An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...
We present a system that can segment articulated, non-rigid motion without a priori knowledge of the number of clusters present in the analyzed scenario. We combine existing algori...
Tracking of humans in videos is important for many applications. A major source of difficulty in performing this task is due to inter-human or scene occlusion. We present an appr...
Autonomous robots need to track objects. Object tracking relies on predefined robot motion and sensory models. Tracking is particularly challenging if the robots can actuate on th...
This paper presents a system for animating customized virtual humans using motion parameters estimated from multi-view image sequences. The advantage of our method is that the sub...