Opening Plenary & Keynote
A New Relevance for Multimedia When We Record Everything Personal
Gordon Bell (Microsoft Research)
Bio: Gordon Bell is a senior researcher at Microsoft Research. Gordon earned the moniker "father of the minicomputer" while serving as vice president of research and development for Digital Equipment Corporation, where he was responsible for the first mini and time-sharing computers and led the development of DEC's VAX. Gordon has been a professor at Carnegie Mellon, served as the first head of the NSF Computing Directorate, led the National Research Network panel that became the NII/GII, and is the author of books on computer technology and startups. He is a member of various professional organizations, including the National Academy of Engineering and the American Academy of Arts and Sciences, and received the 1991 National Medal of Technology. Gordon was instrumental in founding the Computer History Museum, and is digitizing his own history as part of the MyLifeBits project.

Technical Session 1: Content-based Image Retrieval
Session Chair: Alan Hanjalic
Incremental Semi-Supervised Subspace Learning for Image Retrieval
X. He (The Unversity of Chicago)
Manifold-Ranking Based Image Retrieval
J. He (Tsinghua University), M. Li, H.-J. Zhang (Microsoft Research Asia), H. Tong, C. Zhang (Tsinghua University)
Learning an Image Manifold for Retrieval
X. He (University of Chicago), W.-Y. Ma, H.-J. Zhang (Microsoft Research Asia)
A Novel Log-based Relevance Feedback Technique in Content-based
Image Retrieval
C.-H. Hoi, M. R. Lyu (The Chinese University of Hong Kong)

Technical Session 2: Networked Multimedia Applications
Session Chair: Yong Rui
Automatic Replay Generation for Soccer Video Broadcasting
J. Wang (Nanyang Technological University and Institute for Infocomm Research), C. Xu (Institute for Infocomm Research), E. Chng (Nanyang Technological University), K. Wan, Q. Tian (Institute for Infocomm Research)
Networked Multimedia Event Exploration
P. Appan, H. Sundaram (Arizona State University)
Privacy Protecting a Collection in Media Spaces
J. Wickramasuriya, M. t, S. Mehrotra, N. Venkatasubramanian (University of California at Irvine)
An Adaptive Skin Model and Its Application to Objectionable Image Filtering
Q. Zhu, C.-T. Wu, K.-T. Cheng (University of California at Santa Barbara), Y.-L. Wu (VIMA Technologies Inc.)

Art Session 1: Augmented and Virtual Spaces for Creative Learning, Collaboration and Play
Session Chair: Pamela Jennings
Living-room, Interactive, Space-Oriented Augmented Reality
R. Galantay, J. Torpus, M. Engeli (University of Art + Design Bassel)
Scenographies of the Past and Museums of the Future: From
the Wunderkammer to Body-Driven Interactive Narrative Spaces
F. Sparacino (Sensing Places)
New Ways of Worldmaking: the Alterne Platform for VR Art
M. Cavazza, J.-L. Lugrin, S. Hartley, P. Libardi, M. J. Barnes, M. Le Bras (University of Teesside), M. Le Renard (CLARTE), L. Bec (CYPRES), A. Nandi (Commediastra)

Brave New Topics - Session 1: Multimedia Service Composition:
Session Chair: Wolf-Tilo Balke and Klara Nahrstedt
A Taxonomy for Multimedia Service Composition
K. Nahrstedt (University of Illinois at Urbana-Champaign), W.-T. Balke (University of California at Berkeley)
Towards an Integrated Multimedia Service Hosting Overlay
D. Xu, X. Jiang (Purdue University)
Web Services Selection for Distributed Composition of Multimedia Content
M. Wagner, W. Kellerer (DoCoMo Communications Laboratories Europe)
Support for Service Composition in i3
K. Lakshminarayanan, I. Stoica (University of California at Berkeley), K. Wehrle (University of Tübingen)

Technical Session 3 : Audio Processing
Session Chair: Hari Sundaram
Content-based Music Structure Analysis with Applications
to Music Semantics Understanding
N. C. Maddage (Institute for Infocomm Research and National University of Singapore), C. Xu (Institute for Infocomm), M. S. Kankanhalli (National University of Singapore), X. Shao (Institute for Infocomm Research and National University of Singapore)
Real-time Backround Music Monitoring Based on Content-based Retrieval
Y. Suga, N. Kosugi, M. Morimoto (NTT Corporation)
Searching Notated Polyphonic Music Using Transportation Distances
R. Typke, R. C. Veltkamp, F. Wiering (Utrecht University)

