While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than p...
In this paper, we address the issue of joint space-time segmentation of image sequences. Typical approaches to such segmentation consider two image frames at a time, and perform t...
This paper develops a general, formal framework for modeling term dependencies via Markov random fields. The model allows for arbitrary text features to be incorporated as eviden...
FPGAs are one of the essential components in platform-based embedded systems. Such systems are customized and applied only to a limited set of applications. Also some applications...
In [8], the authors proposed the large deformation logunbiased diffeomorphic nonlinear image registration model which has been successfully used to obtain theoretically and intuit...
Igor Yanovsky, Paul M. Thompson, Stanley Osher, Lu...