This paper describes an imagingsystem that has been designed specifically for the purpose of recovering egomotion and structure from video. The system consists of six cameras in a...
In Proc. of IEEE Conf. on CVPR'03, Madison, Wisconsin, 2003 We propose a generative model approach to contour tracking against non-stationary clutter and to coping with occlu...
Semantic scene classification based only on low-level vision cues has had limited success on unconstrained image sets. On the other hand, camera metadata related to capture condit...
We consider the problem of localizing the articulated and deformable shape of a walking person in a single view. We represent the non-rigid 2D body contour by a Bayesian graphical...
We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large an...