Program:

This is the almost-finalized program for the workshop. Peer-reviewed oral sessions, peer-reviewed poster sessions, special sessions, panel, and keynote talks are all included here.

Friday September 28, 2007

Opening: 8:30AM - 10:00AM

• Opening Remarks and Introduction of Speaker. Jia Li (The Pennsylvania State University, USA)
• Keynote Speech. Michael Lesk (Rutgers University, USA)

Coffee break 10:00AM - 10:20AM

Oral Session 1: 10:20AM - 12:00PM Image Retrieval and Multimedia Modeling
Chair: Marco Bertini, University of Florence, Italy

1. Regularized Regression on Image Manifold for Retrieval, Deng Cai (University of Illinois at Urbana Champaign, US) et al.
2. Clustering Near-duplicate Images in Large Collections, Jun Jie Foo (RMIT University, AU)
3. Learning semantic categories for 3D Model Retrieval, Ryutarou Ohbuchi (University of Yamanashi, JP)
4. Learning User Intention in Relevance Feedback using Optimization, Jian Guan (University of Nottingham, UK); Guoping Qiu (University of Nottingham, UK)
5. Unsupervised Content-Based Indexing for Sports Video Retrieval, Michael Fleischman (MIT, US); Deb Roy (MIT, US)

Lunch break 12:00PM - 13:30PM

Poster Session 1: 13:30PM - 15:00PM Multimedia Retrieval and Modeling
Chair: Jia Li, The Pennsylvania State University

1. Effective Retrieval of Polyphonic Audio with Polyphonic Symbolic Queries, Iman Suyoto (RMIT, AU); Alexandra Uitdenbogerd (RMIT, AU); Falk Scholer (RMIT, AU)
2. Visual Language Modeling for Image Classification, Lei Wu (University of Science and Technology of China, CN); Mingjing Li (Microsoft Research Asia, CN); Zhiwei Li (Microsoft Research Asia, CN); Wei-Ying Ma (Microsoft Research, China, CN); Nenghai Yu (University of Science and Technology of China, CN)
3. Optimal Decomposition of P2P Networks based on File Exchange Patterns for Multimedia Content Search & Replication, Nikolaos Doulamis (National Technical University of Athens, GR); Pantelis Karamolegkos (National Technical University of Athens, GR); Anastasios D. Doulamis (National Technical University of Athens, GR); Ioannis Nikolakopoulos (National Technical University of Athens, GR)
4. Music Similarity: Improvements of Edit-based Algorithms by Considering Music Theory, Matthias Robine (University of Bordeaux, FR); Pierre Hanna (University Bordeaux 1, FR); Pascal Ferraro (University Bordeaux 1, FR)
5. Sample-based Creation of Peer Summaries for Efficient Similarity Search in Scalable Peer-to-Peer Networks, Soufyane El Allali (Bamberg University, DE); Daniel Blank (Bamberg University, DE); Wolfgang M|ller (Bamberg University, DE); Andreas Henrich (Bamberg University, DE)
6. Tempo Induction Algorithm in MP3 Compressed Domain, Antonello D'Aguanno (Universit` degli Studi di Milano, IT); Giancarlo Vercellesi (University of Milan, IT)
7. Visual and Textual Fusion for Region Retrieval From Both Bayesian Reasoning and Fuzzy Matching Aspects, Rongrong Ji (Harbin Institute of Technology, CN); Yao Hongxun (Harbin Institute of Technology, HK)
8. Stratified Helix Information of Medial-axis-points Matching for 3D Model Retrieval, Ji Jia (Xi'an Jiaotong Univ., CN); Zheng Qin (Tsinghua University, CN); Jiang Lu (Xi'an Jiaotong Univ., CN)

Poster Session 2: 13:30PM - 15:00PM Video Retrieval and Annotation
Chair: Jia Li, The Pennsylvania State University

1. Exploiting Redundancy in Cross-Channel Video Retrieval, Bouke Huurnink (University of Amsterdam, NL); Maarten de Rijke (University of Amsterdam, NL)
2. Adapting Appearance Models of Semantic Concepts to Particular Videos via Transductive Learning, Ralph Ewerth (University of Marburg, DE); Bernd Freisleben (University of Marburg, DE)
3. Evaluating Bag-of-Visual-Words Representations in Scene Classification, Jun Yang (Carnegie Mellon University, US); Yu-Gang Jiang (City University of Hong Kong, HK); Alexander Hauptmann (Carnegie Mellon University, US); Chong-Wah Ngo (City University of Hong Kong, HK)
4. Searching For Repeated Video Sequences, Tolga CAN (Bilkent University, TR); Pinar Duygulu (Bilkent University, TR)
5. TV Ad Video Categorization with Probabilistic Latent Concept Learning, Jinqiao Wang (Institute of Automation(IA) Chinese Academy of Sciences(CAS), CN); Ling-Yu Duan (Institute for Infocomm Research, SG); Lei Xu (Institute of Automation, CN); Hanqing Lu (the Institute of Automation, Chinese Academy of Sciences, CN); Jesse Jin (University of Newcastle, AU)
6. Building a Comprehensive Ontology To Refine Video Concept Detection, Zheng-Jun Zha (University of Science and Technology of China, CN); Tao Mei (Microsoft Research Asia, CN); Zengfu Wang (University of Science and Technology of China, CN); Xian-Sheng Hua (Microsoft Research Asia, CN)
7. Scene Duplicate Detection from Videos Based on Trajectories of Feature Points, Shin'ichi Satoh (National Institute of Informatics, JP)

