Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...
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. ...
We propose a human action clustering method based on a 3D representation of the body in terms of volumetric coordinates. Features representing body postures are extracted directly...
Massimiliano Pierobon, Marco Marcon, Augusto Sarti...
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...
Abstract. We propose a novel and efficient method for generic arbitraryview object class detection and localization. In contrast to existing singleview and multi-view methods using...
Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung, Long Q...