Presentation 2007-03-16
Semantic News Video Indexing Using the Web
Hidenobu NAGATA, Masashi MORIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a novel methodology of semantic video indexing for broadcasts using the Web. Focusing on the co-occurrence of topics in broadcasts and Web articles, the methodology finds and associates semantically related parts of those broadcasts and articles. Text-based metadata such as closed captions were not used in our method. Instead, using an acoustic model, we extracted a set of multiple sequences of low-level phonetic symbols both from broadcast speech sound and words in Web articles and measured their similarity by error tolerant similarity score. Heuristic parameters for indexing resolution and number of target articles were derived by analyses of broadcasts and Web articles. In the evaluation, approximately 60% of 71 min of actual broadcast news videos were successfully indexed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) video indexing / semantics / Web / metadata
Paper # PRMU2006-258
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/3/9(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) Semantic News Video Indexing Using the Web
Sub Title (in English)
Keyword(1) video indexing
Keyword(2) semantics
Keyword(3) Web
Keyword(4) metadata
1st Author's Name Hidenobu NAGATA
1st Author's Affiliation NTT Cyber Solutions Laboratories, NTT-Corporation()
2nd Author's Name Masashi MORIMOTO
2nd Author's Affiliation NTT Cyber Solutions Laboratories, NTT-Corporation
Date 2007-03-16
Paper # PRMU2006-258
Volume (vol) vol.106
Number (no) 606
Page pp.pp.-
#Pages 6
Date of Issue