S
Shimon Ullman
Researcher at Weizmann Institute of Science
Publications - 212
Citations - 24884
Shimon Ullman is an academic researcher from Weizmann Institute of Science. The author has contributed to research in topics: Cognitive neuroscience of visual object recognition & 3D single-object recognition. The author has an hindex of 59, co-authored 207 publications receiving 24001 citations. Previous affiliations of Shimon Ullman include Massachusetts Institute of Technology.
Papers
More filters
Book ChapterDOI
Shifts in selective visual attention: towards the underlying neural circuitry.
Christof Koch,Shimon Ullman +1 more
TL;DR: This study addresses the question of how simple networks of neuron-like elements can account for a variety of phenomena associated with this shift of selective visual attention and suggests a possible role for the extensive back-projection from the visual cortex to the LGN.
Book
The Interpretation of Visual Motion
TL;DR: In this paper, the authors used the methodology of artificial intelligence to investigate the phenomena of visual motion perception: how the visual system constructs descriptions of the environment in terms of objects, their three-dimensional shape, and their motion through space, on the basis of the changing image that reaches the eye.
Journal ArticleDOI
Face recognition: the problem of compensating for changes in illumination direction
TL;DR: Evaluating the sensitivity of image representations to changes in illumination, as well as viewpoint and facial expression, indicated that none of the representations considered is sufficient by itself to overcome image variations because of a change in the direction of illumination.
Book
Visual routines
TL;DR: This paper exlrmines the processing of visual information beyond the creation of the early representations, and argues that the computation of spatial relations divides the analysis ofVisual information into two main stages.
Journal ArticleDOI
The Interpretation of Structure from Motion
TL;DR: It is shown that this scheme will correctly decompose scenes containing arbitrary rigid objects in motion, recovering their three dimensional structure and motion.