Content-based video search over 1 million videos with 1 core in 1 second

Yu, SI; Jiang, L; Xu, Z; Yang, Y; Hauptmann, AG

Content-based video search over 1 million videos with 1 core in 1 second

Yu, SI Jiang, L Xu, Z Yang, Y

Hauptmann, AG

Permalink

Publication Type:: Conference Proceeding
Citation:: ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval, 2015, pp. 419 - 426
Issue Date:: 2015-06-22

Closed Access

	Filename	Description	Size
	p419-yu.pdf	Published version	1.65 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yu, SI	en_US
dc.contributor.author	Jiang, L	en_US
dc.contributor.author	Xu, Z	en_US
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546	en_US
dc.contributor.author	Hauptmann, AG	en_US
dc.date.issued	2015-06-22	en_US
dc.identifier.citation	ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval, 2015, pp. 419 - 426	en_US
dc.identifier.isbn	9781450332743	en_US
dc.identifier.uri	http://hdl.handle.net/10453/121730
dc.description.abstract	Copyright © 2015 ACM. Many content-based video search (CBVS) systems have been proposed to analyze the rapidly-increasing amount of user-generated videos on the Internet. Though the accuracy of CBVS systems have drastically improved, these high accuracy systems tend to be too inefficient for interactive search. Therefore, to strive for realtime web-scale CBVS, we perform a comprehensive study on the different components in a CBVS system to understand the tradeoffs between accuracy and speed of each component. Directions investigated include exploring different low-level and semanticsbased features, testing different compression factors and approximations during video search, and understanding the time v.s. accuracy trade-off of reranking. Extensive experiments on data sets consisting of more than 1,000 hours of video showed that through a combination of effective features, highly compressed representations, and one iteration of reranking, our proposed system can achieve an 10,000-fold speedup while retaining 80% accuracy of a state-of-the-art CBVS system. We further performed search over 1 million videos and demonstrated that our system can complete the search in 0.975 seconds with a single core, which potentially opens the door to interactive web-scale CBVS for the general public.	en_US
dc.relation.ispartof	ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval	en_US
dc.relation.isbasedon	10.1145/2671188.2749398	en_US
dc.title	Content-based video search over 1 million videos with 1 core in 1 second	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

Copyright © 2015 ACM. Many content-based video search (CBVS) systems have been proposed to analyze the rapidly-increasing amount of user-generated videos on the Internet. Though the accuracy of CBVS systems have drastically improved, these high accuracy systems tend to be too inefficient for interactive search. Therefore, to strive for realtime web-scale CBVS, we perform a comprehensive study on the different components in a CBVS system to understand the tradeoffs between accuracy and speed of each component. Directions investigated include exploring different low-level and semanticsbased features, testing different compression factors and approximations during video search, and understanding the time v.s. accuracy trade-off of reranking. Extensive experiments on data sets consisting of more than 1,000 hours of video showed that through a combination of effective features, highly compressed representations, and one iteration of reranking, our proposed system can achieve an 10,000-fold speedup while retaining 80% accuracy of a state-of-the-art CBVS system. We further performed search over 1 million videos and demonstrated that our system can complete the search in 0.975 seconds with a single core, which potentially opens the door to interactive web-scale CBVS for the general public.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/121730