Technical Session 4: Multimedia Streaming
Session Chair: Chitra Venkatramani
Application-Specific Path Switching: A Case Study for Streaming Video
S. Tao, R. Guérin (University of Pennsylvania)
A Framework for Robust and Scalable Audio Streaming
Y. Wang, W. Huang, J. Korhonen (National University of Singapore)
Loss-resilient On-demand Media Streaming Using Priority Encoding
C. Huang, R. Janakiraman, L. Xu (Washington University in St. Louis)

Technical and Art demonstrations Session 1
Session Chair: Michael Vernick
An Approach to Interactive Media System for Mobile Devices
E.-S. Ryu, C. Yoo (Korea University)
Range Multicast Routers for Large-Scale Deployment of Multimedia Application
N. Jiang, Y. H. Ho, K. A. Hua (University of Central Florida)
Exploiting Content-Based Networking for Video Streaming
V. S. W. Eide (Simula Research Laboratory and University of Oslo), Eliassen (Simula Research Laboratory), J. A. Michaelsen (University of Oslo)
DiMaS: Distributing Multimedia on Peer-to-Peer File Sharing Networks
T. Reti, R. Sarvas (Helsinki Institute for Information Technology)
Demonstrating a Video and Audio Web
C. Parker, A. Pang, S. Pfeiffer (CSIRO-ICT Centre)
Interactive Tele-Journalism: Low Cost, Live, Interactive
Television News Production
S. Van Every (New York University)
P-Karaoke: Personalized Karaoke System
X.-S. Hua, L. Lu, H.-J. Zhang (Microsoft Research Asia)
Demonstration of Adjusting Forward Error Correction with Quality Scaling for TCP-Friendly Streaming MPEG
H. Wu, M. Claypool, R. Kinicki (Worcester Polytechnic Institute)
A Web Based Multi-display Presentation System
F. Zhao, Q. Liu (FX Palo Alto Laboratory)
Generic Support for Personalized Mobile Multimedia Tourist Applications
A. Scherp (Oldenburg Research and Development Institute), S. Boll (University of Oldenburg)
N.A.G. (Network Auralization for Gnutella)
J. Freeman (Columbia University)
Bio-Fi: Inverse Biotelemetry Projects
D. Easterly (Syracuse University)
LEMUR: Robotic Musical Instruments
E. Singer, J. Feddersen (LEMUR)
Userradio
A. Black (Media Arts and Technology Program)

Brave New Topics - Session 2: From Context to Content: Leveraging Contextual Metadata to Infer Multimedia Content
Session Chair: Marc Davis
From Context to Content: Leveraging Context to Infer Media Metadata
M. Davis, S. King, N. Good (University of California at Berkeley), R. Sarvas (Helsinki Institute for Information Technology)
Context a in Geo-Referenced Digital Photo Collections
M. Naaman, S. Harada, Q. Wang, H. Garcia-Molina, A. Paepcke (Stanford University)
Context for Semantic Metadata
K. Haase (beingmeta, inc. and Media Lab Europe)

Technical Poster Session and Reception
Session Chairs: Svetha Venkatesh and Brian Bailey

Multimedia Analysis, Processing, & Retrieval

• MPEG-4 Based Real time Shadows H. Drumm (Technische Universitaet Ilmenau)

• A Content Based Image Retrieval System Based On The Fuzzy ARTMAP Architecture M. Uysal, F. Yarman-Vural (METU, Ankara)

• Video Segmentation Combining Similarity Analysis and Classification M. Cooper (FX Palo Alto Laboratory)

• A Robust and Accumulator-Free Ellipse Hough Transform X. Yu (Institute for Infocomm Research), H. W. Leong (National University of Singapore), C. Xu, Q. Tian (Institute for Infocomm Research)

• 3D Reconstruction and Enrichment of Broadcast Soccer Video X. Yu, X. Yan (Institute for Infocomm Research), T. S. Hay (Nanyang Technological University), H. W. Leong (National University of Singapore)

