Visual digests for news video libraries

Abstract

The Informedia Digital Video Library contains over 2000 hours of video, growing at a rate of 15 hours per week. A good query engine is not sufficient for information retrieval because often the candidate result sets grow in number as the library grows. Video digests summarize sets of stories from the library, providing users with a visual mechanism for interactive browsing and query refinement. These digests are generated dynamically under the direction of the user based on automatically derived metadata from the video library. Three types of digests are discussed: VIBE digests emphasizing word relationships, timelines showing trends against time, and maps showing geographic correlations. Multiple digests can be combined into a single view or animated into a temporal presentation.