Processing digital video directly in the compressed domain has many advantages in terms of storage efficiency, speed, and video quality. We have developed a compressed video editi...
This paper presents experiments that evaluate the effect of different video segmentation methods on text-based video retrieval. Segmentations relying on modalities like speech, vi...
Anecdotal evidence suggests that story-level information is important for the speech component of video retrieval. In this paper we perform a systematic examination of the combina...
Modeling objects by probability density functions (pdf) is a new powerful method to represent complex objects in databases. By representing an object as a pdf, e.g. a Gaussian, it...