USA
12:20   DESIGN AND IMPLEMENTATION OF A DYNAMIC VRML-BROWSABLE, MOVIE ON-DEMAND SYSTEM DISTRIBUTED OVER INTERNET
Giancarlo Fortino, University of Calabria, Italy; Gianfranco Confessore, AVR, Italy; Antonello Mantuano, University of Calabria, Italy
12:40   SEARCH-BASED BUFFER MANAGEMENT POLICIES FOR STREAMING IN CONTINUOUS MEDIA SERVERS
Moustafa Hammad, Walid Aref, Purdue University, USA; Ahmed Elmagarmid, Hewlett Packard, USA


ORAL SESSION TueAmOR2: Multimedia over Wireless
Date: 27.08.2002, 11.00-13.00, CO 2
Chair: Luis Torres, Polytechnic University of Catalonia, Spain
11:00   POWER-EFFICIENT DISTORTION-MINIMIZED RATE ALLOCATION FOR AUDIO BROADCASTING OVER WIRELESS NETWORKS
Zhu Ji, Tsinghua University, China; Qian Zhang, Wenwu Zhu, Jianping Zhou, Microsoft Research Asia, China
11:20   WIRELESS VIDEO TRANSMISSION USING MULTIPLE DESCRIPTION CODES COMBINED WITH PRIORITIZED DCT COMPRESSION
Yi Zhang, National University of Singapore, Singapore; Mehul Motani, National University of Singapore & Institute for Communications Research, Singapore; Hari Krishna Garg, National University of Singapore, Singapore
11:40   LOW DELAY, ERROR ROBUST WIRELESS VIDEO TRANSMISSION ARCHITECTURE FOR VIDEO COMMUNICATION
Tu-Chih Wang, Hung-Chi Fang, Liang-Gee Chen, EE Departmant of National Taiwan University, Taiwan,R.O.C
12:00   BIT ENERGY DISTRIBUTION EFFECTS IN PROGRESSIVELY ENCODED VIDEO
Martin Sehlstedt, James P. LeBlanc, Luleĺ University of Technology, Sweden
12:20   A NEW METHOD FOR ACCESSING DOCUMENTS IN ENVIRONMENTS WITH LIMITED CONNECTION SPEED, STORAGE AND SCREEN SPACE
Michelle Yan, Siemens Corporate Research, USA; Jens Fauteck, University of Applied Sciences, Germany; Shih-Ping Liou, Siemens Corporate Research, USA
12:40   CROSS LAYER TECHNIQUES FOR ADAPTIVE VIDEO STREAMING OVER WIRELSS NETWORKS
Yufeng Shan, Avideh Zakhor, University of California, Berkeley, U.S.A


ORAL SESSION TueAmOR3: Video Processing II
Date: 27.08.2002, 11.00-13.00, CO 3
Chair: Chitra Dorai, IBM Research, USA
11:00   FILM GRAMMAR BASED REFINEMENTS TO EXTRACTING SCENES IN MOTION PICTURES
Ba Tu Truong, Svetha Venkatesh, School of Computing, Curtin University of Technology, Australia; Chitra Dorai, IBM T. J. Watson Research Center, USA
11:20   CREATING MOTION VIDEO SUMMARIES WITH PARTIAL AUDIO-VISUAL ALIGNMENT
Yihong Gong, Xin Liu, Wei Hua, NEC USA, C&C Research Laboratories, U.S.A.
11:40   VIDEO SHOT DETECTION BASED ON LINEAR PREDICTION OF MOTION
Eric Bruno, University of Geneva, Switzerland; Denis Pellerin, LIS/INPG, France
12:00   SHOT TRANSITION DETECTION USING A PERCEPTUAL DISTANCE FUNCTION
Yi Wu, Edward Chang, Beitao Li, UCSB, USA
12:20   AN OPTIMAL INTERPOLATION-BASED SCHEME FOR VIDEO SUMMARIZATION
Nikolaos Doulamis, Anastasios Doulamis, National Technical University of Athens, Electrical and Computer Engineering Department, Greece; Klimis Ntalianis, National Technical University of Athens, Electrica, Greece
12:40   ON MODEL-BASED CLUSTERING OF VIDEO SCENES USING SCENELETS
Hong Lu, Yap-Peng Tan, Nanyang Technological University, Singapore


ORAL SESSION TueAmOR4: Architectures and Implementation
Date: 27.08.2002, 11.00-13.00, CM 1
Chair: Liang-Gee Chen, National Taiwan University, Taiwan
11:00   MEMORY PERFORMANCE OPTIMIZATIONS FOR REAL-TIME SOFTWARE HDTV DECODING
Han Chen, Kai Li, Princeton University, USA; Bin Wei, AT&T Labs Research, USA
11:20   A FAST METHOD FOR TRAINING SUPPORT VECTOR MACHINES WITH A VERY LARGE SET OF LINEAR FEATURES
Jochen Maydt, Rainer Lienhart, Intel Corporation, USA
11:40   A MULTIMEDIA RUTER ARCHITECTURE TO PROVIDE HIGH PERFORMANCE AND QOS GUARANTEES TO MIXED TRAFFIC
Blanca Caminero, Carmen Carrion, Francisco Quiles, University of Castilla-La Mancha, Spain; Jose Duato, Universidad Politecnica de Valencia, Spain; Sudha Yalamanchili, School of Electrical and Computer Engineering, Georgia
12:00   PREDICTING ENERGY CONSUMPTION OF MPEG VIDEO PLAYBACK ON HANDHELDS
Srijan Chakraborty, David Yau, Purdue University, USA
12:20   REDUCED COMPLEXITY HARDWARE IMPLEMENTATION OF DISCRETE WAVELET TRANSFORM FOR JPEG 2000 STANDARD
Philip Dang, Paul Chau, University of California, San Diego, USA
12:40   SUMMARIZING WEARABLE VIDEOS USING SUPPORT VECTOR MACHINE
Haung Wei Ng, Yasuhito Sawahata, Kiyoharu Aizawa, Aizawa Laboratory, University of Tokyo, Japan


ORAL SESSION TueAmOR5: Music Analysis and Retrieval II
Date: 27.08.2002, 11.00-13.00, CM 2
Chair: Sadaoki Furui , Tokyo Institute of Technology, Japan
11:00   QUERY BY HUMMING: MATCHING HUMMING QUERY TO POLYPHONIC AUDIO
Jungmin Song, So-Young Bae, Kyoungro Yoon, LG Electronics, Korea
11:20   SELF-OPTIMIZED SPECTRAL CORRELATION METHOD FOR BACKGROUND MUSIC IDENTIFICATION
Mototsugu Abe, Masayuki Nishiguchi, SONY Corporation, Japan
11:40   AN HMM-BASED APPROACH TO HUMMING TRANSCRIPTION
Hsuan-Huei Shih, Shrikanth S. Narayanan, Integrated Media Systems Center and Department of Electrical Engineering University of Southern California, USA; C.-C. Jay Kuo, IMSC, EE-s, USC, USA
12:00   A PITCH TRACKING SYSTEM DEDICATED TO PROCESS SINGING VOICE FOR MUSIC RETRIEVAL
Emanuele Pollastri, Dipartimento di Scienze dell'Informazione Universitŕ degli Studi di Milano, ITALY
12:20   MIXTURES OF PROBABILITY EXPERTS FOR AUDIO RETRIEVAL AND INDEXING
Malcolm Slaney, IBM Almaden Research Center, USA
12:40   DYNAMIC TEMPORAL SEGMENTATION IN PARAMETRIC NON-STATIONARY MODELING FOR PERCUSSIVE MUSICAL SIGNALS
Remy Boyer, Slim Essid, Nicolas Moreau, ENST-TSI, France


SPECIAL SESSION TueAmOR6: Encoding of 3D Models for Efficient Delivery
Date: 27.08.2002, 11.00-13.00, CM 3
Chair: Laurent Balmelli, IBM Research, USA
11:00   PROTOCOL FOR STREAMING COMPRESSED 3-D ANIMATIONS OVER LOSSY CHANNELS
Ghassan Al-Regib, Yucel Altunbasak, Jarek Rossignac, Russell Mersereau, Georgia Institute of Technology, USA
11:20   PROGRESSIVE CODING OF TEXTURED 3D MODELS
Kyoko Nagatomo, Daisuke Yoshikai, Keio University, Japan; Masahiro Okuda, The University of Kitakyushu, Japan; Masaaki Ikehara, Keio University, Japan; Shin-ichi Takahashi, University of Kitakyushu, Japan
11:40   STREAMING 3D GEOMETRY DATA OVER LOSSY COMMUNICATION CHANNELS
Stephan Bischoff, Leif Kobbelt, RWTH Aachen, Germany
12:00   MPEG4 ANIMATION CLUSTERING FOR NETWORKED VIRTUAL ENVIRONMENTS
Nadia Magnenat-Thalmann, Chris Joslin, MIRALab - University of Geneva, Switzerland
12:20   SCALABLE 3D GRAPHICS PROCESSING IN CONSUMMER TERMINALS
Wolfgang Van Raemdonck, Gauthier Lafruit, IMEC, BELGIUM; Liesbeth (E.F.M.) Steffens, Clara (C.M.) Otero Pérez, Reinder Bril, Philips, The Netherlands
12:40   HYBRID TRANSCODING FOR ADAPTIVE TRANSMISSION OF 3D CONTENT
Ioana Martin, IBM Research, USA


ORAL SESSION TuePmOR1: Media Delivery Networks
Date: 27.08.2002, 14.15-16.15, CO 1
Chair: Susie Wee, HP Labs, USA
14:15   FAST REQUEST TRANSMISSION IN DOCSIS-BASED CATV NETWORKS
Hue-Jiun Ju, National Taiwan Univesity, Taiwan; Wanjiun Liao, National Taiwan University, Taiwan
14:35   LAYERED VIDEO MULTICAST WITH ECN OVER DIFFERENTIATED SERVICE NETWORKS
Kitae Nahm, Qing Li, C.-C. Jay Kuo, Department of Electrical Engineering, University of Southern California, United States
14:55   OPTIMAL CHAINING AND IMPLEMENTATION FOR LARGE SCALE MULTIMEDIA STREAMING
Te-Chou Su, Computer Science, National Tsing Hua University, Taiwan; Shih-Yu Huang, Computer Science, Ming Chuan University, Taiwan; Jia-Shung Wang, Chen-Lung Chan, Computer Science, National Tsing Hua University, Taiwan
15:15   A BUCKET-INTERLEAVING MULTIPLEXER FOR EFFICIENT NEAR-ON-DEMAND STREAMING TO RESOURCE-CONSTRAINED CLIENTS
Yitzhak Birk, Yair Wiener, Technion, Israel
15:35   ON PROBE STRATEGIES FOR DYNAMIC MULTIMEDIA SERVER SELECTION
Lisa Amini, IBM, USA; Henning Schulzrinne, Columbia University, USA
15:55   IMPLEMENTING CONGESTION CONTROL IN THE REAL WORLD
Ladan Gharai, Colin Perkins, USC/ISI, United States


ORAL SESSION TuePmOR2: Adaptive Multimedia Streaming
Date: 27.08.2002, 14.15-16.15, CO 2
Chair: Olivier Verscheure, IBM Research, USA
14:15   OPTIMAL TEMPORAL SAMPLING OF VIDEO UNDER CHANNEL AND BUFFER CONSTRAINTS
Xiang Sean Zhou, Thomas S. Huang, University of Illinois at Urbana Champaign, USA; Shih-Ping Liou, Siemens Corporate Research, USA
14:35   IMPLEMENTATION OF ADAPTIVE STREAMING OF STORED MPEG-4 FGS VIDEO OVER TCP
Philippe De Cuetos, Institut Eurecom, France; Philippe Guillotel, Thomson Multimedia, France; Keith Ross, Institut Eurecom, France; Dominique Thoreau, Thomson Multimedia, France
14:55   A FAIR AND ADAPTIVE SCHEDULING PROTOCOL FOR VIDEO STREAM TRANSMISSION IN MOBILE ENVIRONMENT
Joe Yuen, Kam-Yiu Lam, Edward Chan, City University of Hong Kong, Hong Kong
15:15   AN EFFICIENT ERROR-MINIMIZING ALGORITHM FOR VARIABLE-RATE TEMPORAL VIDEO SAMPLING
Tiecheng Liu, John Kender, Dept. of Computer Science, Columbia University, USA
15:35   FINE-GRAINED SCALABLE VIDEO BROADCASTING OVER CELLULAR NETWORKS
Jiangchuan Liu, Bin Li, Bo Li, Xiren Cao, The Hong Kong University of Science and Technology, China
15:55   RESOURCE-DRIVEN MPEG-4 FGS FOR UNIVERSAL MULTIMEDIA ACCESS
Richard Chen, Mihaela van der Schaar, Philips Research, USA


ORAL SESSION TuePmOR3: Object Detection and Segmentation
Date: 27.08.2002, 14.15-16.15, CO 3
Chair: Alberto del Bimbo, University of Florence, Italy
14:15   GENERIC FOURIER DESCRIPTOR FOR SHAPE-BASED IMAGE RETRIEVAL
Dengsheng Zhang, Guojun Lu, Monash University, Australia
14:35   EVENT CLUSTERING OF CONSUMER PICTURES USING FOREGROUND/BACKGROUND SEGMENTATION
Alexander Loui, Matthieu Jeanson, Eastman Kodak Company, USA
14:55   MULTIPLE FEATURE TEMPORAL MODELS FOR OBJECT DETECTION IN VIDEO
Juan M. Sanchez, Xavier Binefa, Computer Vision Center, Universitat Autonoma de Barcelona, Spain; John R. Kender, Columbia University, USA
15:15   SHAPE-BASED RETRIEVAL OF 3D MESH MODELS
Titus Zaharia, Francoise Preteux, Institut National des Telecommunications, France
15:35   CONSTRAINED VIDEO OBJECT SEGMENTATION BY COLOR MASKS AND MPEG-7 DESCRIPTORS
Fatih Porikli, Mitsubishi Electric Research Labs, USA; Yao Wang, Polytechnic University, USA
15:55   ACCURATE VIDEO OBJECT SEGMENTATION THROUGH CHANGE DETECTION
Andrea Cavallaro, Touradj Ebrahimi, Swiss Federal Institute of Technology, Switzerland


