In this paper we present a probabilistic framework for tracking objects based on local dynamic segmentation. We view the segn to be a Markov labeling process and abstract it as a ...
Recently, we have proposed a novel approach to generating augmented video streams. The output images are a non-photorealistic reproduction of the augmented environment. Special st...
Analysis of videos of human-object interactions involves understanding human movements, locating and recognizing objects and observing the effects of human movements on those obje...
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
We develop a robust technique to find similar matches of human actions in video. Given a query video, Motion History Images (MHI) are constructed for consecutive keyframes. This i...