We present an approach for efficiently recognizing all objects in a scene and estimating their full pose from multiple views. Our approach builds upon a state of the art single-vie...
Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...
We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...
Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we provide a framework for p...
In this paper, we propose an approach to learning appearance models of moving objects directly from compressed video. The appearance of a moving object changes dynamically in vide...