Coffee break 15:00PM - 15:30PM

Special Session 1: 15:30PM - 17:30PM Semantic Indexing of Consumer and Web Videos
Chair: Shih-Fu Chang, Columbia University

1. Kodak Consumer Video Benchmark Data Set: Concept Definition and Annotation
   Alexander C. Loui, Jiebo Luo, Shih-Fu Chang, Dan Ellis, Wei Jiang, Lyndon Kennedy, Keansub Lee, Akira Yanagawa
   (Columbia University, US, and Kodak Researck, US)
2. Large-Scale Multimodal Semantic Concept Detection for Consumer Video
   Shih-Fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Alexander C. Loui, Jiebo Luo
   (Columbia University, US, and Kodak Researck, US)
3. Multi-Modal Web Video Categorization
   Linjun Yang, Jiemin Liu, Tao Mei, Xiaokang Yang, Xian-Sheng Hua
   (Microsoft, CN)
4. Watch What I Watch: Using Community Activity To Understand Content
   David A. Shamma, Ryan Shaw, Peter L. Shafton, Yiming Liu
   (Yahoo! Research, US)
5. Learning People Annotation from the Web via Consistency Learning
   Jay Yagnik, Atiq Islam
   (Google Inc., US)
6. ITEMS: Intelligent Travel Experience Management System
   Chih-Chieh Liu, Chun-Hsiang Huang, Wei-Ta Chu, and Ja-Ling Wu
   (National Taiwan University, TW)

---

Saturday September 29, 2007

Opening: 8:30AM - 10:00AM

• Opening Remarks and Introduction of Speaker. Alberto Del Bimbo (University of Florence, Italy)
• Keynote Speech. Arnold Smeulders (University of Amsterdam, The Netherlands)

Coffee break 10:00AM - 10:20AM

Oral Session 2: 10:20AM - 12:00PM Video Retrieval
Chair: Jiebo Luo, Kodak Research

1. Video Diver: Generic Video Indexing with Diverse Features, Dong Wang (Tsinghua University, CN); Xiaobing Liu (Tsinghua University, CN)
2. Combining Multimodal Preferences for Multimedia Information Retrieval, Eric Bruno (University of Geneva, CH); Jana Kludas (University of Geneva, CH); Stephane Marchand-Maillet (University of Geneva, CH)
3. Trademark matching and retrieval in sports video databases, Andrew Bagdanov (University of Florence, IT); Lamberto Ballan (University of Florence, IT); Marco Bertini (Universit` di Firenze, IT); Alberto Del Bimbo (University of Firenze, IT)
4. RoleNet: Treat a Movie as a Small Society, Chung-Yi Weng (National Taiwan University, TW); Wei-Ta Chu (National Taiwan University, TW); Ja-Ling Wu (National Taiwan University, TW)
5. Semantic-Event Based Analysis and Segmentation of Wedding Ceremony Videos, Wen-Huang Cheng (National Taiwan University, TW); Yung-Yu Chuang (National Taiwan University, TW); Bing-Yu Chen (National Taiwan University, TW); Ja-Ling Wu (National Taiwan University, TW); Shao-Yen Fang (National Taiwan University, TW); Yin-Tzu Lin (National Taiwan University, TW); Chi-Chang Hsieh (National Taiwan University, TW); Chen-Ming Pan (National Taiwan University, TW); Wei-Ta Chu (National Taiwan University, TW); Min-Chun Tien (National Taiwan University, TW)

Lunch break 12:00PM - 13:30PM

Panel Session: 13:30PM - 15:00PM New Challenges in Multimedia Research for the Increasingly Connected and Fast Growing Digital Society
Chair: Jia Li, The Pennsylvania State University
Panelists:
Shih-fu Chang (Columbia University, USA)
Michael Lesk (Rutgers University, USA)
Rainer Lienhart (University of Augsburg, Germany)
Jiebo Luo (Eastman Kodak Research, USA)
Arnold Smeulders (University of Amsterdam, The Netherlands)

Coffee break 15:00PM - 15:30PM

Special Session 2: 15:30PM - 17:00PM Personalized Multimedia Information Retrieval
Chair: Nicu Sebe, University of Amsterdam (The Netherlands)

1. Personalized Multimedia Retrieval: The New Trend?
   Nicu Sebe (University of Amsterdam, NL), Qi Tian (University of Texas)
2. Browsing visual collections using graphs
   Marcel Worring, Ork de Rooij and Ton van Rijn (University of Amsterdam, NL)
3. Personalized Retrieval of Sports Video
   Yifan Zhang, Xiaoyu Zhang, Changsheng Xu, Hanqing Lu (National University of Singapore, SG)
4. Evaluating the Implicit Feedback Models for Adaptive Video Retrieval
   Frank Hopfgartner, Joemon Jose (University of Glasgow, UK)

This schedule is subject to change. Last updated: August 1, 2007.