We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
Shape modeling is a very important issue for many study, for example, object recognition for robot vision, virtual environment construction, and so on. In this paper, a new method...
This article presents a method aiming at quantifying the visual similarity between an image and a class model. This kind of problem is recurrent in many applications such as objec...
A method for matching sequences from two perspective views of a moving person silhouette is presented. Regular (approximate uniform thickness) parts are detected on an image and a ...
In this paper, temporal segmentation of 3D video based on motion analysis is presented. 3D video is a sequence of 3D models made for a real-world dynamic object. A modified shape ...