We propose a method for estimating the pose of a human body using its approximate 3D volume (visual hull) obtained in real time from synchronized videos. Our method can cope with ...
Abstract. In this work, we present an approach to jointly segment a rigid object in a two-dimensional (2D) image and estimate its three-dimensional (3D) pose, using the knowledge o...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
We present two instantiations of generic Interactive State Machines (ISMs) with mobility features which are useful for modeling and verifying dynamically changing mobile systems. I...
Abstract-- Local convergence is a limitation of many optimization approaches for multimodal functions. For hybrid model learning, this can mean a compromise in accuracy. We develop...
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...