In this paper, we develop a new video-to-video face recognition algorithm. The major advantage of the video based method is that more information is available in a video sequence ...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
Film Tear is a form of degradation in archived film and is the physical ripping of the film material. Tear causes displacement of a region of the degraded frame and the loss of im...
Different from appearance-based methods, clustering feature points only by their motion coherence is an emerging category of approach to detecting and tracking individuals among c...
In this paper, a framework that combines feature extraction, model learning, and likelihood computation, is presented for video event detection. First, the independent component a...