away concepts from the surface form of the text. The authors argue that while there has been research into automatic classification, general classification schemes are unsuitable f...
In this paper, we aim to detect human in video over large viewpoint changes which is very challenging due to the diversity of human appearance and motion from a wide spread of view...
Slit-tear visualizations allow users to selectively visualize pixel paths in a video scene. The slit-tear visualization technique is a generalization of the traditional photograph...
We present an automatic and efficient method to extract spatio-temporal human volumes from video, which combines top-down model-based and bottom-up appearancebased approaches. Fr...
In this paper, a motion-based approach for detecting high-level semantic events in video sequences is presented. Its main characteristic is its generic nature, i.e. it can be dire...