Compact Video Description for Copy Detection with Precise Temporal Alignment

Matthijs Douze 1 Hervé Jégou 2 Cordelia Schmid 1 Patrick Pérez 3
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper introduces a very compact yet discriminative video description, which allows example-based search in a large number of frames corresponding to thousands of hours of video. Our description extracts one descriptor per indexed video frame by aggregating a set of local descriptors. These frame descriptors are encoded using a time-aware hierarchical indexing structure. A modified temporal Hough voting scheme is used to rank the retrieved database videos and estimate segments in them that match the query. If we use a dense temporal description of the videos, matched video segments are localized with excellent precision. Experimental results on the Trecvid 2008 copy detection task and a set of 38000 videos from YouTube show that our method offers an excellent trade-off between search accuracy, efficiency and memory usage.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [21 references]  Display  Hide  Download


https://hal.inria.fr/inria-00548641
Contributor : Hervé Jégou <>
Submitted on : Tuesday, March 22, 2011 - 9:22:46 PM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Document(s) archivé(s) le : Sunday, December 4, 2016 - 1:45:58 AM

Files

paper_hal.pdf
Files produced by the author(s)

Identifiers

Citation

Matthijs Douze, Hervé Jégou, Cordelia Schmid, Patrick Pérez. Compact Video Description for Copy Detection with Precise Temporal Alignment. ECCV 2010 - European Conference on Computer Vision, Sep 2010, Heraklion, Greece. pp.522-535, ⟨10.1007/978-3-642-15549-9_38⟩. ⟨inria-00548641v3⟩

Share

Metrics

Record views

1531

Files downloads

528