Presentation 2011-06-07
Video retrieval method based on the improved Tiny LSH using image and audio features
Noboru MURABAYASHI, Kenichi YOSHIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The rapid spread of the broad band internet increases the importance of the copied video detection method from large-scale video data base. In this paper, we propose an improvement of Tiny LSH method using image and audio features. The experiment results for 109.5 hours real video contents shows good retrieval performance. When the video clip length is 30 seconds, the retrieval accuracy rate was improved about 19% compared with the conventional Tiny LSH method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) copyrighted video / image feature / audio feature / Locality-sensitive hashing / direct-mapped cache
Paper # DE2011-23,PRMU2011-54
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/5/30(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) Video retrieval method based on the improved Tiny LSH using image and audio features
Sub Title (in English)
Keyword(1) copyrighted video
Keyword(2) image feature
Keyword(3) audio feature
Keyword(4) Locality-sensitive hashing
Keyword(5) direct-mapped cache
1st Author's Name Noboru MURABAYASHI
1st Author's Affiliation Graduate School of Business Sciences, University of Tsukuba()
2nd Author's Name Kenichi YOSHIDA
2nd Author's Affiliation Graduate School of Business Sciences, University of Tsukuba
Date 2011-06-07
Paper # DE2011-23,PRMU2011-54
Volume (vol) vol.111
Number (no) 77
Page pp.pp.-
#Pages 6
Date of Issue