We propose a method for constructing a video sequence of high space-time resolution by combining information from multiple lowresolution video sequences of the same dynamic scene. ...
A key problem for "face in the crowd" recognition from existing surveillance cameras in public spaces (such as mass transit centres) is the issue of pose mismatches betwe...
We propose a person-dependent, manifold-based approach for modeling and tracking rigid and nonrigid 3D facial deformations from a monocular video sequence. The rigid and nonrigid ...
Abstract. In this paper we present a new method for the 3D reconstruction of highly deforming surfaces (for instance a flag waving in the wind) viewed by a single orthographic came...
We derive a probabilistic framework for robust, realtime, visual tracking of multiple previously unseen objects from a moving camera. This framework models the discrete depth orde...