ORAL SESSION TuePmOR4: Facial animations
Date: 27.08.2002, 14.15-16.15, CM 1
Chair: Tsuhan Chen, Carnegie Mellon University, USA
14:15   3D FACE RECONSTRUCTION FROM VIDEO USING A GENERIC MODEL
Amit Roy Chowdhury, University of Maryland, COllege Park, USA; Sandeep Krishnamurthy, North Carolina State Universityity of North Carolina, USA; Tai Vo, California State University, Fullerton, USA; Rama Chellappa, University of Maryland, COllege Park, USA
14:35   PARAMETER-BASED LIP MODELING FOR FACIAL ANIMATION OF GENERAL OBJECTS
Ze-Jing Chuang, Chung-Hsien Wu, National Cheng Kung University, Taiwan
14:55   HIERARCHICAL MODELING OF A PERSONALIZED FACE FOR REALISTIC EXPRESSION ANIMATION
Yu Zhang, Edmond Cyril Prakash, Eric Sung, Nanyang Technological University, Singapore
15:15   PREVIS: A PERSON-SPECIFIC REALISTIC VIRTUAL SPEAKER
Javier Melenchon, Francesc Alias, Ignasi Iriondo, Enginyeria i Arquitectura La Salle, Spain
15:35   ON RECOVERING DETAILED FACE DEFORMATION UNDER GENERAL LIGHTING USING HEIGHT FROM SHADING
Zhen Wen, Thomas Huang, University of Illinois, United States of America; Zicheng Liu, Microsoft Research, United States of America
15:55   CONSTRUCTION OF FACIAL EXPRESSIONS USING A MUSCLE-BASED FEATURE MODEL
Yi-chih Liu, Hajime Sato, GITS(Waseda University), Japan; Jun Ohya, GITI( Waseda University), Japan; Nobuyoshi Terashima, GITS(Waseda University), Japan


ORAL SESSION TuePmOR5: Compression I
Date: 27.08.2002, 14.15-16.15, CM 2
Chair: Fulvio Moschetti, NTT Docomo, Japan
14:15   BOUNDARY BLOCK-SEARCHING ALGORITHM FOR ARBITRARY SHAPED CODING
Chia-Hung Yeh, National Chung Cheng University, Taiwan; Hsuan Chang, National Yunlin University of Science &Technology, Taiwan; Chung Kuo, National Chung Cheng University, Taiwan
14:35   BLOCK MOTION ESTIMATION USING ADAPTIVE PARTIAL DISTORTION SEARCH
Yui-Lam Chan, Wan-Chi Siu, Ko-Cheung Hui, The Hong Kong Polytechnic University, Hong Kong
14:55   HIGH COMPRESSION OF FACES IN VIDEO SEQUENCES FOR MULTIMEDIA APPLICATIONS
Luis Torres, Daniel Prado, Technical University of Catalonia, Spain
15:15   VIDEO CODING USING JOINT TEMPORAL-SPATIAL COMPENSATION
Zhihai He He, Chang Wen Chen, Sarnoff, USA
15:35   HIDDEN MARKOV TREE BASED TRANSIENT ESTIMATION FOR AUDIO CODING
Stephane Molla, Bruno Torresani, LATP, France
15:55   AUTOMATIC OBJECT EXTRACTION AND DYNAMIC BITRATE ALLOCATION FOR SECOND GENERATION VIDEO CODING
Fulvio Moschetti, NTT DoCoMo, Japan; Giuseppe Covitto, University of Siena, Italy; Francesco Ziliani, Visiowave, Switzerland; Alessandro Mecocci, University of Siena, Italy


SPECIAL SESSION TuePmOR6: Coding and Transmission Formats for 3D Audio
Date: 27.08.2002, 14.15-16.15, CM 3
Chair: Giorgio Zoia, EPFL, Switzerland
14:15   INTERACTIVE ROOM ACOUSTIC RENDERING IN REAL TIME
Lauri Savioja, Tapio Lokki, Helsinki University of Technology, Finland; Jyri Huopaniemi, Nokia Research Center, Finland
14:35   PERCEPTUAL ENCODING OF ACOUSTIC ENVIRONMENTS
Renato Pellegrini, Studer Professional Audio AG, Switzerland; Ulrich Horbach, Professional Audio AG, Switzerland
14:55   HYBRID NATURAL AND STRUCTURED AUDIO CODING FOR 3D SCENES
Stefano Battista, bsoft, italy; Giorgio Zoia, Aleksandar Simeonov, Ruo-Hua Zhou, epfl, switzerland
15:15   FULL-DUPLEX COMMUNICATION SYSTEMS USING LOUDSPEAKER ARRAYS AND MICROPHONE ARRAYS
Herbert Buchner, Sascha Spors, Walter Kellermann, Rudolf Rabenstein, University of Erlangen-Nuremberg, Germany
15:35   RENDERING MPEG-4 AABIFS CONTENT THROUGH A LOW-LEVEL CROSS-PLATFORM 3D AUDIO API
Jean-Michel Trivi, Jean-Marc Jot, Creative Advanced Technology Center, U.S.A.
15:55   REAL-TIME RENDERING OF DYNAMIC SCENES USING WAVE FIELD SYNTHESIS
Ulrich Horbach, Renato Pellegrini, Studer Professional Audio AG, Switzerland; Edo Hulsebos, TU Delft, Netherlands; Etienne Corteel, Ircam, France


Multimedia CDNs: What's the next step?

Tue August 27, 2002, Salle Polyvalente, 16h.30.

Chair/Moderator: Lisa Amini, IBM Research, USA

Organized: Lisa Amini, IBM Research, USA

Multimedia content delivery represents a unique opportunity for technology and service providers – unlike other content types, which are enhanced by delivery from servers positioned at the edge of the network, rich media requires edge delivery to attain reasonable user experiences.  While digital audio and video content brings additional complexities (very large objects, isochronous delivery, and interactivity), the advantages of edge delivery are exceptional.  Attributes making multimedia especially well-suited for edge delivery include: the need for Quality of Service (QoS) for an adequate user experience, write-once-read-many nature, high value to Content Providers, distribution and delivery revenue potential to Service Providers – especially for pervasive and wireless devices, the need for detailed usage statistics, and the potential for content services to adapt and protect multimedia assets are best offered through distributed techniques, to name a few. 

The technical advantages of Content Delivery Networks (CDN) for Internet accessible multimedia are obvious to most in the rich media community. Likewise, in the enterprise environment, e-Learning, collaboration, and corporate communications applications are driving requirements for enterprise CDN (e-CDN) technology.  To meet these demands, researchers and developers are racing to create innovative technology for a range of rich media services, including personalization, annotation, transcoding, rights management, filtering, and a host of other digital content "must-haves."  And yet, recent events have made it clear that the evolution of multimedia CDN’s is highly dependent on a variety of business, as well as technical, issues.

This panel brings key researchers who are creating multimedia distribution and delivery technology together with experts who are leading the deployment of next generation multimedia services. The goal of the panel is to explore, discuss, and come to a better understanding of the issues shaping the multimedia CDN space, including:

Panelists:

Dr. Mark Stuart Day is Senior Scientist at Cisco Systems, where he is technical lead for product management of Cisco's CDN products. He joined Cisco with the acquisition of SightPath in 2000.  Previously, he was at Lotus, where his work contributed to the creation of Lotus Sametime. In the IETF, Mark is co-chair of the working groups on Content Distribution Internetworking (CDI) and Instant Messaging and Presence Protocol (IMPP).  He received his Ph.D. from MIT in 1995.

Dr. Minoru Etoh received the B.E. and M.S.E.E. degrees from Hiroshima University, Hiroshima, Japan, in 1983 and 1985, respectively. He received the Ph.D. degree from Osaka University, Osaka, Japan, in 1993. In 1985 he joined the Matsushita Electric Industrial Co., Ltd. From 1988 to 1990 he worked for the ATR Communication Systems Research Laboratories, the Advanced Telecommunication Research International, Kyoto. From 1991 to 1993, he was a Visiting Researcher at Osaka University. In the period of the ATR and Osaka University, he was involved in Computer Vision research. From 1994 to 1998, he was at the Central Research Laboratories of Matsushita Electric, and in the meantime he participated the MPEG-4 standardization. He was also Adjunct Professor of Nara Institute of Science and Technology from 1997 to 2000. After moving to Matsushita Research Institute of Tokyo in 1999, He joined Multimedia Laboratories of NTT DoCoMo, Inc., Yokosuka, May 2000. He currently works for NTT DoCoMo as Director of Signal Processing Laboratory and also serves as Adjunct Lecturer of Osaka University. He is now conducting the research groups in charge of audio, speech and video coding technologies, media delivery over mobile networks, MPEG, ITU-T, 3GPP, and W3C standardization activities. Dr. Etoh received the 1995 Best Paper Award of IEICE Japan, the 14th Telecom System Technology Prize of the Telecommunications Advancement Foundation(1998), the 7th Sakai Commemorative Prize of IPSJ(1998), respectively. He is a member of IEEE, IEICE, and IPSJ.

Dr. Emmanuel Gouleau has been involved within France Telecom R&D, the R&D labs of France Telecom, as an R&D engineer in several development projects related to the design of hosting architecture for multimedia streaming services since October 1997. Two kinds of architectures are currently considered, either centralized or distributed also called CDN. This implication can be described in two contexts with different timeframes. The first context is "short term" oriented. It consists in the evaluation of current industrial solutions for the key-components of a streaming hosting architecture: load balancing or redirection with L7 switches, caching and splitting with streaming caches, content management software. France Telecom business units expect from FTR&D some recommendations in defining the consistency between the services they want to offer and the industrial offer. The second context, "mid term" oriented, is the follow-on of industrial roadmaps and their relationship with standards design within MPEG and IETF. The main objective is to anticipate the future needs of France Telecom and give some feedback to the industrial manufacturers. A second working area in this context is the development of prototype in order to get a better understanding of the on-going developments of products and protocols.

Dr. John Martin is the chief network architect for Network Appliance, specializing generally in caching architectures and specifically in scalable deployment for ISP and telecom environments. He has a broad knowledge of Internet technologies and since 1995 has been working with various aspects of Web caching, a subject on which he has frequently presented at workshops and conferences. Prior to joining Network Appliance, Martin was working for the Trans-European Research and Education Networking Association (TERENA) as chief technical officer, where he was responsible for initiating various pan-European Web cache projects including TF-CACHE, an initiative to promote the deployment of Web caching across European R&E networks. He also co-founded the Irish ISP UNITE Solutions Ltd., in 1994. Martin is well known within the industry and in March 1999 was co-chair of the programme committee for the 4th International Web Caching Conference held in San Diego and currently co-chairs the IETF Web Replication and Caching Working Group.

Prof. Keith W. Ross is a professor in the Multimedia Communications Department at Institut Eurecom, a research and graduate teaching institution in France.  Before joining Institut Eurecom, he was a professor in the Department of Systems Engineering at theUniversity of Pennsylvania from 1985 through 1997. Professor Ross has made significant research contributions to the theory and practice of computer networking throughout his career. These contributions include important papers in the areas of audio and video streaming, content distribution, quality of service, and traffic modeling of computer networks. His work on Web caching includes the co-development of the CARP protocol, which has been implemented in Microsoft and Netscape caching products. His current research focus is on peer-to-peer networking and content distribution networks. Professor Ross has written two books, including the textbook, "Computer Networking: A Top-Down Approach Featuring the Internet," co-authored with James Kurose, which has been adopted by over 200 universities in the US and is currently being translated into four languages. From July 1999 to July 2001, Professor Ross took a leave from Institut Eurecom to found and lead Wimba, an Internet technology start-up. Wimba develops Java-based streaming messaging technologies for the Internet.

 

Wednesday August 28

POSTER SESSION WedAmPO1: Streaming
Date: 28.08.2002, 9.00-11.00, CO Hall
Chair: Gabriel Fernandez i Ubiergo, Ramon Llull University, Spain
*
AN MPEG-7 TOOL FOR COMPRESSION AND STREAMING OF XML DATA
Ulrich Niedermeier, Munich University of Technology, Germany; Joerg Heuer, Andreas Hutter, Siemens AG, Corporate Technology, Germany; Walter Stechele, Munich University of Technology, Germany
*
A BANDWIDTH EFFECTIVE STREAMING OF JPEG2000 IMAGES USING HYPERTEXT TRANSFER PROTOCOL
Shih Tsung Liang, Tain-Sao Chang, DaYeh University/Dept. CSIE, Taiwan
*
DUAL-PLAN BANDWIDTH SMOOTHING FOR LAYER-ENCODED VIDEO
Tong Gan, Kai-Kuang Ma, Liren Zhang, Nanyang Technological University, Singapore
*
A DECENTRALIZED ARCHITECTURE FOR ADAPTIVE MEDIA DISSEMINATION
Philippe Cudre-Mauroux, Karl Aberer, EPFL, Switzerland
*
OPTIMAL BANDWIDTH ALLOCATION SCHEME WITH DELAY AWARENESS IN MULTIMEDIA TRANSMISSION
Mei-Ling Shyu, University of Miami, USA; Shu-Ching Chen, Florida International University, USA; Hongli Luo, University of Miami, USA
*
EFICIENT AND FLEXIBLE DRIFT-FREE VIDEO BITSTREAM SWITCHING AT PREDICTIVE FRAMES
Xiaoyan Sun, Harbin Institute of Technology, China; Shipeng Li, Feng Wu, Guobin Shen, Microsoft Research Asia, China; Wen Gao, Harbin Institute of Technology, China
*
THE XTREAM MULTIMEDIA SYSTEM
Zoran Dimitrijevic, Raju Rangaswami, Edward Chang, Univ. of California, Santa Barbara, USA