• Analyzing Discussion Scene Contents In Instructional Videos Y. Li, C. Dorai (IBM T.J. Watson Research Center)

• Unsupervised soccer video abstraction based on pitch, dominant color and camera motion analysis F. Coldefy, P. Bouthemy (IRISA/INRIA)

• Calculation of an Aggregated Level of Interest Function for Recorded Events R. Nair (Georgia Institute of Technology)

• A Color Fingerprint of Video Shot for Content Identification X. Yang, Q. Tian (Institute for Infocomm Research), E.-C. Chang (National University of Singapore)

• A Robust On-The-Fly Pitch (OTFP) Estimation Algorithm S. Sood, A. Krishnamurthy (The Ohio State University)

• Picture Quality Improvement in MPEG-4 Video Coding Using Simple Adaptive Filter K.-K. Kwon, S.-H. Im, D.-S. Lim (Embedded S/W Technology Center)

• Motion Based Retrieval of Dynamic Objects in Videos C.-B. Liu, N. Ahuja (University of Illinois at Urbana-Champaign)

• A New Method to Segment Playfield and its Applications in Match Analysis in Sports Video S. Jiang, Q. Ye, W. Gao (Chinese Academy of Sciences & Graduate School of Chinese Academy of Sciences), T. Huang (Graduate School of Chinese Academy of Sciences)

• Location-aware projection with robust 3-D viewing point detection and fast image deformation J. Shimamura, K. Arakawa (NTT Corporation)

• Efficient Block Size Selection for MPEG-2 to H.264 Transcoding G. Chen, Y.-d. Zhang, S.-x. Lin, F. Dai (Chinese Academy of Sciences)

• Enhancing Security of Frequency Domain Video Encryption Z. Liu, X. Li, Z. Dong (University of Queensland)

• Key-Dependant Decomposition Based Image Watermarking

• Indexing and Matching of Polyphonic Songs for Query-by-Singing System T.-W. Leung, C.-W. Ngo (City University of Hong Kong)

• Automatic Extraction of Motion Trajectories in Compressed Sports Videos H. Yi, D. Rajan, L.-T. Chia (Nanyang Technological University)

• Mining Emergent Structures from Mixed Media For Content Retrieval J. Ng, K. Rajaraman, E. Altman (Institute for Infocomm Research)

• An Online-Optimized Incremental Learning Framework for Video Semantic Classification J. Wu (Tsinghua University), X.-S. Hua, H.-J. Zhang (Microsoft Research Asia), B. Zhang (Tsinghua University)

• Singing Voice Detection in Popular Music T. L. Nwe, A. Shenoy, Y. Wang (National University of Singapore)

• Nonparametric Motion Model with Applications to Camera Motion Pattern Classification L.-Y. Duan (Institute for Infocomm Research), M. Xu (Nanyang Technological University), Q. Tian, C.-S. Xu (Institute for Infocomm Research)

• Phrase Structure Detection in Dance V. M. Dyaberi, H. Sundaram, J. James, G. Qian (Arizona State University)

• A Semi-Naïve Bayesian Method Incorporating Clustering with Pair-wise Constraints for Auto Image Annotation W. Jin (National University of Singapore and Fudan University), R. Shi, T. S. Chua (National University of Singapore)

• Region­of­Interest based Image Resolution Adaptation for MPEG­21 Digital Item Y. Hu, L.-T. Chia, D. Rajan (Nanyang Technological University)

• A Reversible Color Transform for 16-Bit Picture Coding N. Li, J. Bu, C. Chen (Zhejiang University)

• PLSA-based Image Auto-Annotation: Constraining the Latent Space F. Monay, D. Gatica-Perez (IDIAP Research Institute)

• Security of Human Video Objects by Incorporating a Chaos-Based Feedback Cryptographic Scheme T. Paraskevi, N. Klimis, K. Stefanos (National Technical University of Athens)

• R*-Histograms: Efficient Representation of Spatial Relations between Objects of Arbitrary Topology Y. Wang, F. Makedon, A. Chakrabarti (Dartmouth College)

• Generating 3D Views of Facial Expressions From Frontal Face Video Based on Topographic Analysis L. Yin, K. Weiss (State University of New York at Binghamton)

