We present a parametric method to automatically identify people in monocular low-resolution video by estimating the height and stride parameters of their gait. Stride parameters (...
An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...
An interactive algorithm for soft segmentation and matting of natural images and videos is presented in this paper. The technique follows and extends [10], where the user first ro...
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a...
—This paper presents a novel approach for automatic recognition of human activities from video sequences. We first group features with high correlations into Category Feature Vec...