POSTER SESSION WedAmPO2: Encryption and Watermarking
Date: 28.08.2002, 9.00-11.00, CO Hall
Chair: Jean-Luc Dugelay, Institut Eurecom, France
*
A ROBUST VIDEO WATERMARKING TECHNIQUE FOR COMPRESSION AND TRANSCODING PROCESSING
Rosa Lancini, Francesco Mapelli, CEFRIEL, Italy; Stefano Tubaro, Politecnico di Milano, Italy
*
SPEECH ENCRYPTION USING CIRCULANT TRANSFORMATIONS
Manjunath G., Anand G.V., Indian Institute of Science, Indian Institute of Science, India
*
ADDING ROBUSTNESS TO GEOMETRICAL ATTACKS TO A WAVELET BASED, BLIND VIDEO WATERMARKING SYSTEM
Cristian Vasile Serdean, Marcel Adrian Ambroze, Martin Tomlinson, University of Plymouth, UK; Graham Wade, University of Newcastle, Australia
*
WATERMARK DETECTION ALGORITHM USING STATISTICAL DECISION THEORY
Seong-Geun Kwon, School of Electrical Engineering and Computer Science, Kyungpook National University, Republic of Korea; Suk-Hwan Lee, School of Electrical Engineering and Computer Science, Kyungpook National University, Republic of Korea; Kee-Koo Kwon, School of Electrical Engineering and Computer Science, Kyungpook National University, Republic of Korea; Ki-Ryong Kwon, Department of Electronic Engineering, Pusan University of Foreign Studies, Republic of Korea; Kuhn-Il Lee, School of Electrical Engineering and Computer Science, Kyungpook National University, Republic of Korea
*
IMPROVING DATA HIDING PERFORMANCE BY USING QUANTIZATION IN A PROJECTED DOMAIN
Fernando Perez-Gonzalez, Felix Balado, University of Vigo, Spain
*
AN INTEGRATED APPROACH TO ENCRYPTING SCALABLE VIDEO
Ahmet Eskicioglu, Brooklyn College of the City University of New York, USA; Edward J. Delp, Purdue University, USA
*
ROBUST WATERMARKING OF VECTOR DIGITAL MAPS
Ryutarou Ohbuchi, Hiroo Ueda, Computer Science Department, Yamanashi University, Japan; Shuh Endoh, GIS Business Promotion , IBM Japan, Japan
*
STEGANALYSIS OF LSB EMBEDDING IN MULTIMEDIA SIGNALS
Sorina Dumitrescu, McMaster University, Canada; Xiaolin Wu, Polytechnic Univ. Brooklyn, United States
*
BLIND CONSISTENCY-BASED STEGANOGRAPHY FOR INFORMATION HIDING IN DIGITAL MEDIA
Hairong Qi, University of Tennessee, USA; Wesley Snyder, William Sander, Army Research Office, USA
*
BLIND WATERMARKING USING WAVELET TREE QUANTIZATION
Shih-Hao Wang, Dept. of Electronic engineering, National Chiao Tung Univ., Taiwan; Yuan-Pei Lin, Dept. of electrical and control engineering, National Chiao Tung Univ., Taiwan
*
A PUBLIC-KEY BASED WATERMARKING FOR COLOR IMAGE AUTHENTICATION
Sung Cheal Byun, Il Lo Lee, Tae Hwan Shin, Byung Ha Ahn, K-JIST, Korea
*
TOWARDS REAL-TIME VIDEO WATERMARKING FOR SYSTEM-ON-CHIP
Guillaume Petitjean, STMicroelectronics, France; Jean-Luc Dugelay, Institut Eurecom, France; Sophie Gabriele, STMicroelectronics, France; Christian Rey, Institut Eurecom, France; Jean Nicolai, STMicroelectronics, France
*
K-TIME ENCRYPTION FOR K-TIME LICENSING
Gregory Perkins, Prabir Bhattacharya, Panasonic, USA
*
SOFT-DECISION DECODING OF TRACEABILITY CODES
Marcel Fernandez, Miguel Soriano, Department of Telematics Engineering. Universitat Politecnica de Catalunya, UPC, Spain
*
COMPRESSED-DOMAIN VIDEO WATERMARKING OF MPEG STREAMS
Dimitrios Simitopoulos, Informatics and Telematics Institute, Greece; Sotirios Tsaftaris, Northwestern University, USA; Nikolaos Boulgouris, Michael Strintzis, Informatics and Telematics Institute, Greece


POSTER SESSION WedAmPO3: Compression II
Date: 28.08.2002, 9.00-11.00, CO Hall
Chair: Oscar Au, Hong-Kong University of Science and Technology, Hong Kong
*
ON THE METHODS AND APPLICATIONS OF ARBITRARILY DOWNSIZING VIDEO TRANSCODING
Yap-Peng Tan, Yongqing Liang, Haiwei Sun, Nanyang Technological University, Singapore
*
PROGRESSIVE ENCODING OF VOXEL SURFACES BASED ON PATTERN CODE REPRESENTATION
Bong Gyun Roh, Chang-Su Kim, Sang-Uk Lee, Seoul Nat'l Univ., South Korea
*
COMPRESSING SETS OF SIMILAR IMAGES USING HYBRID COMPRESSION MODEL
Jiann-Der Lee, Shu-Yen Wan, Chang Gung University, Graduate Institute of Information Engineeing, Taiwan, ROC; Rui-Feng Wu, Chang Gung University, Electrical Engineering Dept, Taiwan, ROC; Cherng-Min Ma, Chang Gung University,Department of Computer Science and Information Management, Taiwan, R.O.C.
*
A STUDY ON TWO-LAYER CODING FOR ANIMATION IMAGES
Ouji Nakagami, Toshinori Miyazawa, Hiroshi Watanabe, Hideyoshi Tominaga, Waseda University, Japan
*
A SIMPLE RATE CONTROL FRAMEWORK FOR SINGLE-PASS VARIABLE BIT RATE MPEG ENCODER
Yung-Ching Chang, Silicon Integrated Systems Corp., Taiwan; Chuan-Yu Cho, Jia-Shung Wang, National Tsing Hua University, Taiwan
*
A FAST EFFICIENT ARCHITECTURE FOR MPEG-4 ZEROTREE ENCODER
Chao Xu, Peking University, China; Yi-zhen Zhang, Xin Fan, Qing-yun Shi, Peking university, China
*
PREPROCESSING TECHNIQUES FOR IMPROVING THE LOSSLESS COMPRESSION OF IMAGES WITH QUASI-SPARSE AND LOCALLY SPARSE HISTOGRAMS
Armando Pinho, DET / IEETA, University of Aveiro, Portugal
*
AN OVERCOMPLETE DISCRETE WAVELET TRANSFORM FOR VIDEO COMPRESSION
Nicu Sebe, Claudiu Lamba, Michael Lew, Leiden University, Netherlands
*
SIMPLE GLOBAL MODEL OF AN MPEG-2 BITSTREAM
Marek Domanski, Adam Luczak, Poznan University of Technology, Poland
*
A NOVEL MOTION ESTIMATION ALGORITHM FOR ARBITRARILY SHAPED VIDEO CODING
Andy Yu, Bing Zeng, Oscar Au, Hong Kong University of Science & Technology, Hong Kong SAR
*
MPEG-4 VERY LOW BIT-RATE VIDEO COMPRESSION BY ADAPTIVELY UTILISING SPRITE TO SHORT SEQUENCES
Kumi Jinzenji, Shigeki Okada, Naoki Kobayashi, NTT Cyber Space Labs. NTT Corporation, Japan; Hiroshi Watanabe, Waseda University, Japan
*
A COMPARISON OF DIFFERENT HAPTIC COMPRESSION TECHNIQUES
Cyrus Shahabi, Antonio Ortega, Mohammad Kolahdouzan, University of Southern California, U.S.A.
*
MOTION ADAPTIVE INTERPOLATION WITH MORPHOLOGICAL OPERATION AND 3:2 PULL-DOWNED RECOVERY FOR DEINTERLACING
Shyh-Feng Lin, Yu-Ling Chang, Dept. of Electrical Eng., National Taiwan University, Taiwan; Liang-Gee Chen, Dept. of Electrical Eng., National Taiwan Universi, Taiwan
*
SUPERVISED SEGMENTATIONAT LOW BIT RATES FOR REGION REPRESENTATION AND COLOR IMAGE COMPRESSION
Olivier Deforges, Joseph Ronsin, UMR IETR/Insa Rennes, France
*
APPROXIMATING COLOR CONSISTENCY IN RETRIEVAL USING THE ENERGY HISTOGRAM OF DCT COEFFICIENTS
Jose A. Lay, University of Sydney, Australia; Ling Guan, Ryerson Polytechnic University, Canada
*
RIGOROUS COUPLED WAVE TRANSFORM CODING OF IMAGES
Ni Y. Chang, Chung J. Kuo, Department of Electrical Engineering, Taiwan
*
IMPROVED QUADTREE ALGORITHM BASED ON JOINT CODING FOR PIECEWISE SMOOTH IMAGE COMPRESSION
Rahul Shukla, Pier Luigi Dragotti, SWISS FEDERAL INSTITUTE OF TECHNOLOGY, LAUSANNE, SWITZERLAND; Minh Do, UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN, USA; Martin Vetterli, SWISS FEDERAL INSTITUTE OF TECHNOLOGY, LAUSANNE, SWITZERLAND


POSTER SESSION WedAmPO4: Algorithms I
Date: 28.08.2002, 9.00-11.00, CO Hall
Chair: Francesco Ziliani, Visiowave, Switzerland
*
A COMPRESSED-DOMAIN VISUAL INFORMATION EMBEDDING ALGORITHM FOR MPEG2 HDTV STREAMS
Bin Yu, Klara Nahrstedt, MONET Group, Department of Computer Science, UIUC, United States
*
TEMPORAL NOISE REDUCTION OF BAYER MATRIXED VIDEO DATA
Angelo Bosco, Massimo Mancuso, Sebastiano Battiato, Giuseppe Spampinato, STMicroelectronics, Italy
*
NEW SCALABLE THREE-STAGE MOTION ESTIMATION TECHNIQUE FOR MOBILE MPEG ENCODING
Stephan Mietens, EESI/University of Technology Eindhoven, The Netherlands; Peter H.N. With, de, CMG/University of Technology Eindhoven, The Netherlands; Christian Hentschel, Philips Research Labs., The Netherlands
*
A RENDEZ-VOUS POINT SELECTION ALGORITHM FOR VIDEOCONFERENCING APPLICATIONS
Jean-François Macq, Laurence A. Wolsey, CORE-UCL, Belgium; Benoit Macq, TELE-UCL, Belgium
*
THE HIERARCHICAL CLUSTER MODEL FOR IMAGE REGION SEGMENTATION
Jonathan Randall, Sydney University, Australia; Ling Guan, Ryerson University, Canada; Xing Zhang, WanQing Li, Motorola Australia Research Center, Australia
*
THE INDUCTIVE INVERSE KINEMATICS ALGORITHM USING UNIFORM POSTURE MAP
Jin Ok Kim, SungkyunKwan Univ., Korea; Bum Ro Lee, Chin Hyun Chung, Kwangwoon Univ., Korea
*
FAST OVER-COMPLETE WAVELET IMPLEMENTATION FOR SPLINE FAMILY
Ngai-Fong Law, Centre for Multimedia Signal Processing, Dept of Electronic & Information Engineering, The Hong Kong Polytechnic University, Hong Kong; Wan-Chi Siu, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong
*
MESH: MEASURING ERRORS BETWEEN SURFACES USING THE HAUSDORFF DISTANCE
Nicolas Aspert, Diego Santa-Cruz, Touradj Ebrahimi, EPFL, Switzerland
*
MAXIMUM LIKELIHOOD FOR BAYESIAN ESTIMATOR BASED ON ALPHA-STABLE FOR IMAGE
Xu Huang, University of Canberra, Australia, Australia; Allan C. Madoc, Center for Actuarial, University of Melbourne, Australia
*
WAVELET KALMAN BASED RECONSTRUCTION
Afshin David, University of Turku, Finland
*
MOTION TRANSPARENCY CONSTRAINT EQUATION BASED ON A WAVELET FUNCTION DECOMPOSITION
Mathias Pingault, Denis Pellerin, Laboratoire des Images et des Signaux, France
*
MACRO-LEVEL SIMILARITY MEASUREMENT IN VIZIR
Horst Eidenberger, Christian Breiteneder, Vienna University of Technology, Austria
*
CONTINUOUS NORMALIZED CONVOLUTION
Kenneth Andersson, Hans Knutsson, Linköping University, Sweden
*
ENHANCEMENT OF COLORED ENGRAVINGS
Vladimir Misic, University of Rochester, USA; Robert Buckley, Xerox Corporation, USA; Kevin Parker, University of Rochester, USA


POSTER SESSION WedAmPO5: Interfaces
Date: 28.08.2002, 9.00-11.00, CO Hall
Chair: Atsuo Yoshitaka, Hiroshima University, Japan
*
TOWARDS A CONTEXT AWARE MINING OF USER INTERESTS FOR CONSUMPTION OF MULTIMEDIA DOCUMENTS
Manolis Wallace, Giorgos Stamou, Image, Video and Multimedia Laboratory, Department of Electrical and Computer Engineering, National Technical University of Athens, Greece
*
CLASSIFYING EMOTIONS IN HUMAN-MACHINE SPOKEN DIALOGS
Chul Min Lee, Shrikanth Narayanan, University of Southern California, US; Roberto Pieraccini, SpeechWorks International, US
*
SPEED BROWSER CONTROLLED BY EYE MOVEMENTS
Takaaki Numajiri, Akio Nakamura, Department of Information and Computer Sciences, Saitama University, Japan; Yoshinori Kuno, Department of Information and Computer Sciences, S, Japan
*
MULTIMODAL EMOTION RECOGNITION IN AUDIOVISUAL COMMUNICATION
Björn Schuller, Manfred Lang, Gerhard Rigoll, Technical University Munich, Germany
*
EXPLOITING MULTIMEDIA COMPONENTS IN SMALL USER INTERFACES
Minna Mäkäräinen, University of Oulu, Finland; Pekka Isomursu, Nokia Mobile Phones, Finland
*
IMPACT OF CAPTIONS ON DEAF AND HEARING PERCEPTION OF MULTIMEDIA VIDEO CLIPS
Stephen Gulliver, Gheorghita Ghinea, BRUNEL UNIVERSITY, UNITED KINGDOM


