Efficient and continuous near-duplicate video detection

Xie, Qing, Huang, Zi, Shen, Heng Tao, Zhou, Xiaofang and Pan, Chaoyi (2010). Efficient and continuous near-duplicate video detection. In: Advances in Web Technologies and Applications - Proceedings of the 12th Asia-Pacific Web Conference, APWeb 2010. Web Conference (APWEB), 2010 12th International Asia-Pacific, Busan, South Korea, (260-266). 6-8 April 2010. doi:10.1109/APWeb.2010.72

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
UQ220627.pdf HERDC combined - not publicly available application/pdf 88.16KB 0

Author Xie, Qing
Huang, Zi
Shen, Heng Tao
Zhou, Xiaofang
Pan, Chaoyi
Title of paper Efficient and continuous near-duplicate video detection
Conference name Web Conference (APWEB), 2010 12th International Asia-Pacific
Conference location Busan, South Korea
Conference dates 6-8 April 2010
Proceedings title Advances in Web Technologies and Applications - Proceedings of the 12th Asia-Pacific Web Conference, APWeb 2010
Journal name Advances in Web Technologies and Applications - Proceedings of the 12th Asia-Pacific Web Conference, APWeb 2010
Place of Publication Piscataway NJ, U.S.A.
Publisher IEEE
Publication Year 2010
Year available 2011
Sub-type Fully published paper
DOI 10.1109/APWeb.2010.72
ISBN 9780769540122
0769540120
Issue Article number 5474129
Start page 260
End page 266
Total pages 7
Collection year 2011
Language eng
Abstract/Summary Online video steam data is surging to an unprecedented level. Massive video publishing and sharing impose heavy demands on continuous video near-duplicate detection for many novel video applications. This paper presents an accurate and accelerated system for video near-duplicate detection over continuous video streams. We propose to transform a high-dimensional video stream into a one-dimensional Video Trend Stream (VTS) tomonitor the continuous luminance changes of consecutive frames, based on which video similarity is derived. In order to do fast comparison and effective early pruning, a compact auxiliary signature named CutSig is proposed to approximate the video structure. CutSig explores cut distribution feature of the video structure and contributes to filter candidates quickly. To scan along a video stream in a rapid way, shot cuts with local maximum AI (average information) in a query video are used as reference cuts, and a skipping approach based on reference cut alignment is embedded for efficient acceleration. Extensive experimental results on detecting diverse near-duplicates in real video streams show the effectiveness and efficiency of our method. © 2010 IEEE.
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ
Additional Notes Full Paper Session 11: Multimedia Information Systems

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 5 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Wed, 17 Nov 2010, 00:46:01 EST by Dr Heng Tao Shen on behalf of School of Information Technol and Elec Engineering