An Overview of the 2004 Workshop on Perceptual Organization in Computer Vision

The 2004 Workshop on POCV emphasized novel, far-reaching ideas in PO rather than extensive experimental validation. This was intended to stimulate more discussion and debate than is typically feasible at a conference such as CVPR. We facilitated this goal by emphasizing novelty and relevance in the reviewing process. Circular reviewing, in which authors reviewed papers, also improved review quality. CVPR authors in PO-related areas were encouraged to submit related, but more advanced (and perhaps unproven) research to POCV. Although this was only marginally successful, it was intended to avoid the common situation where the workshop is primarily a forum for papers rejected from CVPR, while CVPR-accepted papers are not represented at the workshop.