We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several ...
Rosebud is a user-interface prototype which elicits storytelling by child users though interaction with a computationally-augmented physical artifact. In particular, Rosebud links...
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...
Supplying realistically textured 3D city models at ground level promises to be useful for pre-visualizing upcoming traffic situations in car navigation systems. Because this previs...
Nico Cornelis, Bastian Leibe, Kurt Cornelis, Luc J...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...