Presentation	2006-09-08 Corpus-Based Video Analysis Shin'ichi Satoh,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Recent technology innovation enables ordinary people to access huge scale video archives, and thus the requirement of content-based video retrieval and browsing is raised. In order to realize "true" content-based video access, it is crucial to analyze semantic content of videos, however, currently available technologies are far below the level of the practical requirement. On the other hand, continuous speech recognition, natural language processing, character recognition, and face detection/recognition technologies were put to practical use. One of the key technical issues which enables this achievement is the use of corpus-based analysis. It is ideal if we can apply corpus-based method to video analysis. This article introduces TRECVID, one of the first approaches towards corpus-based video analysis. We would like to reveal the latest technology level of corpus-based video analysis, issues in corpus-based video analysis, and future direction of the approach.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	PRMU2006-75
Date of Issue

Conference Information
Committee	PRMU
Conference Date	2006/9/1(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Pattern Recognition and Media Understanding (PRMU)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Corpus-Based Video Analysis
Sub Title (in English)
Keyword(1)
1st Author's Name	Shin'ichi Satoh
1st Author's Affiliation	National Institute of Informatics()
Date	2006-09-08
Paper #	PRMU2006-75
Volume (vol)	vol.106
Number (no)	229
Page	pp.pp.-
#Pages	10
Date of Issue