Speeding up Complex Video Copy Detection Queries

Massive amounts of video data from digital tv channels, online video communities, peer-to-peer networks, and video blogs require automated techniques for copyright enforcement and usage tracking. Effective video copy distortion models usually incur high computational cost. We propose an index supported multistep filter-and-refin e algorithm for a complex copy detection model. We characterize a class of fi lters for which we prove completeness of the result, and provide further runtime improvement by a novel tight approximation. In thorough experiments, we demonstrate that our algorithm substantially improves processing times.

Authors: Assent I., Kremer H., Seidl T.
Published in: Proc. of the 15th International Conference on Database Systems for Advanced Applications (DASFAA 2010), Tsukuba, Japan, Springer LNCS 5981
Publisher: Springer - Heidelberg, Germany
Sprache: EN
Jahr: 2010
Seiten: 307-321
ISBN: 978-3-642-12025-1
Konferenz: DASFAA
Typ: Tagungsbeiträge
Forschungsgebiet: Fast Access to Complex Data