In this paper, we propose a robust model selection criterion for mixtures of subspaces called minimum effective dimension (MED). Previous information-theoretic model selection cri...
In this paper we present a novel learning based method for restoring and recognizing images of digits that have been blurred using an unknown kernel. The novelty of our work is an...
Mithun Das Gupta, ShyamSundar Rajaram, Nemanja Pet...
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
letons to Bone Graphs: Medial Abstraction for Object Recognition Diego Macrini University of Toronto Kaleem Siddiqi McGill University Sven Dickinson University of Toronto Medial d...
The notion of a virtual sensor for optimal 3D reconstruction is introduced. Instead of planar perspective images that collect many rays at a fixed viewpoint, omnivergent cameras c...