Acoustic events produced in meeting-room-like environments may carry information useful for perceptually aware interfaces. In this paper, we focus on the problem of combining diffe...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a poste...
: Mashups exemplify a workflow-like approach to dynamically integrate data and services from multiple web sources. Such integration workflows can build on existing services for web...
Abstract. A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especia...