A Caltech Library Service

Computational modelling of visual attention

Itti, Laurent and Koch, Christof (2001) Computational modelling of visual attention. Nature Reviews Neuroscience, 2 (3). pp. 194-203. ISSN 1471-003X. doi:10.1038/35058500.

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Five important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment. First, the perceptual saliency of stimuli critically depends on the surrounding context. Second, a unique 'saliency map' that topographically encodes for stimulus conspicuity over the visual scene has proved to be an efficient and plausible bottom-up control strategy. Third, inhibition of return, the process by which the currently attended location is prevented from being attended again, is a crucial element of attentional deployment. Fourth, attention and eye movements tightly interplay, posing computational challenges with respect to the coordinate system used to control attention. And last, scene understanding and object recognition strongly constrain the selection of attended locations. Insights from these five key areas provide a framework for a computational and neurobiological understanding of visual attention.

Item Type:Article
Related URLs:
URLURL TypeDescription material for Fig.2 ReadCube access
Koch, Christof0000-0001-6482-8067
Additional Information:© 2001 Macmillan Magazines Ltd. The research carried out in the laboratories of the authors on visual attention is supported by the National Science Foundation, the National Institute of Mental Health and the Office of Naval Research. We thank Alex Pouget for excellent comments and suggestions.
Group:Koch Laboratory (KLAB)
Funding AgencyGrant Number
National Institute of Mental Health (NIMH)UNSPECIFIED
Office of Naval Research (ONR)UNSPECIFIED
Issue or Number:3
Record Number:CaltechAUTHORS:20130816-103152921
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:40408
Deposited By: KLAB Import
Deposited On:11 Jan 2008 22:50
Last Modified:09 Nov 2021 23:48

Repository Staff Only: item control page