Key to effective video retrieval: Effective cataloging and browsing

Abstract

Multimedia data is an increasingly important information medium today. Providing intelligent access for effective use of this information continues to offer challenges in digital library research. As computer vision, image processing and speech recognition research continue to progress, we examine the effectiveness of these fully automated techniques in architecting effective video retrieval systems. We present semi-automated techniques that combine manual input, and video and speech technology for automatic content characterization integrated into a single system we call CueVideo. CueVideo integrates voice and manual annotation, attachment of related data, visual content search technologies (QBICtm), and novel multiview storyboard generation to provide a system where the user can incorporate the type of semantic information that automatic techniques would fail to obtain. © 1998 ACM.