ORAL SESSION WedAmOR1: Middleware
Date: 28.08.2002, 11.00-13.00, CO 1
Chair: Klara Nahrstedt, Univ. of Illinois, Urbana-Champaign, USA
11:00   DIGITAL-ITEM-BASED MEDIA MANAGEMENT SYSTEM AND APPLICATIONS
Richard Qian, Todd Schwartz, Eugene Epshteyn, Intel Labs, USA
11:20   JAVA-BASED CONTINUOUS BROWSING OF REMOTE MAPS FROM A WIRELESS PDA: A FEASIBILITY STUDY
Emanuele Lattanzi, Alessandro Bogliolo, STI - University of Urbino, Italy
11:40   MC-SPF: AN APPLICATION-LEVEL MULTICAST SERVICE PATH FINDING PROTOCOL FOR MULTIMEDIA APPLICATIONS
Jingwen Jin, Klara Nahrstedt, Dept. CS - UIUC, USA
12:00   MOBILE MULTIMEDIA IN VESPER VIRTUAL HOME ENVIRONMENT
Jose Oliveira, INESC Porto / FEP, Portugal; Renato Roque, PT Inovaçăo, Portugal; Eurico Carrapatoso, INESC Porto / FEUP, Portugal; Hans Portschy, Daniel Hovanyi, Imre Berenyi, Siemens AG Oesterreich, Austria
12:20   XFLAVOR: BRIDGING BITS AND OBJECTS IN MEDIA REPRESENTATION
Danny Hong, Alexandros Eleftheriadis, Columbia University, USA
12:40   COMPONENTS FOR IMMERSION
Alexandre Francois, Integrated Media Systems Center, USC, USA


ORAL SESSION WedAmOR2: Algorithms II
Date: 28.08.2002, 11.00-13.00, CO 2
Chair: Ruby Lee, Princeton University, USA
11:00   FAST COMPUTATION OF DCT BY STATISTIC ADAPTED LOOK-UP TABLES
Robert Kutka, Siemens AG, Germany
11:20   MULTIPLE SPRITES AND FRAME SKIPPING TECHNIQUES FOR SPRITE GENERATION WITH HIGH SUBJECTIVE QUALITY AND FAST SPEED
Shao-Yi Chien, Ching-Yeh Chen, Yu-Wen Huang, Liang-Gee Chen, National Taiwan University, Taiwan
11:40   SIMPLE AND EFFECTIVE ALGORITHM FOR AUTOMATIC TRACKING OF A SINGLE OBJECT USING A PAN-TILT-ZOOM CAMERA
Yu-Wen Huang, Bing-Yu Hsieh, Shao-Yi Chien, Liang-Gee Chen, DSP/IC Design Lab., National Taiwan University, Taiwan
12:00   WATERSHED PARALLEL ALGORITHM FOR ASYNCHRONOUS PRPCESSORS ARRAY
Bruno Galilee, Franck Mamalet, France Telecom R&D, france; Marc Renaudin, TIMA, France; Pierre-Yves Coulon, LIS, France
12:20   CACHE-EFFICIENT WAVELET LIFTING IN JPEG 2000
Siddhartha Chatterjee, IBM Research, USA; Christopher Brooks, IBM Software Group, USA
12:40   FAST LIST VITERBI DECODING AND APPLICATION FOR SOURCE-CHANNEL CODING OF IMAGES
Martin Röder, Raouf Hamzaoui, University of Konstanz, Germany


ORAL SESSION WedAmOR3: Sports sequence processing
Date: 28.08.2002, 11.00-13.00, CO 3
Chair: Hongjiang Zhang, Microsoft Research, China
11:00   EVENTS RECOGNITION BY SEMANTIC INFERENCE FOR SPORTS VIDEO
Chuan Wu, Department of Computer Science and Technology, Tsinghua University, P.R.China; Yu-Fei Ma, Hong-Jiang Zhang, Microsoft Research Asia, P.R.China; Yu-Zhuo Zhong, Tsinghua University, P.R.China
11:20   ON THE AUTOMATIC INDEXING OF CRICKET USING CAMERA MOTION PARAMATERS
Mihai Lazarescu, Svetha Venkatesh, Geoff West, Curtin University of Technology, Australia
11:40   STORY BASED REPRESENTATION FOR BROADCASTED SPORTS VIDEO AND AUTOMATIC STORY SEGMENTATION
Naoko Nitta, Noboru Babaguchi, Tadahiro Kitahashi, ISIR, Osaka University, Japan
12:00   MULTI-MODAL EXTRACTION OF HIGHLIGHTS FROM TV FORMULA 1 PROGRAMS
Milan Petkovic, University of Twente, The Netherlands; Vojkan Mihajlovic, University of Nis, Yugoslavia; Willem Jonker, University of Twente, The Netherlands; Slobodanka Djordjevic-Kajan, University of Nis, Yugoslavia
12:20   BASEBALL SCENE CLASSIFICATION USING MULTIMEDIA FEATURES
Wei Hua, Mei Han, Yihong Gong, NEC USA, Inc., USA
12:40   SOCCER HIGHLIGHTS DETECTION AND RECOGNITION USING HMMS
Jurgen Assfalg, Marco Bertini, Alberto Del Bimbo, Walter Nunziati, Pietro Pala, Univ. Firenze - DSI, Italy


ORAL SESSION WedAmOR4: Augmented Reality
Date: 28.08.2002, 11.00-13.00, CM 1
Chair: Xiang Zhang, Siemens, USA
11:00   CONSTRUCTION OF ANIMATION MODELS OUT OF CAPTURED DATA
Ik Soo Lim, Daniel Thalmann, EPFL, Switzerland
11:20   VIRTUALIZING REAL OBJECTS WITH SURFACE INTERREFLECTIONS
Takashi Machida, Cybermedia Center, Osaka University, Japan; Naokazu Yokoya, Nara Institute of Science and Technology, Japan
11:40   LET THE SUNSHINE ON YOUR SCREEN: INTRODUCING AUGMENTED REALITY INTO INTERACTIVE TELEVISION
Jürgen Stauder, Philippe Robert, Thomson multimedia, France
12:00   AVATARS, INTERACTION, AND NEXT-GENERATION TELEVISION
Andrew Tokmakoff, Telematica Instituut, The Netherlands
12:20   USER-FOLLOWING DISPLAYS
Gopal Pingali, Claudio Pinhanez, Tony Levas, Rick Kjeldsen, Mark Podlaseck, IBM T.J. Watson Research Center, USA
12:40   SEAR: TOWARDS A MOBILE AND CONTEXT-SENSITIVE SPEECH-ENABLED AUGMENTED REALITY
Stuart Goose, Sandra Sudarsky, Xiang Zhang, Nassir Navab, Siemens Corporate Research, USA


SPECIAL SESSION WedAmOR5: Rate-Distortion Optimized Delivery of Realtime and Streaming Media I
Date: 28.08.2002, 11.00-13.00, CM 2
Chair: Wenjun Zeng, Packetvideo Corp, USA
Co-chair: Heather Yu (Panasonic, USA), Philip A. Chou (Microsoft, USA)
11:00   END-TO-END VIDEO QUALITY ANALYSIS FOR VIDEO STREAMING OVER IP NETWORK
Zhihai He, Chang Wen Chen, Sarnoff Co, USA
11:20   COST-DISTORTION OPTIMIZED STREAMING MEDIA OVER DIFFSERV NETWORKS
Anshul Sehgal, University of Illinois, USA; Philip A. Chou, Microsoft Corporation, USA
11:40   OPTIMIZED VIDEO STREAMING OVER LOSSY NETWORKS WITH REAL-TIME ESTIMATION OF END-TO-END DISTORTION
Rui Zhang, Stanford, United States; Shankar Regunathan, Microsoft, United States; Kenneth Rose, University of California, United States
12:00   JOINT PRODUCT CODE OPTIMIZATION FOR SCALABLE MULTIMEDIA TRANSMISSION OVER WIRELESS CHANNELS
Vladimir Stankovic, University of Leipzig, Germany; Raouf Hamzaoui, University of Konstanz, Germany; Zixiang Xiong, Texas A & M University, USA
12:20   R-D OPTIMIZED MEDIA STREAMING ENHANCED WITH ADAPTIVE MEDIA PLAYOUT
Mark Kalman, Stanford University, USA; Eckehard Steinbach, Technical University of Munich, Germany; Bernd Girod, Stanford University, USA
12:40   LOW-LATENCY STREAMING OF PRE-ENCODED VIDEO USING CHANNEL-ADAPTIVE BITSTREAM ASSEMBLY
Yi Liang, Bernd Girod, Stanford University, United States


ORAL SESSION WedAmOR6: 3D Processing
Date: 28.08.2002, 11.00-13.00, CM 3
Chair: Arnold Smeulders, Univ. of Amsterdam, Netherlands
11:00   3D PHYSICS-BASED RECONSTRUCTION OF SERIALLY ACQUIRED SLICES
Stelios Krinidis, Christophoros Nikou, Ioannis Pitas, Aristotle University of Thessaloniki, Greece
11:20   VRML ANIMATION FROM MULTI-VIEW IMAGES
Yuichi Iwadate, Miwa Katayama, Kimihiro Tomiyama, Hiroyuki Imaizumi, NHK, Japan
11:40   PERFORMANCE ANALYSIS OF A KINEMATIC HUMAN MOTION MODEL
Shiloh Dockstader, Murat Tekalp, Michel Berg, University of Rochester, USA
12:00   SHAPE RECONSTRUCTION FROM A SINGLE PHOTOGRAPH FOR 3D OBJECT RETRIEVAL AND VISUALIZATION
Carlo Colombo, Alberto Del Bimbo, Federico Pernici, University of Florence, Italy
12:20   ITERATIVE 3D SURFACE MODELLING FROM A SPARSE SET OF MATCHED FEATURE POINTS
Ning Xu, Narendra Ahuja, Beckman Institute, UIUC, USA
12:40   3D MODEL DATABASE SYSTEM BY HAND SKETCH QUERY
Yoshihiro Okada, Kyushu University, Japan


SPECIAL SESSION WedAmOR7: Vision-Based Human Machine Interface
Date: 28.08.2002, 11.00-13.00, Salle Polyvalente
Chair: Ming-Hsuan Yang, Honda Fundamental Research Labs, USA
11:00   PDH: A HUMAN-CENTRIC INTERFACE FOR IMAGE LIBRARIES
Baback Moghaddam, MERL, USA; Qi Tian, UIUC, USA; Neal Lesh, Chia Shen, MERL, USA; Thomas Huang, UIUC, USA
11:20   3D MODEL-BASED VISUAL HAND TRACKING
Thomas Huang, John Lin, UIUC, USA; Ying Wu, Northwestern U, USA
11:40   CONTEXT AWARENESS FOR INTERACTIVE ENVIRONMENTS
James Crowley, INRIA, France
12:00   ANALYSIS OF HUMAN BEHAVIOR BY COMPUTER VISION BASED APPROACHES
Jun Ohya, Waseda U, Japan
12:20   A BOTTOM-UP APPROACH FOR ACTIVITY RECOGNITION IN SMART ROOMS
Burak Ozer, Tiehan Lv, Wayne Wolf, Princeton University, USA
12:40
FACE EXPRESSION ANALYSIS ROBUST TO 3D HEAD POSE MOTION
Ana Cristina Andres del Valle, Jean-Luc Dugelay, Eurecom Institute, France


ORAL SESSION WedPmOR1: Collaborative Environments
Date: 28.08.2002, 14:15-15:55, CO 1
Chair: Oliver Schreer, Heinrich-Hertz-Institut, Germany
14:15   VIDEO REALISTIC AVATAR FOR VIRTUAL FACE-TO-FACE CONFERENCING
Yao-Jen Chang, Chien-Chia Chien, Yung-Chang Chen, National Tsing Hua Univ., ROC
14:35   A NEW CLOCK SYNCHRONIZATION ALGORITHM FOR COLLABORATIVE COMPUTING
Ruediger Schollmeier, Technical University of Munich, Germany; Shih-Ping Liou, Kilian Heckrodt, Siemens Corporate Research, USA
14:55   VIRTUAL TEAM USER ENVIRONMENTS - A STEP FROM TELECUBICLES TOWARDS DISTRIBUTED TELE-COLLABORATION IN MEDIATED WORKSPACES
Peter Kauff, Oliver Schreer, Heinrich-Hertz-Institut, Germany
15:15   MANAGING A CAMERA SYSTEM TO SERVE DIFFERENT VIDEO REQUESTS
Qiong Liu, Don Kimber, Lynn Wilcox, Matthew Cooper, Jonathan Foote, John Boreczky, FX Palo Alto Lab, US
15:35   A DYNAMIC VIDEO COMBINER FOR MULTIPOINT VIDEO CONFERENCING
Kai-Tat Fung, Wan-Chi Siu, Ngai-Fong Law, The Hong Kong Polytechnic University, Hong Kong


ORAL SESSION WedPmOR2: Multimodal Processing
Date: 28.08.2002, 14:15-15:55, CM 2
Chair: Jeroen Vendrig, Univ. of Amsterdam, Netherlands
14:15   A REVIEW ON MULTIMODAL VIDEO INDEXING
Cees Snoek, Marcel Worring, University of Amsterdam, The Netherlands
14:35   SPEAKER INDEPENDENT AUDIO-VISUAL CONTINUOUS SPEECH RECOGNITION
Luhong Liang, Xiaoxing Liu, Yibao Zhao, Xiaobo Pi, Ara Nefian, Intel Corporation, USA
14:55   EXPERIMENTAL EVALUATION OF MULTIMODAL HUMAN COMPUTER INTERFACE FOR TACTICAL AUDIO APPLICATIONS
Zeljko Obrenovic, Dusan Starcevic, FON, Yugoslavia; Emil Jovanov, University of Alabama, U.S.A.
15:15   MULTIMODAL TOPIC SEGMENTATION AND CLASSIFICATION OF NEWS VIDEO
Stephan Raaijmakers, Jurgen Den Hartog, Jan Baan, TNO TPD, Netherlands
15:35   NEW KERNELS FOR ANALYZING MULTIMODAL DATA IN MULTIMEDIA USING KERNEL MACHINES
Hrishikesh Aradhye, SRI International, USA; Chitra Dorai, IBM T. J. Watson Research Center, USA


