Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
We present a variational approachto dense stereo reconstructionwhich combines powerful tools such as regularization and multi-scale processing to estimate directly depth from a num...
We consider the problem of estimating and encoding depth maps from multiple views in the context of 3D-TV with free-viewpoint rendering. We propose a novel codec based on the Rate...
The Visual Thesaurus is a new query approach when no starting image is available. It is a concise representation of all similar regions in a panel of visual patches; the user arra...
This paper describes an efficient pedestrian detection system for videos acquired from moving platforms. Given a detected and tracked object as a sequence of images within a bound...
Yang Ran, Qinfen Zheng, Isaac Weiss, Larry S. Davi...