Title :
Automatic evaluation method for rushes summary content
Author :
Dumont, Emilie ; Mérialdo, Bernard
Author_Institution :
Dept. Commun. Multimedia, Inst. Eurecom, Sophia-Antipolis, France
fDate :
June 28 2009-July 3 2009
Abstract :
During the last years, the development of rushes video summarization systems has greatly increased thanks to the international evaluation campaign TRECVID. In this paper, we propose an automation of the manual TRECVID evaluation using machine learning techniques. We train an automatic assessor to perform evaluation on summary content and we show a high correlation between the manual evaluation performed in TRECVID 2008 and our automatic assessor.
Keywords :
learning (artificial intelligence); video signal processing; TRECVID evaluation; automatic assessor; automatic evaluation method; machine learning techniques; rushes summary content; video summarization system; Automation; Cameras; Humans; Machine learning; Manuals; Particle measurements; Performance evaluation; Qualifications; Rhythm; Watches; TRECVID; Video summarization; evaluation; machine learning;
Conference_Titel :
Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on
Conference_Location :
New York, NY
Print_ISBN :
978-1-4244-4290-4
Electronic_ISBN :
1945-7871
DOI :
10.1109/ICME.2009.5202584