ORAL SESSION WedPmOR3: Caching
Date: 28.08.2002, 14:15-15:55, CO 3
Chair: Cyrus Shahabi, Univ. of Southern California, USA
14:15   CACHE ON DEMAND
Sadhna Ahuja, Tao Wu, Sudhir Dixit, Nokia, USA
14:35   CACHING VIDEO OBJECTS: LAYERS VS VERSIONS?
Felix Hartanto, The Chinese University of Hong Kong, Hong Kong; Jussi Kangasharju, Institut Eurecom, France; Martin Reisslein, Arizona State University, U.S.A.; Keith Ross, Institut Eurecom, France
14:55   REPLACEMENT STRATEGIES FOR QUALITY BASED VIDEO CACHING
Stefan Podlipnig, Laszlo Böszörmenyi, University Klagenfurt, Austria
15:15   MODELING DISK CACHING POLICIES FOR VIDEO ON DEMAND SYSTEMS
Gianni Conte, Giuliano Bertoletti, University of Parma - Dip. Ingegneria dell'Informazione, Italy; Francesco Zanichelli, University of Parma - Dip. Ingegneria dell'Informa, Italy
15:35   PEER-TO-PEER MULTIMEDIA STREAMING AND CACHING SERVICE
Won J. Jeon, Klara Nahrstedt, University of Illinois at Urbana-Champaign, USA


ORAL SESSION WedPmOR4: Compressed Domain Processing
Date: 28.08.2002, 14:15-15:55, CM 1
Chair: Benoit Macq, Catholic University of Louvain, Belgium
14:15   COMPRESSED DOMAIN OBJECT TRACKING FOR AUTOMATIC INDEXING OF OBJECTS IN MPEG HOME VIDEO
Radhakrishna Achanta, National University of Singapore, Singapore; Mohan Kankanhalli, National Univeristy of Singapore, Singapore; Philippe Mulhem, National University of Singapore, Singapore
14:35   EXTRACTING COARSE BOUNDARY FEATURES FOR VIDEO PROCESSING
Ramazan Aygun, Aidong Zhang, SUNY/Buffalo, USA
14:55   COLOUR QUANTIZATION OF COMPRESSED VIDEO SEQUENCES BASED ON THE ESTIMATION OF CUMULATIVE COLOUR HISTOGRAM
Wan-Fung Cheung, Yuk-Hee Chan, The Hong Kong Polytechnic University, Hong Kong
15:15   UNIVERSAL MPEG CONTENT ACCESS USING COMPRESSED-DOMAIN SYSTEM STREAM EDITING TECHNIQUES
Ching-Yung Lin, Belle Tseng, John Smith, IBM, USA
15:35 
MPEG AUDIO BITSTREAM PROCESSING TOWARDS THE AUTOMATIC GENERATION OF SPORTS PROGRAMME SUMMARIES
David Sadlier, Sean Marlow, Noel O'Connor, Noel Murphy, Centre for Digital Video Processing, Ireland


 

SPECIAL SESSION WedPmOR5: Rate-Distortion Optimized Delivery of Realtime and Streaming Media II
Date: 28.08.2002, 14:15-15:55, CM 2
Chair: Philip A. Chou, Microsoft Research, USA
Co-chair: Heather Yu (Panasonic, USA), Wenjun Zeng (PacketVideo Corp, USA)
14:15   DIRECTED ACYCLIC GRAPH BASED SOURCE MODELING FOR DATA UNIT SELECTION OF STREAMING MEDIA OVER QOS NETWORKS
Gene Cheung, Hewlett-Pakard Laboratories, Japan, Japan; Wai-tian Tan, Hewlett-Packard Laboratories, Palo Alto, USA
14:35   DELIVERY OF MPEG VIDEO STREAMS WITH CONSTANT PERCEPTUAL QUALITY OF SERVICE
Davide Quaglia, Politecnico di Torino, Italy; Juan Carlos De Martin, IRITI-CNR, Italy
14:55   OPTIMIZED VIDEO STREAMING FOR NETWORKS WITH VARYING DELAY
Susie Wee, Wai-tian Tan, John Apostolopoulos, HP Labs, USA; Minoru Etoh, NTT DoCoMo, Japan
15:15   OPTIMAL RATE CONTROL FOR VIDEO TRANSMISSION OVER VBR CHANNELS BASED ON A HYBRID MMAX/MMSE CRITERION
Sang-Yong Lee, Antonio Ortega, university of southern california, united states
15:35   RATE-DISTORTION EFFICIENT VIDEO TRANSMISSION FROM MULTIPLE SERVERS
Abhik Majumdar, Rohit Puri, Kannan Ramchandran, University of California, Berkeley, U.S.A.


 

SPECIAL SESSION WedPmOR6: Media Apps on GPP
Date: 28.08.2002, 14:15-15:55, CM 3
Chair: Eric Debes, Intel, USA
14:15   MULTI-LEVEL MEMORY PREFETCHING FOR MEDIA AND STREAM PROCESSING
Jason Fritts, Washington University, USA
14:35   A PLATFORM-INDEPENDENT METHODOLOGY FOR PERFORMANCE ESTIMATION OF STREAMING MEDIA APPLICATIONS
Hans-Joachim Stolberg, Mladen Berekovic, Peter Pirsch, University of Hannover, Germany
14:55   OPTIMIZING DSP AND MEDIA BENCHMARKS FOR PENTIUM 4: HARDWARE AND SOFTWARE ISSUES
Daniel Etiemble, University of Toronto, Canada
15:15   CHARACTERIZING MULTIMEDIA KERNELS ON GENERAL-PURPOSE PROCESSORS
Eric Debes, William Macy, Yen-Kuang Chen, Minerva Yeung, Intel Labs, USA
15:35   PLX: A FULLY SUBWORD-PARALLEL INSTRUCTION SET ARCHITECTURE FOR FAST SCALABLE MULTIMEDIA PROCESSING
Ruby Lee, Murat Fiskiran, Princeton University, USA


Defining the Next Generation Challenges in Media Composition, Compression, and Communication R&D.

Wed August 28, 2002, Salle Polyvalente, 16h.15.

Chair/Moderator: Heather Yu, Panasonic Research, USA.

Organized by: Heather Yu, Panasonic Technologies; Wenjun Zeng, PacketVideo.

 

The Internet is a gigantic pool of rich media in the form of audio, images, video, and graphics, as well as text and hypertext. With the ability to enhance the user experience in an engaging and effective fashion, rich media are increasingly being incorporated into new network applications such as IP telephony, streaming multi-media, interactive advertisements, and Internet radio/TV.

In this panel, we intend to focus on rich media com-position, compression, and communication, as they relate to media content creation, media aggregation, media asset management, and media distribution methods and infrastructure. Panelists will draw on their substantial expertise, both in academia and industry, in addressing these issues. The goal is to raise, discuss, and possibly answer some critical questions to come to a better understanding of:

Media communication is a common theme of interest to all panelists. Motivated by the emerging trends of communication of real-time media over packet networks, deployment of broadband and content distribution networks, and deployment of integrated services networks for wireless and mobile devices, the panel would like to explore the following issues further: Where do we really need breakthroughs for media communication research, especially on real time and streaming media, to have a major impact on future information distribution and systems? What are the risky areas, where breakthroughs don't seem likely at the moment, but if research were successful then the impact would be enormous? Mobile devices are becoming platforms for multimedia communications. What business models make best sense for this emerging market? What are the technology challenges for wireless multimedia communication, especially streaming media and real time communication? If we look ahead five years, what will most surprise us in terms of rich media communication experience and technology?

Panelists:

Prof. Tsuhan Chen Since October 1997, Tsuhan Chen has been with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, where he is now a Professor.  He directs the Advanced Multimedia Processing Laboratory, striving to turn multimedia technologies from science fiction into reality.  His research interests include multimedia signal processing and communication, audio-visual interaction, biometrics, processing of 2D/3D graphics, bioinformatics, and building collaborative virtual environments.  From August 1993 to October 1997, he worked in the Visual Communications Research Department, AT&T Bell Laboratories, Holmdel, New Jersey, and later at AT&T Labs-Research, Red Bank, New Jersey, as a senior technical staff member and then a principle technical staff member. Tsuhan helped create the Technical Committee on Multimedia Signal Processing, as the founding chair, and the Multimedia Signal Processing Workshop, both in the IEEE Signal Processing Society.  His endeavor later evolved into the founding of the IEEE Transactions on Multimedia and the IEEE International Conference on Multimedia and Expo, both joining the efforts of multiple IEEE societies.  He has recently been appointed as the Editor-in-Chief for IEEE Transactions on Multimedia since 2002. Before serving as the Editor-in-Chief for IEEE Transactions on Multimedia, he also served in the Editorial Board of IEEE Signal Processing Magazine and as Associate Editor for IEEE Trans. on Circuits and Systems for Video Technology, IEEE Trans. on Image Processing, IEEE Trans. on Signal Processing, and IEEE Trans. on Multimedia.  He has co-edited a book titled Advances in Multimedia: Systems, Standards, and Networks. Tsuhan received the B.S. degree in electrical engineering from the National Taiwan University in 1987, and the M.S. and Ph.D. degrees in electrical engineering from the California Institute of Technology, Pasadena, California, in 1990 and 1993, respectively.  He received the Charles Wilts Prize for outstanding independent research in Electrical Engineering leading to a Ph.D. degree at the California Institute of Technology.  He has published many technical papers and holds thirteen U.S. patents.  He is a recipient of the National Science Foundation CAREER Award.

Dr. Leonardo Chiariglione, a national of Italy, is Vice President, Multimedia of Telecom Italia Lab, the Corporate Research Centre of the Telecom Italia Group. In February 1999, he was appointed ExecutiveDirector of the Secure Digital Music Initiative (SDMI), charged with developing technical specifications for secure digital delivery of music, position he held until March 2001. Dr. Chiariglione originated and chairs the Moving Pictures Experts Group (MPEG), the ISO standardization group which produced the MPEG-1, MPEG-2 and MPEG-4 standards that support digital audio-visual applications on diverse delivery systems, MPEG-7 and is producing MPEG-21. Dr. Chiariglione also originated the Digital Audio-Visual Council (DAVIC), the Foundation for Intelligent Physical Agents (FIPA) and the EURASIP journal "Image Communications". Dr. Chiariglione obtained his Ph.D. from the University of Tokyo, and graduated in Electronic Engineering from the Polytechnic of Turin.

Prof. Bernd Girod is Professor of Electrical Engineering in the Information Systems Laboratory of Stanford University, California. He also holds a courtesy appointment with the Stanford Department of Computer Science. His research interests include networked multimedia systems, video signal compression, and 3-d image analysis and synthesis. He received his M. S. degree in Electrical Engineering from Georgia Institute of Technology, in 1980 and his Doctoral degree "with highest honors" from University of Hannover, Germany, in 1987. Until 1987 he was a member of the research staff at the Institut für Theoretische Nachrichtentechnik und Informationsverarbeitung, University of Hannover, working on moving image coding, human visual perception, and information theory. In 1988, he joined Massachusetts Institute of Technology, Cambridge, MA, USA, first as a Visiting Scientist with the Research Laboratory of Electronics, then as an Assistant Professor of Media Technology at the Media Laboratory. From 1990 to 1993, he was Professor of Computer Graphics and Technical Director of the Academy of Media Arts in Cologne, Germany, jointly appointed with the Computer Science Section of Cologne University. He was a Visiting Adjunct Professor with the Digital Signal Processing Group at Georgia Institute of Technology, Atlanta, GA, USA, in 1993. From 1993 until 1999, he was Chaired Professor of Electrical Engineering/Telecommunications at University of Erlangen-Nuremberg, Germany, and the Head of the Telecommunications Institute I, co-directing the Telecommunications Laboratory. He has served as the Chairman of the Electrical Engineering Department from 1995 to 1997, and as Director of the Center of Excellence "3-D Image Analysis and Synthesis" from 1995-1999. He has been a Visiting Professor with the Information Systems Laboratory of Stanford University, Stanford, CA, during the 1997/98 academic year. As an entrepreneur, Prof. Girod has worked successfully with several start-up ventures as founder, investor, director, or advisor. Most notably, he has been a founder and Chief Scientist of Vivo Software, Inc., Waltham, MA (1993-98); after Vivo's aquisition, since 1998, Chief Scientist of RealNetworks, Inc. (Nasdaq: RNWK); and, since 1996, an outside Director of 8x8, Inc. (Nasdaq: EGHT). Prof. Girod was elected Fellow of the IEEE in 1998 'for his contributions to the theory and practice of video communications. He is the recipient, with Joachim Eggers, of the 2001 EURASIP Best Paper Award and has been named "Distinguished Lecturer" for the year 2002 by the IEEE Signal Processing Society.

Dr. Philip A. Chou received the B.S.E. degree from Princeton University, Princeton, NJ, in 1980, and the M.S. degree from the University of California, Berkeley, CA, in 1983, both in electrical engineering and computer science, and the Ph.D. degree in electrical engineering from Stanford University, Stanford, CA, in 1988. Since 1977, he has worked for IBM, AT&T Bell Laboratories, Princeton Plasma Physics Lab, Telesensory Systems, Speech Plus, Hughes, Xerox, VXtreme, and Microsoft, where he was involved variously in office automation, motion estimation, character recognition, speech compression, LPC and text-to-speech synthesis, compression of digitized terrain, speech and document recognition, and multimedia network communication. His research interests are data compression, pattern recognition, and multimedia processing and communication. In 1994-95, he was a consulting associate professor at Stanford University. Since 1998, he has been an affiliate professor at the University of Washington.  Currently, he is with Microsoft Corporation, in Redmond, WA. Dr. Chou serves on the IEEE Technical Committee for Image and Multidimensional Signal Processing (IMDSP).  From 1998 to 2001, he served on the editorial board of the IEEE Transactions on Information Theory as an Associate Editor for Source Coding. He is a senior member of the IEEE, a member of Phi Beta Kappa, Tau Beta Pi, Sigma Xi, and the IEEE Computer, Information Theory, Signal Processing, and Communications societies, and was an active member of the MPEG committee. He is the recipient, with Tom Lookabaugh, of the 1993 Signal Processing Society Paper award.

