Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of o...
We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding t...
We propose a semi-supervised learning algorithm for discriminant analysis, which uses the geometric structure of both labeled and unlabeled samples and perform a manifold regulari...
Our objective is to model the visual manifold of object appearance corresponding to geometric transformation. We learn a generative model for object appearance where the appearanc...
This paper presents a scalable solution to the problem of tracking objects across spatially separated, uncalibrated, non-overlapping cameras. Unlike other approaches this technique...