In this paper, we introduce a new image descriptor for broad Image Categorization, the Progressive Randomization (PR), that uses perturbations on the values of the Least Significa...
A new message-passing scheme for MRF optimization is proposed in this paper. This scheme inherits better theoretical properties than all other state-of-the-art message passing met...
Most dense stereo correspondence algorithms start by establishing discrete pixel matches and later refine these matches to sub-pixel precision. Traditional sub-pixel refinement me...
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...
The boundaries of image regions necessarily consist of edges (in particular, step and roof edges), corners, and junctions. Currently, different algorithms are used to detect each ...