Abstract. In this paper, we present a novel successive relaxation linear programming scheme for solving the important class of consistent labeling problems for which an L1 metric i...
Abstract. This article introduces a technique for improving the efficiency of diagnosis through approximate compilation. We extend the approach of compiling a diagnostic model, as...
Low-dimensional representations of sensory signals are key to solving many of the computational problems encountered in high-level vision. Principal Component Analysis (PCA) has b...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...