—Color models are often used for representing object appearance for foreground segmentation applications. The relationships between colors can be just as useful for object select...
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that ar...
Michael J. Black, Yaser Yacoob, Allan D. Jepson, D...
A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-tempo...
Explicit surfaces, such as triangulations or wireframe models, have been extensively used to represent the deformable 3?D models that are used to fit 3?D point and 2?D silhouette ...
Model order selection and cue combination are both difficult open problems in the area of clustering. In this work we build upon stability-based approaches to develop a new method...
Andrew Rabinovich, Serge Belongie, Tilman Lange, J...