In this work we address the problem of boundary detection by combining ideas and approaches from biological and computational vision. Initially, we propose a simple and efficient ...
Iasonas Kokkinos, Rachid Deriche, Olivier D. Fauge...
We present a method for learning complex appearance mappings, such as occur with images of articulated objects. Traditional interpolation networks fail on this case since appearan...
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this...
For effective retrieval of visual information, statistical learning plays a pivotal role. Statistical learning in such a context faces at least two major mathematical challenges: ...
— We propose a method that takes observations of a random vector as input, and learns to segment each observation into two disjoint parts. We show how to use the internal coheren...