Presentation 2011-06-06
Mining Self-Similarity for Near-Duplicate Video Retrieval
Zhipeng WU, Kiyoharu AIZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Nowadays, with the exponential growth of digital video sources such as video-sharing websites and online TV broadcasting, the high level of redundancy caused by overlapping or near-duplicate videos greatly degrades the user experience. The notion of near-duplicate denotes that these videos are not exactly identical but are approximately identical which might differ in various transformations such as photometric variations, editing operations. In this paper, we propose a self-similarity Matrix (SSM) based near-duplicate video analysis method. By mining the self-similarity, video is represented as a 2-dimension matrix, which is a more succinct and discriminative representation for 3-dimension spatio-temporal video volume.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Near-duplicate video retrieval / Self-similarity matrix / Content-based copy detection
Paper # DE2011-5,PRMU2011-36
Date of Issue

Conference Information
Committee DE
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 Data Engineering (DE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Mining Self-Similarity for Near-Duplicate Video Retrieval
Sub Title (in English)
Keyword(1) Near-duplicate video retrieval
Keyword(2) Self-similarity matrix
Keyword(3) Content-based copy detection
1st Author's Name Zhipeng WU
1st Author's Affiliation Dept. of Information and Communication Eng., The University of Tokyo()
2nd Author's Name Kiyoharu AIZAWA
2nd Author's Affiliation Interfaculty Initiative in Information Studies, The University of Tokyo
Date 2011-06-06
Paper # DE2011-5,PRMU2011-36
Volume (vol) vol.111
Number (no) 76
Page pp.pp.-
#Pages 6
Date of Issue