[visionlist] Second International Workshop on Shape Perception in Human and Computer Vision

[Zygmunt Pizlo]

Topic and Motivation

On the computer vision side, shape was the backbone of classical object 
recognition systems in the 1960s, 1970s, and 1980s. However, the advent 
of appearance-based recognition in the 1990's drew the spotlight away 
from shape. While an active shape community continued in the periphery, 
only recently has shape re-entered the mainstream with a return to 
contours, shape hierarchies, shape grammars, shape priors, and even 3-D 
shape inference. On the human vision side, shape research was also 
affected by paradigm changes. Unlike the computer vision community, 
psychologists have usually agreed that shape is important, but it has 
been less clear to them what it is about shape that should be studied: 
surfaces, invariants, parts, multiple views, learning, simplicity, shape 
constancy or shape illusions? The growing interest in mathematical 
formalisms and computational models has begun to provide the long 
overdue common denominator for these various paradigms.

The goal of this workshop is to bring together some of the community's 
most distinguished shape perception researchers, from both human and 
computer vision, to help bridge not only the historical gap but the 
cross-disciplinary gap. They will reflect on their past and current 
experience in working with shape, identify the major challenges that 
need to be addressed, and help define directions for future research. 
This will be the second such multidisciplinary workshop devoted 
specifically to shape perception.

The first SPHCV was a major success, exposing students and researchers 
in computer vision to recent progress in the human shape perception 
community.  We hope to provide students and researchers in human shape 
perception an equivalent exposure to recent progress in the computer 
vision community.

Organization and Workshop Format

The format of the one-day workshop will be 12 invited speakers (six 
human vision, six computer vision). Each talk will last 25 min plus 5 
min for discussion. The speakers have been chosen to represent a broad 
cross-section of shape perception research, representing the major 
paradigms in both the human and computer vision communities. Speakers 
will be encouraged to reflect on their experience, identify critical 
challenges, etc., rather than present snapshots of their latest research 
results.

Location of the Workshop

The workshop is part of ECVP2009 and will be held on 29th of August 
2009. For more info about the program, abstracts, and registration, as 
well as a boat cruise, see:

http://viper.psych.purdue.edu/workshops/iwsphcv09/

Zyg Pizlo