2nd International Workshop on Semantic Learning Applications in Multimedia (SLAM)

In association with CVPR 2007

Minneapolis, MN, USA
June 18, 2007

Sponsored by


research.kodak.com

New! Program (.pdf) (.html)

Important Dates

Paper submission: 04/02/07
Notification of acceptance: 04/20/07
Receipt of camera ready copy: 04/27/07
Workshop: 06/18/07

Organization

General Chairs:

Tom Huang, University of Illinois at Urbana-Champaign
Jiebo Luo, Kodak Research Labs
Milind Naphade, IBM T J Watson Research Center

Program Committee:

Selim Aksoy, Bilkent University
Kobus Barnard, University of Arizona
Serge Belongie, UCSD
Matthew Boutell, Rose-Hulman Institute of Technology
Christopher Brown, University of Rochester
Tat-Seng Chua, NUS
Li Deng, Microsoft Research
Guoliang Fan, Oklahoma State University
Jianping Fan, University of North Carolina at Charlotte
Alan Hanjalic, Delft University of Technology
Anthony Hoogs, GE Global Research
Xian-Sheng Hua, Microsoft Research Asia
Horace Ip, City University of Hong Kong
Qiang Ji, Rensselaer Polytechnic Institute
Jim Little, UBC
Yunqian Ma, Honeywell Research
Nemanja Petrovic, Google, Inc.
Andreas Savakis, Rochester Institute of Technology
Nicu Sebe, U Amsterdam
Mubarak Shah, UCF
John R. Smith, IBM
Rahul Sukthankar, Intel Research Pittsburg
Qibin Sun, Institute for Infocomm Research
Qi Tian, University of Texas at San Antonio
Antonio Torralba, MIT
George Tzanetakis, University of Victoria
James Wang, Pennsylvania State University
Yi Wu, Intel Research
Zhongfei Zhang, SUNY Binghamton
Song-Chun Zhu, UCLA

Scope

The use of semantic knowledge in multimedia is rapidly becoming more widespread and significant. In areas such as multimedia content analysis, media integration, semantic cues and knowledge are being used to achieve performance that is not attainable by purely bottom-up, data-driven approaches. In many applications, meaningful multimedia content recognition is not possible without contextual, semantic support. However, many fundamental challenges still remain.

This workshop will bring together an interdisciplinary group of researchers in computer vision, speech/music recognition, knowledge representation and ontologies, machine learning, natural language and other areas to examine the issues and recent results in using semantic knowledge to enhance multimedia. Recent progress in machine learning has enabled the rigorous management of uncertainty in large-scale reasoning problems, and this has stimulated the use of semantic methods and reasoning in multimedia. Simultaneously, the natural language and artificial intelligence communities have developed large computational models and databases of semantic knowledge. The multimedia communities are using both evidential reasoning methods and semantic knowledgebases to fuse multiple data sources for intelligent multimedia content analysis, integration, and delivery.

Papers are solicited in all disciplines related to the central theme, including but not limited to:

Paper Submission

In keeping with the spirit of a workshop, submitted papers may emphasize intellectual risks and argue for ideas that do not yet have comprehensive experimental support. Hence papers may not need describe fully developed algorithms, methods, or results as would normally be required for acceptance at CVPR.

Papers describing novel, unpublished research are solicited in the areas listed above and closely related topics. Reviewing will be by members of the program committee. Each paper will receive at least two reviews. Acceptance will be based on relevance to the workshop, novelty, and technical quality. Papers should be at most 8 pages in length, in the same style format as CVPR, and encoded as pdf.

All accepted papers will be included in the electronic CVPR proceedings.

NEW for Authors! Electronic Submission Instructions Please click on the link below to register with the EDAS conference management system after Feb 15, 2007:

http://edas.info/Tyn.php?c=5381

You may not have an account with EDAS yet. Please use your email address as the user name, and leave the password field blank. EDAS will then create an account and email you the password. Use the password to login to EDAS and upload your paper in PDF format. You may choose to show author information or not in the paper, and the reviews will be either open or blind accordingly.

Best Paper Award

The IEEE PAMI TC is sponsoring a Best Paper award for each of the CVPR 2007 workshops. All accepted papers will be automatically considered for the SLAM 2007 Best Paper award. Presentation quality will be a factor in the award decision. The winner will be announced at the panel discussion at the end of the workshop.

