3WNews: who, where, and when in news video

Authors:
Jun Yang;Alexander G. Hauptmann
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Year:
2006

Citing 4
Cited 0

Collages as dynamic summaries for news video

Proceedings of the tenth ACM international conference on Multimedia
MediaMill: exploring news video archives based on learned semantics

Proceedings of the 13th annual ACM international conference on Multimedia
From Language to Time: A Temporal Expression Anchorer

TIME '06 Proceedings of the Thirteenth International Symposium on Temporal Representation and Reasoning
Annotating news video with locations

CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe 3WNews as a novel system for browsing news video by the people (who) and locations (where) appearing in the footage as well as the time (when) of news events. The people names, locations, and time expressions are recognized from video transcript and their ambiguous references are resolved. As a key advantage, 3WNews distinguishes the people and locations that actually appear in the video from those merely mentioned in the transcript, and uses them as (better) indexes for browsing. It also supports browsing of news video by event time instead of broadcasting time.