This paper presents a target tracking framework for unstructured
crowded scenes. Unstructured crowded scenes
are defined as those scenes where the motion of a crowd
appears to b...
We propose a novel method for automatically discover-ing key motion patterns happening in a scene by observing the scene for an extended period. Our method does not rely on object ...
Abstract. In this paper, we propose an efficient video coding system that applies statistical learning methods to reduce the computational cost in H.264 encoder. The proposed metho...
We report on a diary study of how and why knowledge workers use the World Wide Web. By examining in detail a complete two-day set of Web activities from each of 24 people, we cons...
Recent approaches to reconstructing city-sized areas from large image collections usually process them all at once and only produce disconnected descriptions of image subsets, whi...