While numerous algorithms have been proposed for object tracking with demonstrated success, it remains a challenging problem for a tracker to handle large change in scale, motion,...
* We present a novel approach for grouping from motion, based on a 4-D Tensor Voting computational framework. From sparse point tokens in two frames we recover the dense velocity f...
Abstract. We propose a generative approach to the problem of labeling images containing configurations of objects from multiple classes. The main building blocks are dense statisti...
This paper describes a method for finding wide-baseline correspondences between images at locations along gradient edges. We find edges in scale space using established methods an...
This paper presents a framework to simultaneously segment and track multiple body parts of interacting humans in the presence of mutual occlusion and shadow. The framework uses mu...