We consider the problem of recognizing human actions from still images. We propose a novel approach that treats the pose of the person in the image as latent variables that will h...
Abstract. This paper presents a novel approach for motion segmentation from feature trajectories with missing data. It consists of two stages. In the first stage, missing data are...
In this highly technological world, various methods have been developed for the purpose of recovering the shape of 3D objects from 2D images. In this paper, we introduce methods t...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
For detecting objects in natural visual scenes, several powerful image features have been proposed which can collectively be described as spatial histograms of oriented energy. Th...