Useful Links

CVPR 2007

Kodak Research Labs (KRL)

Career Opportunities at Kodak (Please see Job Requisition # 11250BR)

Program

Monday, Jun 18

7:45 AM - 8:30 AM

Breakfast

8:30 AM - 8:40 AM

Welcome and Opening Remarks

Chairs: Tom Huang, Jiebo Luo, and Milind Naphade

8:40 AM - 9:25 AM

Morning Keynote: Antonio Torralba, CSAIL, MIT

What could you do if you had a huge collection of annotated images?

9:25 AM - 10:10 AM

Session 1: Semantic Image Annotation

Kernel Sharing With Joint Boosting For Multi-Class Concept Detection  
Wei Jiang (Columbia University, USA); Shih-Fu Chang (Dept. of E.E. , Columbia Univ., USA); Alexander Loui (Eastman Kodak, USA)
Automatic Image Annotation by Ensemble of Visual Descriptors  
Emre Akbas (University of Illinois at Urbana-Champaign, USA); Fatos Yarman Vural (Middle East Technical University, Turkey)
Home Interior Classification using SIFT Keypoint Histograms  
Brian Ayers (Rose-Hulman Institute of Technology, USA); Matthew Boutell (Rose-Hulman Institute of Technology, USA)

10:10 AM - 10:30 AM

AM Break

10:30 AM - 11:30 AM

Session 2: Object and Event Recognition

Recognizing Groceries in situ Using in vitro Training Data  
Michele Merler (University of Trento, Italy, Italy); Carolina Galleguillos (UC San Diego, USA); Serge Belongie (UC San Diego, USA)
Hierarchical Recognition of Human Activities Interacting with Objects  
Michael Ryoo (University of Texas at Austin, USA); Jake Aggarwal (U. Texas, USA)
Accurate Dynamic Sketching of Faces from Video  
Zijian Xu (University of California at Los Angeles, USA); Jiebo Luo (Eastman Kodak Company, USA)
Scene Segmentation and Categorization Using NCuts  
YanJun Zhao (Dept CS of Tsinghua university, P.R. China); Tao Wang (Intel China Research Center, P.R. China); Peng Wang (Intel China research center, P.R. China); Yangzhou Du (Intel China Research Center, P.R. China)

12:30 PM - 2:00 PM

Lunch

2:00 PM - 3:00 PM

Afternoon Keynote: Dennis Moellman, Program Manager, Disruptive Technology Office (formerly ARDA)

The VACE Research Program: Video Analysis and Content Extraction

3:00 PM - 3:10 PM

PM Break

3:10 PM - 3:55 PM

Session 3: Multimedia Search and Retrieval

Fusing Local Image Descriptors for Large-Scale Image Retrieval  
Eva Hoerster (Univeristy of Augsburg, Germany); Rainer Lienhart (Univ of Augsberg, Germany)
Diverse Active Ranking for Multimedia Search  
Shyamsundar Rajaram (University of Illinois at Urbana-Champaign, USA); Charlie Dagli (University of Illinois at Urbana-Champaign, USA); Nemanja Petrovic (Google Inc., USA); Thomas Huang (University of Illinois at Urbana-Champaign, USA)
Using Group Prior to Identify People in Consumer Images  
Andrew Gallagher (Eastman Kodak Company, USA); Tsuhan Chen (CMU, USA)

3:55 PM - 4:40 PM

Session 4: Audio and Video Analysis

A Multimodality Framework for Creating Speaker/Non-Speaker Profile  
Jehanzeb Abbas (University of Illinois at Urbana Champaign, USA); Charlie Dagli (University of Illinois at Urbana-Champaign, USA); Thomas Huang (University of Illinois at Urbana-Champaign, USA)
Segmental Hidden Markov Models for View-based Sport Video Analysis  
Yi Ding (Oklahoma State University, USA); Guoliang Fan (Oklahoma State University, USA)
Salient Object Detection on Large-Scale Video Data  
Hong Lu (Fudan University, P.R. China)

4:40 PM - 5:10 PM

Panel Discussion

Panel: Tom Huang, Jiebo Luo, Dennis Moellman, Milind Naphade, Antonio Torralba

Best Paper Award

The SLAM 2007 Best Paper award will be announced at the end of the panel discussion. Note that presentation quality will be a factor in the award decision.