We present a Bayesian framework for learning higherorder transition models in video surveillance networks. Such higher-order models describe object movement between cameras in the...
Abstract Colin Campbell, Wolfgang Grieskamp, Lev Nachmanson, Wolfram Schulte, Nikolai Tillmann, and Margus Veanes Microsoft Research, Redmond, WA, USA Abstract. We describe a pract...
Colin Campbell, Wolfgang Grieskamp, Lev Nachmanson...
We present a surface representation and a set of algorithms that allow interactive placement of curved parametric objects without interpenetration. Using these algorithms, a model...
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
This paper introduces a fast continuous collision detection technique for polyhedral rigid bodies. As opposed to most collision detection techniques, the computation of the first ...