We propose the use of attentional cascades based on the DCT and motion information contained in an MPEG coded stream. An attentional cascade is a sequence of very efficient class...
This study describes experiments on automatic detection of semantic concepts, which are textual descriptions about the digital video content. The concepts can be further used in c...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
This paper presents an information-driven online video composition system. The composition work handled by the system includes dynamically setting multiple pan/tilt/zoom (PTZ) cam...
Qiong Liu, Xiaojin Shi, Don Kimber, Frank Zhao, Fr...
Super-Resolution is the problem of generating one or a set of high-resolution images from one or a sequence of lowresolution frames. Most methods have been proposed for super-reso...