Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understand...
We present a computer vision system for robust object tracking in 3D by combining evidence from multiple calibrated cameras. This kernel-based 3D tracker is automatically bootstra...
Ambrish Tyagi, Mark A. Keck, James W. Davis, Geras...
This paper presents an approach to reconstruct nonstationary, articulated objects from silhouettes obtained with a monocular video sequence. We introduce the concept of motion blu...
Abstract. In this paper we introduce a novel approach for learning view-invariant gait representation that does not require synthesizing particular views or any camera calibration....
This paper addresses the problem of reconstructing the density of a scene from multiple projection images produced by modalities such as x-ray, electron microscopy, etc. where an ...
Satya P. Mallick, Sameer Agarwal, David J. Kriegma...