================================ Announcement and Call for Papers IEEE Computer Society Workshop on Perceptual Organization in Computer Vision July 8th (pre ICCV 2001) --- Vancouver, Canada As recognized by the Gestalt school, the importance of perceptual organization (PO) in human vision cannot be overestimated; it imparts both efficiency and robustness to the visual process. Since early demonstrations in the 1980s underscored its usefulness in object recognition, the computer vision community has seen various applications of PO in artificial vision systems such as in stereo matching, model indexing, contour completion, figure-ground segmentation, change detection, and more. Indeed, it can be argued that a reasonable computational model of perception can be built around the notion of repeated detection and classification of organized structure. Recently, there has been a surge of activity in the application of perceptual organization to computer vision tasks. In this workshop we intend to bring together researchers focusing on different aspects of perceptual organization, share ideas, debate the role(s) of perceptual organization in artificial vision systems and outline future research directions. The workshop will consist of high quality technical papers describing new or ongoing work in perceptual organization, as well as a few invited talks from other, related, disciplines (one of them given by Prof. Adelson from MIT). We intend to provide enough time for discussion during the sessions as well as a special open discussion by the end of the workshop. Work in all areas related to perceptual organization is welcome. This includes, but is not limited to work in the domains of: modeling human performance on psychophysical stimuli; segmentation or grouping in single natural images; segmentation of medical or other non-visual imagery; and segmentation in video of independently moving objects. Relevant techniques include, but are not limited to, graph-based algorithms including spectral methods; search algorithms; techniques from learning including E-M, belief propagation, and Markov Chain Monte Carlo methods; and level set methods. The abstracts of the accepted papers will be disseminated among the participants as an informal proceedings. All authors are invited to submit their papers to a special issue of IEEE PAMI dedicated to POCV. A separate call for papers for this special issue will be published soon. The deadline is expected to be around December 2001. PAPER SUBMISSION: Since we will not produce a published proceedings, we do not preclude submissions describing work that will appear in other forums. However, please mention in your cover letter if this work has already been accepted to another workshop or conference. Four copies of an extended abstract (up to 4 pages, double-space, 12 pt, 1 inch margins) should be received no later than March 30, 2001 by Michael Lindenbaum, Computer Science Dept., Technion, Haifa 32000, Israel ( mailto:mic@cs.technion.ac.il Phone: 972-4-8294331) The program committee: David Jacobs. Michael Lindenbaum (joint chairs) Arnon Amir, Kim Boyer, Pietro Perona, Ruth Rosenholtz, Sudeep Sarkar, Arnold Smeulders, Yair Weiss, Lance Williams, Steven Zucker. For updates and more information please refer to meeting page http://www.cs.technion.ac.il/~mic/POCV2001/pocv2001.html or send mail to either mailto:dwj@research.nj.nec.com or to mailto:mic@cs.technion.ac.il .