Special Seminar: Can Distributed Local Saliency Computations Solve the Feature Binding

TITLE: Can Distributed Local Saliency Computations Solve the Feature Binding
Problem?John K. TsotsosYork University, Toronto, Canada
Director, Center for Vision Research
Professor, Department of Computer Science & Engineering
Canada Research Chair in Computational VisionHOST: Laurent itti Abstract:
Computational vision has a long history of proposing methods for
decomposing a visual signal into components. For example, many good
strategies have appeared for decomposing visual motion signals (such as
Heeger, Sperling). What has been far more elusive is how to recombine
those components into a whole. This problem has even merited its own name
- the binding problem. To date no realizable process has appeared to solve
the binding problem, even in part, although several proposals have
appeared. This paper proposes a novel solution for a significant portion
of the binding problem, namely, the re-combination of visual features into
larger patterns and their localization in the image. The solution requires
the abandonment of the nearly ubiquitous saliency map and adoption of a
distributed, localized computation of saliency that is dependent on local
neural selectivity constraints. This strategy is demonstrated within a
fully implemented model that attends to simple motion patterns in image
sequences.
-------------------------------------------------

Location: Hedco Neurosciences Building (HNB) - -107

Audiences: Everyone Is Invited

Contact: Vishal Thakkar