Prof. Edward J. Delp was born in Cincinnati, Ohio. He received the B.S.E.E. (cum laude) and M.S. degrees from the University of Cincinnati, and the Ph.D. degree from Purdue University. In May 2002 he received a Doctor of Technology (Honoris Causa) from the Tampere University of Technology in Tampere, Finland. From 1980-1984, Dr. Delp was with the Department of Electrical and Computer Engineering at The University of Michigan, Ann Arbor, Michigan. Since August 1984, he has been with the School of Electrical and Computer Engineering and the Department of Biomedical Engineering at Purdue University, West Lafayette, Indiana. In 2002 he received a chaired professorship and currently is The Silicon Valley Professor of Electrical and Computer Engineering and Professor of Biomedical Engineering at Purdue University. His research interests include image and video compression, multimedia security, medical imaging, multimedia systems, communication and information theory. Dr. Delp is a Fellow of the IEEE, a Fellow of the SPIE, and a Fellow of the Society for Imaging Science and Technology (IS&T). In 2000 he was selected a Distinguished Lecturer of the IEEE Signal Processing Society. From 1997-1999 he was Chair of the Image and Multidimensional Signal Processing (IMDSP) Technical Committee of the IEEE Signal Processing Society. From 1994-1998 he was Vice-president for Publications of IS&T. He was Co-Chair of the SPIE/IS&T Conference on Security and Watermarking of Multimedia Contents that was held in San Jose in January 1999, January 2000, January 2001, and January 2002. Dr. Delp was the General Co-Chair of the 1997 Visual Communications and Image Processing Conference (VCIP) held in San Jose. He was Program Chair of the IEEE Signal Processing Society's Ninth IMDSP Workshop held in Belize in March 1996. He was General Co-Chairman of the 1993 SPIE/IS&T Symposium on Electronic Imaging. He is the Program Co-Chair of the IEEE International Conference on Image Processing that will be held in Barcelona in 2003. From 1984-1991 Dr. Delp was a member of the editorial board of the International Journal of Cardiac Imaging. From 1991-1993, he was an Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence. From 1992-1999 he was a member of the editorial board of the journal Pattern Recognition. From 1994-2000, Dr. Delp was an Associate Editor of the Journal of Electronic Imaging. From 1996-1998, he was an Associate Editor of the IEEE Transactions on Image Processing. In 1990 he received the Honeywell Award and in 1992 the D. D. Ewing Award, both for excellence in teaching. In 2001 he received the Raymond C. Bowman Award for fostering education in imaging science from the Society for Imaging Science and Technology (IS&T). In 1990 he received a Fulbright Fellowship to visit the Universitat Politecnica de Catalunya in Barcelona, Spain. In 2002 he was awarded a Nokia Fellowship.

Dr. Dorée Duncan Seligmann is currently the director of Collaborative Applications Research at AvayaLabs. Seligmann studied anthropology at Harvard, writing a thesis that compared Irish and Irish-American pubs. Afterward, she moved to Paris, where she began a theater group. Upon returning to the United States, she earned a Ph.D. in Computer Science at Columbia University and joined Bell Labs. At Bell Labs, she helped build the Rapport multimedia conferencing system and application sharing system. She then developed Archways, an automatically generated virtual environment with 3D graphics and 3D sound. Her interest is in developing new systems that enable people to communicate more effectively and efficiently. Under the broad rubric of providing a rich user experience, this work involves issues ranging from aesthetic considerations to mechanisms to increase ease-of-use and a user's control over devices and systems. More specifically her current work centers around context-aware applications using presence, location, and the plethora of small and often wireless devices. Other activities include founding board member of Thundergulch, the Lower Manhattan Cultural Council's "new media laboratory," the book “Life Into Art: Isadora Duncan and Her World” and editor the art and technology column in IEEE Multimedia.

 

Thursday August 29

POSTER SESSION ThuAmPO1: Face Analysis and Recognition
Date: 29.08.2002, 9.00-11.00, CO Hall
Chair: Marco La Cascia, University of Palermo, Italy
*
FACIAL EXPRESSION RECOGNITION FROM VIDEO SEQUENCES
Ira Cohen, University of Illinois at Urbana-Champaign, USA; Nicu Sebe, Lieden University, Netherlands; Ashutosh Garg, University of Illinois at Urbana-Champaign, USA; Michael Lew, Lieden University, Netherlands; Thomas Huang, University of Illinois at Urbana-Champaign, USA
*
KEY POINTS BASED SEGMENTATION OF LIPS
Nicolas Eveno, Alice Caplier, Pierre-Yves Coulon, LIS, France
*
LOCALIZING THE IRIS CENTER BY REGION GROWING SEARCH
Bo Cao, Shiguang Shan, Wen Gao, Institute of Computing Technology, Chinese Academy of Sciences, China; Debin Zhao, Harbin Institute of Technology, China
*
EMBEDDED BAYESIAN NETWORKS FOR FACE RECOGNITION
Ara Nefian, Intel Corporation, USA
*
A METHOD FOR 3D FACE MODELING AND CARICATURED FIGURE GENERATION
Takayuki Fujiwara, Hiroyasu Koshimizu, SCCS, Chukyo University, JAPAN; Kouta Fujimura, Gorou Fujita, Yoshiaki Noguchi, Naoya Ishikawa, SANYO Electric Co., JAPAN
*
FAST MARCHING METHODS APPLIED TO FACE LOCATION IN VIDEOPHONE APPLICATIONS USING COLOUR INFORMATION
Prag Sharma, Richard Reilly, University College Dublin, Ireland
*
SEMANTIC FACE MATCHING
Rein-Lien Hsu, Anil Jain, Michigan State Univ., USA
*
ROBUST FACE MATCHING UNDER DIFFERENT LIGHTING CONDITIONS
Chyuan-Huei Yang, Dept. of Computer sciences, National Tsing Hua Univ., Taiwan; Shang-Hong Lai, Long-Wen Chang, Dept. of Computer Sciences, NTHU, Taiwan
*
ROBUST FACE RECOGNITION BASED ON MOTION PURSUIT
Ruoyu Wang, Thomas Huang, Univ. Illinois at Urbana Champaign, USA; Peter Stubler, Rajiv Mehrotra, Eastman Kodak Company, USA


POSTER SESSION ThuAmPO2: Hardware/Software Implementation
Date: 29.08.2002, 9.00-11.00, CO Hall
Chair: Eric Debes, Intel, USA
*
TEXTURE CODER DESIGN OF MPEG-4 VIDEO BY USING INTERLEAVING SCHEDULE
Chih-Wei Hsu, Wei-Min Chao, Yung-Chi Chang, Liang-Gee Chen, Graduate Institute of Electronics Engineering, National Taiwan University, Taiwan
*
DESIGN AND COLLECTION OF ACOUSTIC SOUND DATA FOR HANDS-FREE SPEECH RECOGNITION AND SOUND SCENE UNDERSTANDING
Satoshi Nakamura, ATR Spoken Language Translation Research Labs., Japan; Kazuo Hiyane, Mitsubishi Research Institute, Japan; Futoshi Asano, AIST, Japan; Yutaka Kaneda, Tokyo Denki University, Japan; Takeshi Yamada, Tsukuba University, Japan; Takanobu Nishiura, Wakayama University, Japan; Tetsunori Kobayashi, Waseda University, Japan; Shiro Ise, Kyoto, University; Hiroshi Saruwatari, NAIST, Japan
*
A RECONFIGURABLE DIGITAL SIGNAL PROCESSOR ARCHITECTURE FOR HIGH-EFFICIENCY MPEG-4 VIDEO ENCODING
Li-Hsun Chen, Wei-Lung Liu, Oscal T.-C. Chen, National Chung Cheng Univ., Taiwan; Ruey-Liang Ma, Industrial Technology Reserch Institute, Taiwan
*
MULTIMEDIA-APPLICATION-DRIVEN INSTRUCTION SET ARCHITECTURE SIMULATION
Ivano Barbieri, Massimo Bariani, Alberto Cabitto, Marco Raggio, University of Genoa, Italy
*
PARALLEL FILE STRIPING ON OPTICAL JUKEBOX SERVERS
Joaquin Tarraga, Axs Techologies SA, Switzerland; Roger D. Hersch, EPFL, Switzerland
*
RECONFIGURABLE AND LOW POWER 2D-DCT IP FOR UBIQUITOUS MULTIMEDIA STREAMING
Maurizio Martina, Andrea Molino, Fabrizio Vacca, Dip. Elettronica - Politecnico di Torino, ITALY
*
PCI-BASED MULTI-PROCESSOR SYSTEM FOR IMMERSIVE VIDEOCONFERENCE TERMINALS
Oliver Schreer, Michael Karl, Peter Kauff, Heinrich-Hertz-Institut Berlin, Germany
*
ON-CHIP COMMUNICATION ANALYSIS FOR MULTIMEDIA APPLICATIONS
Girish Varatkar, Radu Marculescu, Carnegie Mellon University, Dept. of ECE, USA
*
DESIGN OF A DYNAMIC SMIL PLAYER
Kari Pihkala, Petri Vuorimaa, Helsinki University of Technology, Finland
*
VIDEO APPLICATIONS ON HYPER-THREADING TECHNOLOGY
Yen-Kuang Chen, Matthew Holliman, Eric Debes, Intel Labs, US


POSTER SESSION ThuAmPO3: Multimedia Analysis and Databases
Date: 29.08.2002, 9.00-11.00, CO Hall
Chair: Fatih Porikli , Mitsubishi Electric Research Labs, USA
*
USING INDEXING STRUCTURES FOR RESOURCE DESCRIPTORS EXTRACTION FROM DISTRIBUTED IMAGE REPOSITORIES
Stefano Berretti, Alberto Del Bimbo, Pietro Pala, University of Florence, ITALY
*
REGION-BASED NONPARAMETRIC OPTICAL FLOW SEGMENTATION WITH PRE-CLUSTERING AND POST-CLUSTERING
Kai-Kuang Ma, Hai-Yun Wang, Nanyang Technological University, Singapore
*
SEMANTIC KNOWLEDGE CONSTRUCTION FROM ANNOTATED IMAGE COLLECTIONS
Ana Benitez, Shih-Fu Chang, Columbia University, USA
*
VALIDATING MPEG-21 ENCAPSULATED FUCTIONAL METADATA
Boris Rogge, Dimitri Van de Ville, Rik Van de Walle, Ignace Lemahieu, Ghent University, Belgium
*
MULTI-LAYERED VIDEOTEXT EXTRACTION METHOD
Lalitha Agnihotri, Nevenka Dimitrova, Philips Research, USA; Mario Soletic, Philips Semiconductors, Italy
*
MODELING OF VIDEO OBJECTS IN A VIDEO DATABASES
Lei Chen, M. Tamer Ozsu, School of Computer Science, University of Waterloo, Canada
*
A HIERARCHICAL IMAGE SEGMENTATION ALGORITHM
Wei Yu, Jason Fritts, Washington University, USA; Fangting Sun, Iowa State University, USA
*
A MOTION-TOLERANT DISSOLVE DETECTION ALGORITHM
C. W. Su, Department of Computer Science and Information Engineering, National Central University, Taiwan; H. R. Tyan, Department of Information and Computer Engineering, Chung Yuan Christian University, Taiwan; H. Y. Mark Liao, Institute of Applied Science and Engineering Resea, Taiwan; L. H. Chen, Department of Computer Science and Information Eng, Taiwan
*
SCALABLE SPATIAL EVENT REPRESENTATION
Jelena Tesic, Shawn Newsam, B.S. Manjunath, UC Santa Barbara, U.S.A.
*
GENERATION OF STEREOSCOPIC IMAGE SEQUENCES USING STRUCTURE AND RIGID MOTION ESTIMATION BY EXTENDED KALMAN FILTERS
Sotiris Diplaris, Nikos Grammalidis, Dimitris Tzovaras, Michael Strintzis, Informatics and Telematics Institute, Greece
*
A METHOD AND BROWSER FOR CROSS-REFERENCED VIDEO SUMMARIES
Aya Aner, Lijun Tang, John Kender, Columbia University, USA
*
STRUCTURING THE PERSONAL MULTIMEDIA COLLECTION OF A MOBILE DEVICE USER BASED ON GEOLOCATION
Marc Gelgon, Kevin Tilhou, University of Nantes, France
*
A COMPUTER VISION SYSTEM FOR KNOWLEDGE-BASED 3D SCENE ANALYSIS USING RADIO-FREQUENCY TAGS
Mustapha Boukraa, Shigeru Ando, University of Tokyo, Japan


POSTER SESSION ThuAmPO4: Audio Processing
Date: 29.08.2002, 9.00-11.00, CO Hall
Chair: John A. Sorensen, IT University of Copenhagen, Denmark
*
AUDIO SIGNAL CLASSIFICATION USING TIME-FREQUENCY PARAMETERS
Karthikeyan Umapathy, Ryerson University, Canada; Sridhar Krishnan, Ryerson Univeristy, Canada; Shihab Jimaa, University of Hertfordshire, UK
*
SPATIAL AUDITORY PROCESSING FOR A HEARING ROBOT
Jie Huang, The University of Aizu, Japan
*
PREDOMINANT PITCH CONTOUR EXTRACTION FROM AUDIO SIGNALS
Hafiz Malik, Ashfaq Khokhar, Rashid Ansari, Bruno Baillon, ECE Dept. University of Illinois at Chicago, USA
*
A NEW AUDIO SKEW DETECTION AND CORRECTION ALGORITHM
Richard Akester, Stephen Hailes, UCL, UK
*
AN EVALUATION OF SOUND SOURCE IDENTIFICATION WITH RWCP SOUND SCENE DATABASE IN REAL ACOUSTIC ENVIRONMENTS
Takanobu Nishiura, Wakayama University, Japan; Satoshi Nakamura, ATR Spoken Language Translation Research Labs., Japan
*
AUDIO MIXING FOR CENTRALIZED CONFERENCES IN A SIP ENVIRONMENT
Samer Hawwa, Ericsson Research Canada, Canada
*
MULTIRESOLUTION SPECTRAL CONVERSION FOR MULTICHANNEL AUDIO RESYNTHESIS
Athanasios Mouchtaris, Shrikanth Narayanan, Chris Kyriakakis, University of Southern California, USA
*
VISUALIZATION OF MULTIPLE LISTENER ROOM RESPONSE EQUALIZATION
Sunil Bharitkar, University of Southern California (USC), USA; Chris Kyriakakis, USC, USA
*
ON SEGMENTATION OF NARROWLY-SPACED NOISY AUDIO SIGNALS
Farook Sattar, Moe Pwint, Nanyang Technological University, Singapore; Rajamani Doraiswami, The University of New Brunswick, Canada


