The Fifth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision

IMPORTANT DATES:
- Submission deadline: 11:59pm EST, March 17, 2006
- Notification: April 17, 2006
- Final versions of accepted papers due: April 24, 2006

**Please note that biological vision researchers working in the field of perceptual organization are encouraged to submit work that may stimulate new directions of research in the computer vision community.

THEME:
Perceptual Organization is the process of establishing a meaningful relational structure over raw visual data, where the extracted relations correspond to the physical structure of the scene. A driving motivation behind perceptual organization research in computer vision is to deliver representations needed for higher-level visual tasks such as object detection, object recognition, activity recognition and scene reconstruction. Because of its wide applicability, the potential payoff from perceptual organization research is enormous.

The 5th IEEE POCV Workshop, to be held in conjunction with CVPR 2006 (New York), will bring together experts in perceptual organization and related areas to report on recent research results and to provide ideas for future directions.

PREVIOUS IEEE POCV WORKSHOPS:
* 2004 CVPR (Washington, DC)
* 2001 ICCV (Vancouver, Canada)
* 1999 ICCV (Crete, Greece)
* 1998 CVPR (Santa Barbara, CA)

SCOPE:
Papers are solicited in all areas of perceptual organization, including but not limited to:

• image segmentation
• feature grouping
• texture segmentation
• contour completion
• spatiotemporal/motion segmentation
• figure-ground discrimination
• integration of top-down and bottom-up methods
• perceptual organization for object or activity detection/recognition
• unification of segmentation, detection and recognition
• biologically-motivated methods
• neural basis for perceptual organization
• learning in perceptual organization
• graphical methods
• natural scene statistics
• evaluation methods

ALGORITHM EVALUATION:
Research progress in perceptual organization depends in part on quantitative evaluation and comparison of algorithms. Authors reporting results of new algorithms are strongly encouraged to objectively quantify performance and compare against at least one competing approach.

BROADER ISSUES:
Perceptual organization research faces a number of challenges. One is defining what the precise goal of perceptual organization algorithms should be. What kind of representation should they deliver? What databases should be used for evaluation? How can we quantify performance to allow objective evaluation and comparison between algorithms? How do we know when we�ve succeeded? To try to meet these challenges, we particularly encourage contributions of a more general nature that attempt to address one or more of these questions. These may include definitional papers, theoretical frameworks that might apply to multiple different perceptual organization problems, establishment of useful databases, modeling of underlying natural scene statistics, evaluation methodologies, etc. Biological Motivation

BIOLOGICAL MOTIVATION:
Much of the current work in perceptual organization in computer vision has its roots in qualitative principles established by the Gestalt Psychologists nearly a century ago, and this link between computational and biological research continues to this day. Following this tradition, we specifically invite biological vision researchers working in the field of perceptual organization to submit work that may stimulate new directions of research in the computer vision community.

WORKSHOP OUTPUT:
All accepted papers will be included in the Electronic Proceedings of CVPR, distributed on DVD at the conference, and will be indexed by IEEE Xplore. We are also exploring the possibility of a special journal issue on perceptual organization in computer vision, with a separate call for papers.

PAPER SUBMISSION:
Submission is electronic, and must be in PDF format. Papers must not exceed 8 double-column pages. Submissions must follow standard IEEE 2-column format of single-spaced text in 10 point Times Roman, with 12 point interline space. All submissions must be anonymous. Please us the IEEE Computer Society CVPR format kit. Stay tuned for exact details on how to submit.

In submitting a paper to the POCV Workshop, authors acknowledge that no paper of substantially similar content has been or will be submitted to another conference or workshop during the POCV review period.

For further details and updates, please see the workshop website: elderlab.yorku.ca/pocv

WORKSHOP CHAIRS:
James Elder, York University
jelder@yorku.ca

Jeffrey Mark Siskind, Purdue University
qobi@purdue.edu

PROGRAM COMMITTEE:
Ronen Basri, Weizmann Institute, Israel
Kim Boyer, Ohio State University, USA
James Coughlan, Smith-Kettlewell Institute, USA
Sven Dickinson, University of Toronto, Canada
Anthony Hoogs, GE Global Research, USA
David Jacobs, University of Maryland, USA
Ian Jermyn, INRIA, France
Ben Kimia, Brown University, USA
Norbert Kruger, Aalborg University, Denmark
Michael Lindenbaum, Technion, Israel
Zili Liu, University of California, Los Angeles, USA
David Martin, Boston College, USA
Gerard Medioni, University of Southern California, USA
Zygmunt Pizlo, Purdue University, USA
Sudeep Sarkar, University of South Florida, USA
Eric Saund, Palo Alto Research Centre, USA
Kaleem Siddiqi, McGill University, Canada
Manish Singh, Rutgers University, USA
Shimon Ullman, Weizmann Institute, Israel
Johan Wagemans, University of Leuven, Belgium
Song Wang, University of South Carolina, USA
Rich Zemel, University of Toronto, Canada
Song-Chun Zhu, University of California, Los Angeles, USA
Steve Zucker, Yale University, USA