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...
An adaptive spatiotemporal saliency algorithm for video attention detection using motion vector decision is proposed, motivated by the importance of motion information in video se...
Yaping Zhu, Natan Jacobson, Hong Pan, Truong Q. Ng...
A novel method based on geometrical and texture information is proposed for facial expression recognition from video sequences. The Discriminant Non-negative Matrix Factorization ...
This thesis aims to analyze, model, and develop a framework for next-generation multimedia authoring tools targeted to end-users. In particular, I concentrate on the combination o...
This paper proposes a motion-focusing method to extract key frames and generate summarization synchronously for surveillance videos. Within each pre-segmented video shot, the prop...