POSTER SESSION ThuAmPO5: Applications/Systems
Date: 29.08.2002, 9.00-11.00, CO Hall
Chair: Timothy K. Shih, Tamkang University, Taiwan
*
SURFING THE WEB ON TV: THE MHP APPROACH
Alberto Gil, Jose Pazos, Cándido López, José López, Raúl Rubio, Manuel Ramos, Rebeca Díaz, University of Vigo, Spain
*
THE COMMUNITY OF MULTIMEDIA AGENTS PROJECT
Gang Wei, Valery Petrushin, Anatole Gershman, Accenture Technology Labs, The United States
*
APPLYING MPEG-21 IN DIGITAL TELEVISION - EXAMPLE USE SCENARIOS: EPOSTCARD, EGAME, AND ETICKET
Artur Lugmayr, Samuli Niiranen, Anurag Mailaparampil, Perttu Rautavirta, Mikko Oksanen, Florina Tico, Seppo Kalli, DMI/TTKK, Finland
*
AN ABSTRACR ANIMATION MODEL FOR INTEGRATING SMIL BASIC ANIMATION ELEMENTS WITH MULTIMEDIA DOCUMENTS
Tien Tran Thuong, Cécile Roisin, Opéra project, INRIA Rhone Alpes, France
*
AUTONOMOUS PRESENTATION OF 3 DIMENSIONAL CG CONTENTS
Akiyo Nadamoto, Communications Research Laboratory, Keihanna Human Info-Communication Research Center, Japan; Takeshi Yabe, Masaki Shikata, Kobe University, Japan; Katsumi Tanaka, Kyoto University, Japan
*
THE MYTV SYSTEM - A DIGITAL INTERACTIVE TELEVISION PLATFORM IMPLEMENTATION
Bostjan Marusic, Marijan Leban, University of Ljubljana, Faculty of Electrical Engineering, Slovenia
*
VIDEO PORTAL FOR A MEDIA SPACE OF STRUCTURED VIDEO STREAMS
Takehiro Ogura, Noboru Babaguchi, Tadahiro Kitahashi, Osaka University, Japan
*
DELIVERING MULTIPLE VIDEO DIGEST FOR A LARGE-SCALE ARCHIVAL AND RETRIEVAL SYSTEM
Chih-Chang Hsu, RCAST, The University of Tokyo, Japan; Youichi Ishibashi, TAO Yamagata Video Archive Research Center, Japan; Takuyo Kogure, Matsushita Electric Industrial Co. Ltd., Japan; Fumio Hasegawa, Tohoku University of Art and Design, Japan; Terumasa Aoki, Hiroshi Yasuda, RCAST, The University of Tokyo, Japan
*
THE MERL SPOKENQUERY INFORMATION RETRIEVAL SYSTEM, A SYSTEM FOR RETRIEVING PERTINENT DOCUMENTS FROM A SPOKEN QUERY
Peter Wolf, Bhiksha Raj, Mitsubishi Electric Research Labs, USA
*
E-PLAY
Claudia Goldman, University of Massachusetts, USA; Scott Kirkpatrick, Hebrew University, Israel
*
MULTIMEDIA MEDICAL DIAGNOSTIC DOCUMENT
Rita Noumeir, Ecole de technologie superieure, Canada
*
ADDITIONAL CONTENT-RELATED SERVICE/PRODUCT OFFERING SYSTEM BASED ON NEW STANDARDS: MPEG-21 AND CONTENT ID/DOI
Hideki Sakamoto, Masanori Yamada, Takao Nakamura, Tadashi Nakanishi, NTT Cyber Solutions Labs., Japan
*
REAL-TIME VIDEO BASED MOTION CAPTURE SYSTEM BASED ON COLOR AND EDGE DISTRIBUTIONS
Yoshiaki Akazawa, Yoshihiro Okada, Koichi Niijima, Kyushu University, Japan
*
PROVIDING CONSISTENT SMIL 2.0 DOCUMENTS
Paulo Sampaio, Jean-Pierre Courtiat, LAAS-CNRS, France
*
CONTENT ACCESS AND DISTRIBUTION OF MULTIMEDIA MEDICAL DATA IN E-HEALTH
Jinman Kim, School of IT, University of Sydney, Australia; David (Dagan) Feng, Hong Kong Polytechnic University, Australia; Tom (Weidong) Cai, School of IT, University of Sydney, Australia; Stefan Eberl, Dept. of PET and Nuclear Medicine, RPA Hospital, Australia
*
MOBILE CONTEXT-AWARE STORIES
Linda Doyle, Trinity College Dublin, Ireland; Glorianna Davenport, MIT Media Lab, USA; Donal O'Mahony, Trinity College Dublin, Ireland
*
MIRACLES: MULTIMEDIA INFORMATION RETRIEVAL, CLASSIFICATION, AND EXPLORATION SYSTEM
Susumu Endo, Shuichi Shiitani, Yusuke Uehara, Daiki Masumoto, Shigemi Nagata, FUJITSU LABORATORIES LTD, Japan


ORAL SESSION ThuAmOR1: Joint Media Processing
Date: 29.08.2002, 11.00-13.00, CO 1
Chair: Jean-Philippe Thiran, EPFL, Switzerland
11:00   COMBINING AUDIO AND VIDEO FOR VIDEO SEQUENCE INDEXING APPLICATIONS
Alberto Albiol, UPV, Spain; Luis Torres, Urgell, Spain; Edward J. Delp, Purdue University, USA
11:20   ENHANCED VIDEO BROWSING USING AUTOMATICALLY EXTRACTED AUDIO EXCERPTS
Jonathan Foote, Matthew Cooper, Lynn Wilcox, FX Palo Alto Laboratory, United States
11:40   FEATURE SPACE MUTUAL INFORMATION IN SPEECH-VIDEO SEQUENCES
Torsten Butz, Jean-Philippe Thiran, ITS-DE, EPFL, Switzerland
12:00   SCENE CHANGE DETECTION BY AUDIO AND VIDEO CLUES
Shu-Ching Chen, Florida International University, School of Computer Science, USA; Mei-Ling Shyu, University of Miami, Department of Electrical and Computer Engineering, USA; Wenhui Liao, Chengcui Zhang, Florida International University, USA
12:20   SEMANTIC INDEXING OF MULTIMEDIA USING AUDIO, TEXT AND VISUAL CUES
Giridharan Iyengar, Harriet Nock, Chalapathy Neti, Martin Franz, IBM T J Watson Research Center, USA
12:40 
REAL TIME FACE DETECTION FOR MULTIMODAL SPEECH RECOGNITION
Kazumasa Murai, Information Media Laboratory, Japan; Satoshi Nakamura, ATR Spoken Language Translation Research Laboratories, Japan


ORAL SESSION ThuAmOR2: Education
Date: 29.08.2002, 11.00-13.00, CO 2
Chair: Peiya Liu, Siemens, USA
11:00   MULTIMEDIA COURSEWARE DEVELOPMENT USING INFLUENCE DIAGRAM
Timothy Shih, Lun-ping Hung, Tamkang University, Taiwan
11:20   A STUDY ON AUTOMATIC DATABASE CREATION AND SUMMARIZATION OF A VAULTING HORSE CLASS
Hisashi Miyamori, Communications Research Laboratory, Japan
11:40   MULTIMEDIA EDUCATION SYSTEM FOR INTERACTIVE EDUCATIONAL SERVICES
Hideki Sumiyoshi, Ichiro Yamada, Nobuyuki Yagi, NHK, JAPAN
12:00   WEB INFORMATION EXTRACTION FOR CONTENT AUGMENTATION
Angel Janevski, Nevenka Dimitrova, Philips Research USA, USA
12:20   SATELLITE REMOTE EDUCATION SYSTEM DESIGN AND IMPLEMENTATION USING MPEG-4 UNDER DVB COMPLIANT NETWORK
Bong-Ho Lee, Soo In Lee, ETRI, South KOREA
12:40   TOWARDS AUTTOMATING THE GENERATION OF SCORM-BASED MULTIMEDIA PRODUCT TRAINING MANUALS
Peiya Liu, Liang Hsu, Amit Chakraborty, Siemens, USA


ORAL SESSION ThuAmOR3: Image Retrieval
Date: 29.08.2002, 11.00-13.00, CO 3
Chair: Edward Chang, University of California, Santa Barbara, USA
11:00   ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN
Bin Zhang, Catalin Tomai, Aidong Zhang, State University of New York at Buffalo, USA
11:20   ROBUST COLOR-BASED IMAGE RETRIEVAL USING BIPARTITE GRAPHS
Mario Nascimento, Shengjiu Wang, Univ. of Alberta, Canada
11:40   IMAGE RETRIEVAL AND RELEVANCE FEEDBACK USING PEER INDEXING
Jun Yang, Qing Li, City University of Hong Kong, Hong Kong, China; Yueting Zhuang, Zhejiang University, China
12:00   PREFETCHING FOR CONTENT-BASED IMAGE RETRIEVAL
Janghyun Yoon, Nikil Jayant, Georgia Institute of Technology, United States
12:20   IMAGE RETRIEVAL BASED ON MULTI-SCALE EDGE MODEL
Paul Bao, Xianjun Zhang, Hong Kong Polytechnic University, Hong Kong
12:40   A STUDY OF IMAGE RETRIEVAL BY ANCHORING
Apostol (Paul) Natsev, John R. Smith, IBM Watson Research Center, USA


ORAL SESSION ThuAmOR4: User Interface
Date: 29.08.2002, 11.00-13.00, CM 1
Chair: Malcolm Slaney , IBM Research, USA
11:00   A REAL-TIME INTERACTIVE NON-VERBAL COMMUNICATION SYSTEM THROUGH SEMANTIC FEATURE EXTRACTION
Jin Hou, Yoshinao Aoki, Media Lab, Japan
11:20   KEYSTROKE RECOGNITION FOR VIRTUAL KEYBOARD
Jani Mantyjarvi, Jussi Koivumaki, Petri Vuori, NOKIA, Finland
11:40   A COST-EFFECTIVE SOLUTION FOR EYE-GAZE ASSISTIVE TECHNOLOGY
Fulvio Corno, Laura Farinetti, Isabella Signorile, Politecnico di Torino, Italy
12:00   MOSAIC FEEDBACK FOR SKETCH TRAINING AND RETRIEVAL IMPROVEMENT
Odej Kao, Ingo La Tendresse, Michael Skubowius, TU Clausthal, Germany
12:20   HAPTIC DESIGN FOR DIGITAL AUDIO
Lonny Chu, Stanford University, USA
12:40   PHYSICALLY-BASED AUDIO RENDERING OF CONTACT
Federico Avanzini, University of Padova, Italy; Matthias Rath, Davide Rocchesso, University of Verona, Italy


ORAL SESSION ThuAmOR5: Multimedia Streaming
Date: 29.08.2002, 11.00-13.00, CM 2
Chair: Ling Guan, Ryerson Univ., Canada
Co-chair: Jose A. Lay, University of Sydney, Australia
11:00   LOSS CONCEALMENTS OF SUBBAND CODED IMAGES FOR REAL-TIME TRANSMISSIONS IN THE INTERNET
Benjamin Wah, University of Illinois at Urbana-Champaign, USA; Xiao Su, Inktomi Corporation, USA
11:20   A REAL-TIME INTERNET STREAMING MEDIA TESTBED
Wolfgang Kellerer, DoCoMo Euro-Labs, Germany; Eckehard Steinbach, Munich University of Technology, Germany; Peter Eisert, Heinrich-Hertz-Institute, Germany; Bernd Girod, Stanford University, USA
11:40   EFFECTS OF CELL LOSS ON MPEG VIDEO: ANALYTICAL MODELING AND EMPIRICAL VALIDATION
Christopher Snyder, Uttam Sarkar, Dilip Sarkar, University of Miami, USA
12:00   GUARANTEEING QUALITY-OF-SERVISCE FOR DELIVERY OF COMPRESSED VIDEOS BASED ON GOP-AWARE EFFECTIVE ENVELOPES
Sheau-Ru Tong, Department of Management Information Systems, National Pingtung University of Science and Technology, Taiwan, R.O.C.; Yuan-Tse Yu, Department of Computer Science, National Chengkung University, Taiwan, R.O.C.; Chung-Ming Huang, Department of Computer Science, National Chengkung, Taiwan, R.O.C.
12:20   RTP PACKETIZATION OF MPEG-4 ELEMENTARY STREAMS
Matthias Olenroth, Hermann Hellwagner, University Klagenfurt, Department of Information Technology, Austria
12:40   GUARANTEEING QUALITY OF SERVICE FOR IMAGE TRANSMISSION BY MEANS OF HYBRID LOSS PROTECTION
Marco Grangetto, Enrico Magli, Mauro Marzo, Gabriella Olmo, Dept. of Electronics - Politecnico di Torino, Italy


SPECIAL SESSION ThuAmOR6: Benchmarking of Data Hiding Technologies
Date: 29.08.2002, 11.00-13.00, CM 3
Chair: Slava Voloshynovskiy, Univ. of Geneva, Switzerland
Co-chair: Benoit Macq (Catholic University of Louvain, Belgium ), Thierry Pun (Univ. of Geneva, Switzerland)
11:00   BLIND WATERMARKING METHOD BASED ON DWT MIDDLE FREQUENCY PAIR
Quan Yuan, Hongxun Yao, Harbin Institute of Technology, P.R.China; Wen Gao, Inst. of Computing Tech.,China Academy of Science, P.R.China; Sanghyun Joo, Electronics and Telecommunications Research Inst., KOREA
11:20   CAPACITY-SECURITY ANALYSIS OF DATA HIDING TECHNOLOGIES
Sviatoslav Voloshynovskiy, Thierry Pun, University of Geneva, Switzerland
11:40   PROVABLY OR PROBABLY ROBUST DATA HIDING?
Felix Balado, Fernando Perez-Gonzalez, University of Vigo, Spain
12:00   THE CERTIMARK BENCHMARK: ARCHITECTURE AND FUTURE PERSPECTIVES
Jan C. Vorbrüggen, MediaSec Technologies GmbH, Germany; François Cayre, TELE Lab., UC Louvain, Belgium
12:20   HUMAN VISUAL SYSTEM FEATURES ENABLING WATERMARKING
Jean-Francois Delaigle, Christophe Devleeschouwer, Benoit Macq, UCL, Belgium; Inald Lagendijck, TUD, Netherlands
12:40   WATERMARK DETECTION: BENCHMARKING PERSPECTIVES
Nikos Nikolaidis, Vasilios Solachidis, Anastasios Tefas, Ioannis Pitas, Department of Informatics, Aristotle University of Thessaloniki, Greece


