Much of the research on video-based human motion capture assumes the body shape is known a priori and is represented coarsely (e.g. using cylinders or superquadrics to model limbs...
Alexandru O. Balan, Leonid Sigal, Michael J. Black...
Abstract. Velocity distributions are an enhanced representation of image velocity implying more velocity information than velocity vectors. Velocity distributions allow the represe...
This paper proposes a novel approach to motion capture
from multiple, synchronized video streams, specifically
aimed at recording dense and accurate models of the structure
and ...
Yasutaka Furukawa (University of Washington), Jean...
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...
In this paper, we propose a robust model selection criterion for mixtures of subspaces called minimum effective dimension (MED). Previous information-theoretic model selection cri...