We present a probabilistic framework for component-based automatic detection and tracking of objects in video. We represent objects as spatio-temporal two-layer graphical models, w...
Leonid Sigal, Ying Zhu, Dorin Comaniciu, Michael J...
- Events are at the core of reactive applications, which have become popular in many domains. Contemporary modeling tools lack the capability express the event semantics and relati...
Abstract. We present an approach for articulated motion detection and pose estimation that uses only motion information. To estimate the pose and viewpoint we introduce a novel mot...
We demonstrate a multiscale pedestrian detector operating in near real time (5 fps on 640x480 images) with state-of-the-art detection performance. The computational bottleneck of ...
Video-surveillance systems are becoming more and more autonomous in the detection and the reporting of abnormal events. In this context, this paper presents an approach to detect ...