—The goal of this paper is to correct bleed-through in degraded documents using a variational approach. The variational model is adapted using an estimated background according t...
Abstract This paper focuses on human behavior recognition where the main problem is to bridge the semantic gap between the analogue observations of the real world and the symbolic ...
In this paper we reformulate the 3D reconstruction of deformable surfaces from monocular video sequences as a labeling problem. We solve simultaneously for the assignment of featu...
First IEEE International Workshop on Biologically Motivated Computer Vision, Seoul, Korea (May 2000). There is considerable evidence that object recognition in primates is based o...
In this paper, we propose a rank minimization method to fuse the predicted confidence scores of multiple models, each of which is obtained based on a certain kind of feature. Spe...