Skip to main navigation Skip to search Skip to main content

Attending to visual motion: Localizing and classifying affine motion patterns

  • John K. Tsotsos
  • , Marc Pomplun
  • , Julio C. Martinez-Trujillo
  • , Kunhao Zhou
  • York University Toronto

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The Selective Tuning Model is a proposal for modelling visual attention in primates and humans. This paper describes ongoing research to include attention to motion stimuli within the model. The effort is unique because it seems that no past model presents a motion hierarchy plus attention to motion. We propose a biologically realistic model of the primate visual motion system attempting to explain howa hierarchical feed-forward network consisting of layers representing cortical areas V1, MT, MST, and 7a detects and classifies different kinds of motion patterns. The STM model is then integrated into this hierarchy demonstrating that successfully attending to motion patterns results in localization (segmentation) and labeling of those patterns.

Original languageEnglish
Title of host publicationProceedings - 1st Canadian Conference on Computer and Robot Vision
Pages452-462
Number of pages11
DOIs
StatePublished - 2004
EventProceedings - 1st Canadian Conference on Computer and Robot Vision - London, Ont, Canada
Duration: May 17 2004 → May 19 2004

Publication series

NameProceedings - 1st Canadian Conference on Computer and Robot Vision

Conference

ConferenceProceedings - 1st Canadian Conference on Computer and Robot Vision
Country/TerritoryCanada
CityLondon, Ont
Period5/17/04 → 5/19/04

ASJC Scopus Subject Areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Attending to visual motion: Localizing and classifying affine motion patterns'. Together they form a unique fingerprint.

Cite this