Video-based recognition and prediction of a temporally extended activity can benefit from a detailed description of high-level expectations about the activity. Stochastic grammars...
This work deals with modeling and markerless tracking of athletes interacting with sports gear. In contrast to classical markerless tracking, the interaction with sports gear come...
Bodo Rosenhahn, Christian Schmaltz, Thomas Brox, J...
This paper addresses the problem of recovering structure and motion from silhouettes. Silhouettes are projections of contour generators which are viewpoint dependent, and hence do...
Abstract. Super-resolution is a technique to restore the detailed information from the degenerated data. Lots of previous work is for 2D images while super-resolution of 3D models ...
To share resources in open distributed systems we have developed autonomous mobile programs, which periodically use a cost model to decide where to execute in a network. In additi...