• Music Artist Style Identification by Semi-supervised Learning from both Lyrics and Content T. Li, M. Ogihara (University of Rochester)

• The relative effectiveness of concept-based versus content-based video retrieval M. Yang, B. M. Wildemuth, G. Marchionini (North Carolina at Chapel Hill)

• Affinity Relation Discovery in Image abase Clustering and Content-based Retrieval M.-L. Shyu (University of Miami), S.-C. Chen, M. Chen (Florida International University), C. Zhang (University of Alabama at Birmingham)

• Do not zero-pute: an efficient homespun MPEG audio layer II decoding and optimization strategy P. De Smet, F. Rooms, H. Q. Luong, W. Philips (Ghent University)

Networking Posters

• Collusion Attack on a Multi-Key Secure Video Proxy Scheme Y. Wu, F. Bao (Institute for Infocomm Research)

• Index Frame Audio Transmission J. R. Parker, K. Chung (University of Calgary)

• Supporting Continuous Consistency in Multiplayer Online Games F. W. B. Li (The Hong Kong Polytechnic University), L. W. F. Li, R. W. H. Lau (City University of Hong Kong)

• Application of packet assembly technology to digital video and VoIP traffic T. Kanda (Japan Telecom), K. Shimamura (Kochi University of Technology)

• Replication Strategies for Partitioned Media Streams in Complex Networks S. Jin (Case Western University)

• Real-time Content Analysis and Adaptive Transmission of Lecture Videos for Mobile Applications T. Liu, C. Choudary (University of South Carolina)

• Drift Reduction in Predictive Video Transmission using a Distributed Source Coded Side-Channel A. Majumdar, J. Wang, K. Ramchandran (University of California at Berkeley)

• Probability Fusion for Correlated Multimedia Streams P. K. Atrey, M. S. Kankanhalli (National University of Singapore)

• Collaboration-Aware Peer-to-Peer Media Streaming S. Ye, F. Makedon (Dartmouth College)

• Video Transport over Wireless Networks H. Garudadri, P. Sagetong, S. Nanda (Qualcomm Inc.)

• Disruption-tolerant Content-aware Video Streaming T. Liu, S. Nelakuditi (University of South Carolina)

Multimedia Tools, End-Systems, and Applications Posters

• Mobile MultiModal Presentation A. Solon, P. McKevitt, K. Curran (University of Ulster)

• Automatic Pan Control System for Broadcasting Ball Games Based on Audience's Face Direction S. Daigo, S. Ozawa (Keio University)

• Key-Dependant Decomposition Based Image Watermarking S. Hu (Polytechnic University)

• SMARXO: Towards Secured Multimedia Applications by Adopting RBAC, XML, and Object-Relational database S.-C. Chen (Florida International University), M.-L. Shyu (University of Miami), N. Zhao (Florida International University)

• A Multiple Watermarking Algorithm Based on CDMA Technique F. Zou, Z. Lu, H. Ling (Huazhong University of Science and Technology)

• Scene Tunnels for Seamless Virtual Tour J. Y. Zheng, Y. Zhou, M. Shi (Indiana University and Purdue University at Indianapolis)

• Learning Image Semantics From Users Relevance Feedback A. Shah-Hosseini, G. M. Knapp (Louisiana State University)

• SenseWeb : Collaborative Image Classification in a Multi-User Interaction Environment R. Lopez-Gulliver, H. Tochigi, T. Sato, M. Suzuki, N. Hagita (ATR Media Information Science Research Labs)

• Director in your pocket: Holistic help for the hapless home videographer B. Adams, S. Venkatesh (Curtin University of Technology)

• K-BOX: A Query-by-Singing based Music Retrieval System D. Tao, H. Liu, X. Tang (The Chinese University of Hong Kong)

• Image-based Modeling and Rendering with Geometric Proxy A. M. K. Siu, R. W. H. Lau (City University of Hong Kong)

• Automatic Music Video Generation Based on Temporal Pattern Analysis X.-S. Hua, L. Lu, H.-J. Zhang (Microsoft Research Asia)

• The Creation of a Music-Driven Digital Violinist J. Yin, A. Dhanik, D. Hsu, Y. Wang (National University of Singapore)

• Challenges of Networked Media: Integrating the Navigational Features of Browsing Histories and Media Playlists into a Media Browser A. Pang, C. Parker, S. Pfeiffer (CSIRO-ICT Centre)

• Classification of human actions using face and hands detection H. Ikeda, M. Maeda, N. Kato, H. Kashimura (Fuji Xerox Co., Ltd.)

