In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...
We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences...
The formalism of probabilistic graphical models provides a unifying framework for capturing complex dependencies among random variables, and building large-scale multivariate stat...
The study of networked systems is an emerging field, impacting almost every area of engineering and science, including the important domains of communication systems, biology, soc...
Abstract. In this paper, we propose a new feature based non-rigid image registration method for dealing with two important issues. First, in order to establish reliable anatomical ...