Abstract. This paper presents a novel approach to implement estimation and recognition of human motion from uncalibrated monocular video sequences. As it is difficult to find a go...
This paper addresses the problem of 3D motion reconstruction from a series of 2D projections under low reconstructibility. Reconstructibility defines the accuracy of a 3D reconst...
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
Dirk Ormoneit, Hedvig Sidenbladh, Michael J. Black...
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. ...
Abstract. In this paper we present a new method for the 3D reconstruction of highly deforming surfaces (for instance a flag waving in the wind) viewed by a single orthographic came...