Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...
Abstract. Successful multi-target tracking requires solving two problems - localize the targets and label their identity. An isolated target's identity can be unambiguously pr...
Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...
Abstract. Conventional photometric stereo has a fundamental limitation that the scale of recovered geometry is limited to the resolution of the input images. However, surfaces that...
This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mappi...