The goal of motion segmentation and layer extraction can be viewed as the detection and localization of occluding surfaces. A feature that has been shown to be a particularly stro...
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even...
In this paper we propose to use lexical semantic networks to extend the state-of-the-art object recognition techniques. We use the semantics of image labels to integrate prior kno...
In this paper, we present an interactive offline tracking system for generic color objects. The system achieves 60100 fps on a 320 ? 240 video. The user can therefore easily refin...
Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve sta...