We boost the efficiency and robustness of distributionbased matching by random subsampling which results in the minimum number of samples required to achieve a specified probabili...
In this paper we introduce two new methods for solving binary quadratic problems. While spectral relaxation methods have been the workhorse subroutine for a wide variety of comput...
Discriminative approaches to human pose inference involve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping ha...
In this paper we consider the problem of reconstructing the 3D position and surface normal of points on an unknown, arbitrarily-shaped refractive surface. We show that two viewpoi...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...