Special Issue on
Video Computing

Guest Editor
Dr. Mubarak Shah, University of Central Florida, USA

Submission Deadline: March 1st, 2001

Computer Vision has also been called Image Understanding, since the aim of vision has been to understand a single image of a scene, locate and identify objects, their shape and structure, spatial arrangements, and relationships between other objects, etc. Recently, computer vision has been progressing from image understanding to video understanding. The aim of video understanding is to understand a sequence of images instead of a single image, which includes detection and measurement of motion, motion-based recognition and motion recognition, etc. Video provides multiple temporal constraints, which make it easier to analyze a complex and coordinated series of events that cannot be understood by just looking at only a single image or a few frames. Since most videos are about people, during the last few years, researchers have focused on recognition of human actions, activities, gestures, visual speech, facial expressions etc. Video understanding has also been called an inverse Hollywood problem. Since in Hollywood the aim is to transform a script into a box office hit movie (video). On the other hand, the aim in video understanding is to transform a video (movie) into a transcript (symbolic or textual description).

The effective use of video requires understanding of video processing, video analysis, video synthesis, video retrieval, video compression and other related computing techniques. In this special issue of International Journal of Computer Vision, we will publish papers related to various aspects of video computing. We invite papers on recent results in video computing areas, including but not limited to the following topics:

Prospective authors are encouraged to submit high quality, original works, which have not appeared, nor are under consideration, in any other journals.

Video Understanding Gesture Recognition Facial Expression Recognition Visual Lipreading Human Activity Recognition	Video Abstraction Skims Abstracts Key Frames
Video Surveillance and Monitoring Tracking Scene Change Detection Visual Traffic Monitoring Intruder Detection Video Sentries	Video Segmentation Shots, Scenes, Stories Layered Representations of Video Object-based segmentation of video
Video Compression MPEG-4 Knowledge-based Compression Semantic-based Compression Video Phones Video Mosaics	Video Synthesis Facial Animation Body Animation Motion Capture
	Video Registration Model-based registration Geo-registration of video Site Modeling from video