The Seventh IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV) San Francisco, California, June 13, 2010. In Conjunction with IEEE CVPR 2010

WORKSHOP CHAIRS: Song Wang, (songwang@cec.sc.edu) University of South Carolina Philippos Mordohai, (Philippos.Mordohai@stevens.edu) Stevens Institute of Technology PROGRAM COMMITTEE: Sven Dickinson, University of Toronto Charless Fowlkes, University of California, Irvine Leo Grady, Siemens Corporate Research James Hays, Brown University Derek Hoiem, University of Illinois at Urbana-Champaign Anthony Hoogs, Kitware Inc. Hiroshi Ishikawa, Nagoya City University Ian Jermyn, INRIA Benjamin Kimia, Brown University Iasonas Kokinos, Ecole Centrale Paris Michael Lindenbaum, Technion Gerard Medioni, University of Southern California John Oliensis, Stevens Institute of Technology Xiaofeng Ren, Intel Labs Seattle Sudeep Sarkar, University of South Florida Joachim Stahl, Clarkson University Zhuowen Tu, University of California, Los Angeles Stella Yu, Boston College

Workshop Program FINAL SUBMISSION OF CAMERA-READY PAPERS: All authors with accepted papers in the workshop: please read and follow these INSTRUCTIONS to prepare for and submit your final camera-ready papers. IMPORTANT DATES: · Submission deadline: 11:59pm EST, March 12, 2010 · Notification: April 05, 2010 · Final versions of accepted papers due: April 15, 2010 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 use the IEEE Computer Society CVPR format kit. 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. Click here to enter the online submission system. INVITED TALKS: · Sven Dickinson, University of Toronto Title: The Role of Intermediate Shape Priors in Perceptual Grouping and Image Abstraction · Gerard Medioni, University of Southern California Title: Tensor Voting: Review and New Elements · Jianbo Shi, University of Pennsylvania Title: Shape Packing With Contours and Segments for Object Recognition THEME: Perceptual Organization (PO) is the process of establishing a meaningful relational structure over raw visual data so as visual primitives arising from the common physical cause are grouped together. A driving motivation behind perceptual organization research in computer vision is to deliver compact representations and to reduce the space of hypotheses for higher-level visual tasks. 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 figure-ground segmentation, contour completion, stereo matching, model indexing, change detection, activity recognition, and more. Recent progress in PO has encouraged more participation from experts in related areas such as object recognition, texture and motion analysis. Because of its wide applicability, the potential payoff from perceptual organization research is enormous. Among the objectives of POCV is to encourage presentation of new ideas and facilitate discussion on the future of PO. To this end, papers introducing novel concepts will be considered for acceptance even if they lack full experimental validation. The schedule will include longer periods for questions and answers after each talk than CVPR to enable dialogue and the exchange of ideas. PREVIOUS IEEE POCV WORKSHOPS: · 2008 CVPR (Anchorage, AK) · 2006 CVPR (New York, NY) · 2004 CVPR (Washington, DC) · 2001 ICCV (Vancouver, Canada) · 1999 ICCV (Corfu, Greece) · 1998 CVPR (Santa Barbara, CA) SCOPE: Papers are solicited in all areas of perceptual organization, including but not limited to: * image segmentation * interactive image 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 * visual attention models, algorithms and applications * learning in perceptual organization * graphical methods * natural scene statistics * evaluation methods 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 IEEEXplore.