• Interactive Manipulation of Replay Speed While Listening to Speech Recordings W. Hürst, T. Lauer, G. Götz (Albert-Ludwigs Universität Freiburg)

• Ambulant: A Fast, Multi-Platform Open Source SMIL Player D. C. A. Bulterman, J. Jansen, K. Kleanthous, K. Blom, D. Benden (Centrum voor Wiskunde en Informatica)

• Designing Experiential Environments for Management of Personal Multimedia R. Singh (San Francisco State University), R. Knickmeyer, P. Gupta, R. Jain (Georgia Institute of Technology)

• Avatar-mediated face tracking and lip reading for human computer interaction X. Wei, L. Yin (State University of New York at Binghamton), Z. Zhu, Q. Ji (Rensselaer Polytechnic Institute)

• Possibilities and Limitations of Immersive Free Hand Expression: a Case Study with Professional Artists W. Mäkelä (Helsinki University of Art and Design), M. Reunanen, T. Takala (Helsinki University of Technology)

• Cortina: A System for Large-scale, Content-based Web Image Retrieval T. Quack, U. Mönich, L. Thiele, B. S. Manjunath (University of California at Santa Barbara)

• Seeing Sounds: Exploring Musical Social Networks P. D. Adamczyk (University of Illinois at Urbana-Champaign)

• User-assisted Tools for Concurrency Control in Distributed Multimedia Collaborations A. Sabbir, K. Ravindran (City University of New York)

• Facial Expression Representation and Recognition Based on Texture Augmentation and Topographic Masking L. Yin, J. Loi, W. Xiong (State University of New York at Binghamton)

• Grouping Web Image Search Result X.-J. Wang (Microsoft Research Asia and Tsinghua University), W.-Y. Ma (Microsoft Research Asia), Q.-C. He (Microsoft Research Asia and School of Mathematical Sciences), X. Li (Tsinghua University)

• Tracking Text in MPEG Videos J. Gllavata, R. Ewerth (University of Siegen), B. Freisleben (University of Marburg)

Art Poster Session
Session Chair: Alex Jaimes
DATAREADER: A Tool for Art and Science Collaborations
A. Polli (Hunter College)
Composing the Digital Rainstick
D. Birchfield (Arizona State University)
Tools Used While Developing Auracle: A Voice-Controlled
Networked Instrument
K. Varnik (Akademie Schloss Solitude), J. Freeman (Columbia University), C. Ramakrishnan (Akademie Schloss Solitude)
ARIA: An Adaptive and Programmable Media-flow Architecture
for Interactive Arts
L. Peng, K. S. Candan, K. D. Ryu, K. S. Chatha, H. Sundaram (Arizona State University)
Using Web Frequency Within Multi-Media Exhibitions
D. A. Shamma, S. Owsley (Northwestern University), S. Bradshaw (The University of Iowa), K. J. Hammond (Northwestern University)

Art Exhibit Reception at Macy Gallery

Wednesday, October 13, 2004

Technical Best Paper Contest Session
Session Chair: Rainer Lienhart
Multi-Level Annotation of Natural Scenes Using Dominant
Image Components and Semantic Concepts
J. Fan, Y. Gao, H. Luo (University of North Carolina at Charlotte)
Learning Query-Class Dependent Weights in Automatic Video Retrieval
R. Yan, J. Yang, A. G. Hauptmann (Carnegie Mellon University)
Family Ensemble: A Collaborative Musical Edutainment System
for Children and Parents
C. Oshima (ATR Media Information Science Labs), K. Nishimoto (Japan Advanced Institute of Science and Technology), M. Suzuki (ATR Media Information Science Labs),

Technical Session 6: Learning in Multi-Modal a
Session Chair: Edward Chang
Multimodal Concept-Dependent Active Learning for Image Retrieval
K.-S. Goh, E. Y. Chang, W.-C. Lai (VIMA Technologies)
Optimal Multimodal Fusion for Multimedia a Analysis
Y. Wu, E. Y. Chang (University of California at Santa Barbara), K. C.-C. Chang (University of Illinois at Urbana-Champaign), J. R. Smith (IBM T.J. Watson Research Center)
Naming Every Individual in News Video Monologues
J. Yang, A. G. Hauptmann (Carnegie Mellon University)

