We investigate the problem of learning the structure of an articulated object, i.e. its kinematic chain, from feature trajectories under affine projections. We demonstrate this po...
In this paper we propose a rate-distortion optimized motion estimation algorithm that is built upon a quadtree structure. Each node of the quadtree represents a block in the curre...
This work focusses on bridging between folksonomies, which provide social but mainly flat and unstructured metadata on web resources, and semantic web ontologies, which instead des...
This paper describes techniques for dynamically modeling the 2-D appearance and 3-D geometry of a
scene by integrating information from a moving camera. These techniques are illus...
In this paper, we present a novel multi-modal framework for semantic event extraction from basketball games based on webcasting text and broadcast video. We propose novel approach...