In this paper, a novel method to learn the intrinsic object structure for robust visual tracking is proposed. The basic assumption is that the parameterized object state lies on a...
The evolution of dependencies in information hierarchies can be modeled by sequences of compound digraphs with edge weights. In this paper we present a novel approach to visualize...
This paper addresses online learning of reference object distribution in the context of two hybrid tracking schemes that combine the mean shift with local point feature correspond...
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...