We introduce a new method for segmentation of 3D medical data based on geometric variational principles. A minimal variance criterion is coupled with a geometric edge alignment mea...
Michal Holtzman-Gazit, Dorith Goldsher, Ron Kimmel
This paper presents a method for matching closed, 2D shapes (2D object silhouettes) that are represented as an ordered collection of shape contexts [1]. Matching is performed using...
This paper introduces a gestural perceptual-based approach to select objects, i.e., nodes and/or edges along paths. Based on known results from perception research, we propose a mo...
Even more than in our physical world, in our digital world we need systems that meet the security objective of service providers and users in equal measure. This paper investigates...
In this paper, we introduce a first-order probabilistic model that combines multiple cues to classify human activities from video data accurately and robustly. Our system works in...