Picasso's bulls

NIPS-95 Workshop

Object Features for Visual Shape Representation

NIPS-95 Workshop: Saturday, Dec 2, 1995

Updated Nov 25, 1995

Organizers: Shimon Edelman, Nathan Intrator

Overview - - Other Workshops - Ski Conditions

Invited Speakers

Abstracts and Schedule (Updated Nov 25)

more bulls

Overview:

Object recognition can be regarded as a comparison between the stimulus shape and a library of reference shapes stored in long-term memory. It is not likely that the visual system stores exact templates or snapshots of familiar objects, both for pragmatic reasons (the appearance of a 3D object depends on the viewing conditions, making a close match between the stimulus and a template unattainable), and because of computational limitations that have to do with the curse of dimensionality. Many competing approaches to the extraction of features useful for shape representation have been proposed in the past.

The workshop will explore and compare some of these approaches. We shall be particularly interested in discussing different approaches for evaluating feature extraction rules: information theory, statistics, pattern recognition etc. We would like to elaborate on the goal of feature/information extraction in early visual cortex, the relevance of the statistics of the input environment to studying learning rules and comparison between visual cortical plasticity models. Presentation of psychophysical and neurobiological data relevant to the feature issue will be encouraged.

POTENTIAL PARTICIPANTS: connectionists / feature extraction people / vision researchers / neurobiologists working on perceptual learning

Some related links

We shall list here links to related works and publications. For efficient surfing, only directly related links will be kept.


Shimon Edelman
Dept. of Applied Math & Comp Sci
The Weizmann Institute of Science
Rehovot 76100, Israel
email: edelman@wisdom.weizmann.ac.il
phone: +972-8-342856
fax: +972-8-344122
Nathan Intrator
Institute for Brain and Neural Systems
Brown University, Box 1843
Providence, RI 02912, USA
email: nin@cns.brown.edu
phone: (401) 863-1488
fax: (401) 863-3494