TRECVID 2007 Rushes Summarization
Feng Wang and Chong-Wah Ngo
Video Retrieval Group (VIREO), City University of Hong Kong
Rushes are the raw
material (extra video, B-rolls footage) use to produce a video. 20 to 40 times
as much material may be shot as actually becomes part of the finished
The system task in rushes
summarization is, given a video from the rushes test collection, to
automatically create an MPEG-1 summary clip that shows the main object (animate
and inanimate) and events in the rushes video to be summarized. The summary
should maximize the number of frames used and present the information in way
that maximizes the usability of the summary and speed of object/event
Seven criterions are used
by TRECVID 2007 to evaluate 2 baselines made by CMU, and the 22 submissions from
USA, Europe, Australia and Asia.
- duration of the summary (sec)
- difference between target (4% of original video size) and actual summary size (target-actual) (sec)
- total time spent judging the inclusions of objects and events (sec)
- total video play time (vs. pause) to judge the inclusions (sec)
- fraction of inclusions found in the summary (0 - 1)
- Was the summary easy to understand: 1 strongly disagree - 5 strongly agree
Was there a lot of duplicate video: 1 strongly agree - 5 strongly disagree
|Mean of 22 teams
Demo Page: http://vireo.cs.cityu.edu.hk/research/tvs07-demo/demo_page.htm
(Dept. of Computer Science, CityU
Prof. C. W. Ngo (Dept. of Computer Science, CityU
TRECVID 2007 http://www-nlpir.nist.gov/projects/tv2007/tv2007.html#2.4
TVS Workshop at ACM Multimedia 2007 http://www-nlpir.nist.gov/projects/tv7.acmmm/
VIREO Research Group at CityU of HK http://vireo.cs.cityu.edu.hk/
Wang and C. W.
Ngo, "Rushes Video Summarization by Object and Event Understanding",
TRECVID BBC Rushes Summarization Workshop at ACM Multimedia '07.
C. W. Ngo, Z. Pan, and X. Y. Wei, "Hierarchical Hidden Markov Model for Rushes Structuring and Indexing",
Int. Conf. on Image and Video Retrieval,
C. W. Ngo, Z. Pan, X. Wei, X. Wu, H. K. Tan, and W. Zhao, "Motion Driven Approaches to Shot Boundary Detection, Low-Level Feature Extraction and BBC Rushes Characterization at TRECVID 2005",
TRECVID Workshop, 2005.
C. W. Ngo, T. C. Pong, and R. T. Chin,
"Video Partitioning through Temporal Slices Analysis", IEEE Trans. on Circuits and Systems for Video
Technology, 11(8), pp. 941-953, 2001.