The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
Vision-based user interfaces enable natural interaction modalities such as gestures. Such interfaces require computationally intensive video processing at low latency. We demonstr...
Ming-yu Chen, Lily B. Mummert, Padmanabhan Pillai,...
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
We present a video recognition system of a “Go” TV program. It generates a Go play record automatically from a broadcast of Go played by human professionals. “Go” is the a...
Sign board detection is important for such computer vision applications as video surveillance and content based visual information retrieval. Previous researches on this topic foc...