We describe a “bag-of-rectangles” method for representing and recognizing human actions in videos. In this method, each human pose in an action sequence is represented by orien...
Motion is the strongest visual appeal to attention [2], yet it is rarely used in the visualization of large-scale quantitative information. Motion is complex; it can vary across n...
demanding algorithm of a video encoder. It is known that about 60% ~ 80% of the total computation time is consumed for motion estimation [1]. The second is its high impact on the v...
J. Lee, Narayanan Vijaykrishnan, Mary Jane Irwin, ...
A digital image stabilization system compensates the image movement caused by hand jiggle for the image sequence captured by a hand-held video camera. In this paper, a simplified ...
This paper describes an efficient pedestrian detection system for videos acquired from moving platforms. Given a detected and tracked object as a sequence of images within a bound...
Yang Ran, Qinfen Zheng, Isaac Weiss, Larry S. Davi...