Technical and Art demonstrations Session 2:
Session Chair: James Griffioen
• Art Demo: Remote Interactive Graffiti
J. Foote, D. Kimber (FX Palo Alto Laboratory)
• Art Demo: 15 Seconds of Fame - An interactive, computer-vision based art installation
B. Batagelj, F. Solina, P. Peer (University of Ljubljana)
• Art Demo: The Association Engine: A Free Associative Digital Improviser
S. Owsley, D. A. Shamma, K. J. Hammond (Northwestern University), S. Bradshaw (The University of Iowa), S. Sood (Northwestern University)
• Reading movies - an integrated DVD player for browsing movies and their scripts
R. Ronfard (INRIA Rhone Alpes)
• Advanced User Interfaces for Dynamic Video Browsing
W. Hürst, G. Götz, P. Jarvers (Albert-Ludwigs-Universität Freiburg)
• METIS: a flexible abase founion for unified media management
R. King, N. Popitsch (Research Studio Digital Memory Engineering), U. Westermann (University of Vienna)
• A 3D Reconstruction and Enrichment System for Broadcast Soccer Video
X. Yan, X. Yu (Institute for Infocomm Research), T. S. Hay (Nanyang Technological University)
• Intuitive and Effective Interfaces for WWW Image Search Engines
Z.-W. Li, X. Xie (Microsoft Research Asia), H. Liu, X. Tang (The Chinese University of Hong Kong), M. Li, W.-Y. Ma (Microsoft Research Asia)
• GURU: A Multimedia Distance-Learning Framework for Users with Disabilities
V. Balasubramanian, N. Venkatasubramanian (University of California at Irvine)
• A Visuospatial Memory Cue System for Meeting Video Retrieval
T. Nagamine, A. Jaimes, K. Omura, K. Hirata (Fuji Xerox Co., Ltd.)
• Non-Parametric Motion Model
L.-Y. Duan (Institute for Infocomm Research), M. Xu (Nanyang Technological University), Q. Tian, C.-S. Xu (Institute for Infocomm Research)
• Fast and Robust video clip search using index structure
L.-Y. Duan, J.-S. Yuan, Q. Tian, C.-S. Xu (Institute for Infocomm Research)
• Audio Keyword Generation for Sports Video Analysis
M. Xu (Nanyang Technological University), L.-Y. Duan (Institute for Infocomm Research), L.-T. Chia (Nanyang Technological University), C.-s. Xu (Institute for Infocomm Research)
• Concept-Oriented Video Skimming via Semantic Video Classification
H. Luo, J. Fan (University of North Carolina at Charlotte)

Banquet and Boat Tour

Video Demonstration Session
Session Chair: Frank Nack
A Personal Projected Display
M. Ashdown (University of Tokyo), P. Robinson (University of Cambridge)
First-year Students' Paper Chase - Mobile Location-Aware Multimedia Game
P. Klante, J. Krösche, D. Ratt (Oldenburg Research and Development Institute), S. Boll (University of Oldenburg)
Mobile Media Metadata: Metadata Creation System for Mobile Images
M. Davis (University of California at Berkeley)
Físchlár @ TRECVID2003: System Description
C. Gurrin, H. Lee, A. F. Smeaton (Dublin City University)
An EPIC Enhanced Meeting Environment
Q. Liu, F. Zhao, J. Doherty, D. Kimber (FX Palo Alto Laboratory)
The Evolving Oblique: The Embodiment of a Virtual Topology
J. Walker (University of Cambridge), S. Bluemm (I.A.M.A.S.), B. Haslett (Dartmouth College)

Doctoral Symposium - Session 1
Session Chair: Paal Halvorsen
Supporting Adaptive Remote Access to Multiresolutional or Hierarchical a for Large User Groups
D. Gotz (University of North Carolina at Chapel Hill)
Semantic-Aware Automatic Video Editing
S. Bocconi (CWI)
Thematic Alignment of Documents with Meeting Dialogs
D. Mekhaldi, D. Lalanne (Département d'Informatique)