A method for matching sequences from two perspective views of a moving person silhouette is presented. Regular (approximate uniform thickness) parts are detected on an image and a ...
Tracking people using movie sequences is not straightforward because of the human body's articulation and the complexity of a person's movements. In this paper we show ho...
The 3D shape of the human body is useful for applications in fitness, games and apparel. Accurate body scanners, however, are expensive, limiting the availability of 3D body mode...
—Most of the development of pose recognition focused on a single person. However, many applications of computer vision essentially require the estimation of multiple people. Henc...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...