Words-of-interest selection based on temporal motion coherence for video retrieval

Wang, Lei; Song, Dawei and Elyan, Eyad (2011). Words-of-interest selection based on temporal motion coherence for video retrieval. In: 34th Annual ACM SIGIR Conference (SIGIR'2011) , 24-28 July 2011, Beijing, China.

Full text available as:

Preview

PDF (Version of Record) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Download (434Kb)

DOI (Digital Object Identifier) Link:	http://dx.doi.org/doi:10.1145/2009916.2010117
Google Scholar:	Look up in Google Scholar

Abstract

The "Bag of Visual Words" (BoW) framework has been widely used in query-by-example video retrieval to model the visual content by a set of quantized local feature descriptors. In this paper, we propose a novel technique to enhance BoW by the selection of Word-of-Interest (WoI) that utilizes the quantified temporal motion coherence of the visual words between the adjacent frames in the query example. Experiments carried out using TRECVID datasets show that our technique improves the retrieval performance of the classical BoW-based approach.

Item Type:	Conference Item
Copyright Holders:	2011 The Authors
Extra Information:	SIGIR’11, July 24–28, 2011, Beijing, China. ACM 978-1-4503-0757-4/11/07 pp.1197-1198
Keywords:	Bag of Visual Words; words-of-interest; video retrieval; temporal motion coherence
Academic Unit/Department:	Mathematics, Computing and Technology > Computing
Item ID:	33903
Depositing User:	Dawei Song
Date Deposited:	21 Jun 2012 08:54
Last Modified:	25 Oct 2012 16:00
URI:	http://oro.open.ac.uk/id/eprint/33903

Actions (login may be required)

	View Item
RDF+XMLBibTeXRDF+N-TriplesJSONDublin CoreAtomOAI-ORE Resource Map (Atom Format)Simple MetadataReferMETSOAI-ORE Resource Map (RDF Format)HTML CitationASCII CitationMultiline CSVRefMan RIS Format (UTF-8)OpenURL ContextObjectEndNoteMODSOpenURL ContextObject in SpanMPEG-21 DIDLEP3 XMLRefMan RIS FormatRDF+N3Eprints Application Profile	Public: Report issue / request change