An Information Theoretic Model of Saliency and Visual Search

Authors:
Neil D. Bruce;John K. Tsotsos
Affiliations:
Department of Computer Science and Engineering and, Centre for Vision Research, York University, Toronto, ON, Canada;Department of Computer Science and Engineering and, Centre for Vision Research, York University, Toronto, ON, Canada
Venue:
Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint
Year:
2008

Citing 2
Cited 1

Modeling visual attention via selective tuning

Artificial Intelligence - Special volume on computer vision
High-order contrasts for independent component analysis

Neural Computation

Spatiotemporal Saliency: Towards a Hierarchical Representation of Visual Saliency

Attention in Cognitive Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a proposal which quantifies visual saliency based on an information theoretic definition is evaluated with respect to visual psychophysics paradigms. Analysis reveals that the proposal explains a broad range of results from classic visual search tasks, including many for which only specialized models have had success. As a whole, the results provide strong behavioral support for a model of visual saliency based on information, supplementing earlier work revealing the efficacy of the approach in predicting primate fixation data.