ORAL SESSION ThuPmOR1: Learning - Classification Algorithms
Date: 29.08.2002, 14.15-16.15, CO 1
Chair: Richard J. Qian, Intel, USA
14:15   TOWARDS OPTIMAL CLUSTERING FOR APPROXIMATE SIMILARITY SEARCHING
Ertem Tuncel, Kenneth Rose, University of California Santa Barbara, USA
14:35   TEXTURE CLASSIFICATION BASED ON MULTIPLE GAUSS MIXTURE VECTOR QUANTIZERS
Kyungsuk Pyun, Information systems Labs., EE, Stanford university, USA; Chee Sun Won, EE, Donguk university, Korea; Johan Lim, Dept. of statistics, Stanford university, USA; Robert M. Gray, Information systems Labs., EE, Stanford university, USA
14:55   BPMS VERSUS SVMS FOR IMAGE CLASSIFICATION
Gang Wu, Edward Chang, UCSB, USA; Chung-Sheng Li, IBM T.J. Watson, USA
15:15   SPEEDING UP THE SIMILARITY SEARCH IN MULTIMEDIA DATABASE
Terrence Chen, Munehiro Nakazato, Thomas Huang, University of Illinois at Urbana-Champaign, USA
15:35   LEARNING SEMANTIC MULTIMENDIA REPRESENTATIONS FROM A SMALL SET OF EXAMPLES
Milind Naphade, Ching-Yung Lin, John Smith, IBM T. J. WATSON RESEARCH, UNITED STATES
15:55   TRADEMARK RETRIEVAL USING CONTOUR-SKELETON STROKE CLASSIFICATION
Wing Ho Leung, Tsuhan Chen, Carnegie Mellon University, U.S.A.


ORAL SESSION ThuPmOR2: Media Processing
Date: 29.08.2002, 14.15-16.15, CO 2
Chair: Andrea Cavallaro, EPFL, Switzerland
14:15   ERASING VIDEO LOGOS BASED ON IMAGE INPAINTING
Weiqi Yan, Mohan Kankanhalli, NUS, Singapore
14:35   LINKING OBJECTS IN VIDEOS BY IMPORTANCE SAMPLING
Daniel Gatica-Perez, IDIAP, Switzerland; Ming-Ting Sun, University of Washington, USA
14:55   DETECTING PATH INTERSECTIONS IN PANORAMIC VIDEO
Xinding Sun, UCSB, USA; Don Kimber, Jonathan Foote, FX Palo Alto Lab, USA; B. S. Manjunath, UCSB, USA
15:15   DETECTION OF SLIDE TRANSITION FOR TOPIC INDEXING
Chong Wah Ngo, City University of Hong Kong, HK; Ting-Chuen Pong, Hong Kong University of Science and Technology, HK; Thomas Huang, University of Illinois at Urbana Champaign, USA
15:35   REDUCING BLURRING-EFFECT IN HIGH RESOLUTION MOSAIC GENERATION
Ramazan Aygun, Aidong Zhang, SUNY/Buffalo, USA
15:55   REAL-TIME VIDEO SURVEILLANCE FOR TRAFFIC MONITORING USING VIRTUAL LINE ANALYSIS
Belle Tseng, Ching-Yung Lin, John Smith, IBM T. J. Watson Research Center, USA


ORAL SESSION ThuPmOR3: Data hiding and watermarking
Date: 29.08.2002, 14.15-16.15, CO 3
Chair: Fernando Perez-Gonzalez, University of Vigo, Spain
14:15   BIT-RATE ADAPTED WATERMARKING ALGORITHM FOR COMPRESSED IMAGES
Ludovic Guillemot, Jean-Marie Moureaux, CRAN - CNRS - University Henri Poincaré Nancy 1, France
14:35   WATERMARKING OF SETS OF POLYGONAL LINES USING FUSION TECHNIQUES
Alexia Giannoula, Nikos Nikolaidis, Dept. of Informatics, Aristotle University of Thessaloniki, Greece; Ioannis Pitas, Dept. of Informatics, Aristotle University of Thes, Greece
14:55   A PERFORMANCE ANALYSIS OF SPREAD-SPECTRUM WATERMARKING BASED ON REDUNDANT TRANSFORMS
Li Hua, James Fowler, Mississippi State University, United States
15:15   COPYRIGHT PROTECTION OF 3D IMAGES USING WATERMARKS OF SPECIFIC SPATIAL STRUCTURE
Giorgos Louizis, Anastasios Tefas, Ioannis Pitas, Aristotle University of Thessaloniki, Greece
15:35   A ROBUST STEGANOGRAPHIC WAVELET-BASED SYSTEM FOR RESISTANT MESSAGE HIDING UNDER ERROR PRONE NETWORKS
Klimis Ntalianis, Anastasios Doulamis, Nikolaos Doulamis, Stefanos Kollias, National Technical University of Athens, GREECE
15:55   ROBUST TURBO-BASED DATA HIDING FOR IMAGE AND VIDEO SOURCES
Jim Chou, Kannan Ramchandran, University of California - Berkeley, United States


SPECIAL SESSION ThuPmOR4: New Challenges for User Authentication
Date: 29.08.2002, 14.15-16.15, CM 1
Chair: Jana Dittmann, IPSI, Germany
Co-chair: Petra Wohlmacher (Reg TP, Germany), Claus Vielhauer (Darmstadt University, Germany)
14:15   TECHNIQUES FOR ICONIC IMAGE-BASED BIOMETRICS
Massimo Tistarelli, DAP University of Sassari, Italy; Andrea Lagorio, Enrico Grosso, DIST University of Genova, Italy
14:35   BIOMETRIC APPLICATIONS BASED ON HANDWRITING
Falko Ramann, Platanista, Germany; Claus Vielhauer, Ralf Steinmetz, Technical University Darmstadt, Germany
14:55   SOME RESULTS ON ROBUSTNESS, SECURITY AND USABILITY OF BIOMETRIC SYSTEMS
Gunter Lassmann, T-Systems Nova, Germany
15:15   ENHANCING THE PERFORMANCE OF PERSONAL IDENTITY AUTHENTICATION SYSTEMS BY FUSION OF FACE VERIFICATION EXPERTS
Josef Kittler, University of Surrey, United Kingdom; Marco Ballette, University of Cagliari, Italy; Jacek Czyz, University of Leuvain la Neuve, Belgium; Fabio Roli, University of Cagliari, Italy; Luc Vandendorpe, University of Louvain la Neuve, Belgium
15:35   A PROPOSAL OF WRITER VERIFICATION OF HAND WRITTEN OBJECTS
Yosuke Kato, Takayuki Hamamoto, Seiichiro Hangai, Tokyo University of Science, Japan
15:55   SMARTHCARDS WITH BIOMETRIC USER VERIFICATION
Bruno Struif, Dirk Scheuermann, FhG-SIT, Germany


ORAL SESSION ThuPmOR5: Error Resilience
Date: 29.08.2002, 14.15-16.15, CM 2
Chair: Enrico Magli, Politecnico di Torino, Italy
14:15   TEXTURE REFRESHMENT NEED METRIC FOR RESILIENT OBJECT-BASED VIDEO CODING
Luis Soares, Fernando Pereira, Instituto Superior Técnico / IT, Portugal
14:35   LSP-BASED MULTIPLE-DESCRIPTION CODING FOR REAL-TIME LOW BIT-RATE VOICE TRANSMISSIONS
Dong Lin, Benjamin Wah, Department of Electrical and Computer Engineering and the Coordinated Science Laboratory,University of Illinois, Urbana, United States
14:55   SOFT DECODING OF MULTIPLE DESCRIPTIONS
Thomas Guionnet, Christine Guillemot, Eric Fabre, IRISA-INRIA, France
15:15   FLEXIBLE REDUNDACY INSERTION IN A POLYPHASE DOWN SAMPLING MULTIPLE DESCRIPTION IMAGE CODING
Nicola Franchi, Marco Fumagalli, Rosa Lancini, CEFRIEL, Italy
15:35   CHANNEL ADAPTED SCAN-BASED MULTIPLE DESCRIPTION VIDEO CODING
Manuela Pereira, Marc Antonini, Michel Barlaud, I3S Laboratory, FRANCE
15:55   ERROR RESILIENCE OF VIDEO TRANSMISSION BY RATE-DISTORTION OPTIMIZATION AND ADAPTIVE PACKETIZATION
Yuxin Liu, School of Electrical and Computer Engineering, Purdue University at West Lafayette, U.S.A.; Paul Salama, Dept. of Electrical and Computer Engineering, IUPUI, U.S.A.; Edward Delp, School of ECE, Purdue University at West Lafayette, U.S.A.

 

Multimedia Indexing: Promises and Problems.

Thu August 29, 2002, Salle Polyvalente, 16h.30

Chair/Moderator: John Smith, IBM Research, USA.

Organized by : John Smith, IBM Research, USA.

 

In recent years, digital photos, music, video, and other forms of multimedia data have become a regular part of modern life.  The incredible growth in the amount and importance of multimedia data is continuing to be driven by further advances in multimedia-enabled computers and networked consumer electronics devices, growing storage capacities, and increasing penetration of broadband.  Furthermore, consumer and business applications such as on-line education, entertainment, and medicine are driving requirements for indexing diverse kinds of multimedia data.

Multimedia indexing holds great promise for allowing efficient and effective methods for searching, retrieving, and summarizing multimedia data.  Some of the interoperability challenges are being addressed by the recently developed MPEG-7 standard, which promises to enable interoperable multimedia description by providing a rich set of standardized tools for describing features of multimedia content in XML.  Since MPEG-7 does not standardize methods for extracting the descriptions, nor for matching and searching, we are left with having to develop the corresponding technologies.  Some of the technical challenges for multimedia indexing are being addressed in recent work on automatic feature extraction and similarity searching, multi-modal analysis and semantic classification, active learning and relevance feedback searching, and so on.  At the same time, recent multimedia retrieval benchmarking trials have revealed that usability gap still remains for multimedia retrieval systems, which indicates that we are not quite there yet.

The objective of this panel is to address critical questions concerning the promise and problems of multimedia indexing including the following:

In this panel, we examine these different dimensions of the problems and promise of multimedia indexing.  We examine the technical challenges and discuss research projects aimed at addressing them.  Finally, we conclude by making assessments about the nature and timing of technology developments in relation to the consumer and business needs for multimedia indexing

Panelists:

Prof. Edward Chang received his Ph.D. in Electrical Engineering at Stanford University in 1999. He is an Assistant Professor at the department of Electrical and Computer Engineering at the University of California, Santa Barbara. His research interests include multimedia databases and interactive TV.  He is a recipient of the IBM Faculty Partnership Award in 2000, 2001, and the NSF Career Award in 2002. He is a co-founder and CTO of a multimedia database company.

Dr. Giridharan Iyengar is a Research Staff member at IBM's T.J. Watson Research Center in Yorktown Heights, New York.   He is with the Human Language Technologies department, working on multimodal information fusion, audio-visual speech technologies, and AV speech event detection.  Prior to joining IBM Research, he completed his Ph.D. (1999) from the MIT Media Laboratory where he worked on video indexing and retrieval.  His thesis, "Characterization of Unstructured Video" looked at distributional clustering algorithms for video retrieval applied to cataloguing of home videos. The focus of this work was to build a set of tools that analyze, characterize and prepare casually shot footage for interesting reuse such as making short summaries, video postcards etc.  Giri is interested in semantic analysis and statistical modeling of video, multimodal information fusion, and multimedia indexing and retrieval.

Dr. Rainer Lienhart received a Master's degree in Computer Science and Applied Economics and a Ph.D. in computer science from the University of Mannheim, Germany on 'Methods for Content Analysis, Indexing and Comparison of Digital Video Sequences'. He was a core member of the Movie Content Analysis Project (MoCA). Since 1998 he is a Staff Researcher at Intel Labs in Santa Clara. His research interests includes image/video/audio content analysis, machine learning, scalable signal processing, scalable learning, ubiquitous and distributed media computing in heterogeneous networks, media streaming, peer-to-peer networking and mass media sharing. (http://www.lienhart.de,  http://www.videoanalysis.org).

Dr. Malcolm Slaney is a research staff member at IBM Almaden Research Center and a visiting instructor at Stanford's CCRMA.  He received his PhD in electrical engineering from Purdue University.  He is coauthor of the book "Principles of Computerized Tomographic Imaging (IEEE Press, and recently republished as a SIAM Classic in Applied Mathematics) and coeditor of the book "Computational Models of Auditory Function" (IOS Press).  While at Apple Computer, he was one of the first two users of the QuickTime software, creating a Cray port of the software for use in scientific visualization. Lately his work has been applying signal processing techniques to text and multimedia to create indexing tools.

Dr. HongJiang Zhang joined Microsoft Research Asia in 1999, where he is a Senior Researcher and the Assistant Managing Director. He has been with the Institute of Systems Science, National University of Singapore, and HP Labs, USA, as a Research Manger.  Dr. Zhang is well known in the multimedia research community for his pioneering work in video and image content analysis, representation, retrieval and browsing. He has authored 3 books, 200 referred papers and book chapters, over 30 US patents and pending applications, and numerous special issues of professional journals in multimedia processing, content-based media retrieval, and video content analysis. "Image and Video Processing in Multimedia Systems", the book he co-authored and published by Kluwer in 1995, was the first one addressed content-based image and video retrieval research. He currently serves on the editorial boards of five international journals and a dozen committees of international conferences. He was the Program Committee Co-chair of the ACM Multimedia Conference, 1999.