Localization of attended multi-feature stimuli: tracing back feed-forward activation using localized saliency computations

Authors:
John K. Tsotsos
Affiliations:
Dept. of Computer Science & Engineering, and, Centre for Vision Research, York University, Toronto, Ontario, Canada
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 5
Cited 0

A neural network model for selective attention in visual pattern recognition

Biological Cybernetics
An inhibitory beam for attentional selection

Proceedings of the 1991 York conference on Spacial vision in humans and robots
Modeling visual attention via selective tuning

Artificial Intelligence - Special volume on computer vision
The complexity of perceptual search tasks

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 2
Attending to visual motion

Computer Vision and Image Understanding - Special issue: Attention and performance in computer vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper demonstrates how attended stimuli may be localized even if they are complex items composed of elements from several different feature maps and from different locations within the Selective Tuning (ST) model. As such, this provides a step towards the solution of the ‘binding problem' in vision. The solution relies on a region-based winner-take-all algorithm, a definition of a featural receptive field for neurons where several representations provide input from different spatial areas, and a localized, distributed saliency computation specialized for each featural receptive field depending on its inputs. A top-down attentive mechanism traces back the connections activated by feed-forward stimuli to localize and bind features into coherent wholes.