Show simple item record

dc.contributor.authorZhang, Q.en_US
dc.contributor.authorCorvaglia, M.en_US
dc.contributor.authorAksoy, S.en_US
dc.contributor.authorNaci, U.en_US
dc.contributor.authorAdami, N.en_US
dc.contributor.authorAginako, N.en_US
dc.contributor.authorAlatan, A.en_US
dc.contributor.authorAlexandre, L. A.en_US
dc.contributor.authorAlmeida, P.en_US
dc.contributor.authorAvrithis, Y.en_US
dc.contributor.authorBenois-Pineau, J.en_US
dc.contributor.authorChandramouli, K.en_US
dc.contributor.authorDamnjanovic, U.en_US
dc.contributor.authorEsen, E.en_US
dc.contributor.authorGoya, J.en_US
dc.contributor.authorGrzegorzek, M.en_US
dc.contributor.authorHanjalic, A.en_US
dc.contributor.authorIzquierdo, E.en_US
dc.contributor.authorJarina, R.en_US
dc.contributor.authorKapsalas, P.en_US
dc.contributor.authorKompatsiaris, I.en_US
dc.contributor.authorKuba, M.en_US
dc.contributor.authorLeonardi, R.en_US
dc.contributor.authorMakris, L.en_US
dc.contributor.authorMansencal, B.en_US
dc.contributor.authorMezaris, V.en_US
dc.contributor.authorMoumtzidou, A.en_US
dc.contributor.authorMylonas, P.en_US
dc.contributor.authorNikolopoulos, S.en_US
dc.contributor.authorPiatrik, T.en_US
dc.contributor.authorPinheiro, A. M. G.en_US
dc.contributor.authorReljin, B.en_US
dc.contributor.authorSpyrou, E.en_US
dc.contributor.authorTolias, G.en_US
dc.contributor.authorVrochidis, S.en_US
dc.contributor.authorYakın, G.en_US
dc.contributor.authorZajic, G.en_US
dc.date.accessioned2016-02-08T11:44:59Z
dc.date.available2016-02-08T11:44:59Z
dc.date.issued2007en_US
dc.identifier.urihttp://hdl.handle.net/11693/27117
dc.description.abstractIn this paper, we give an overview of the four tasks submitted to TRECVID 2007 by COST292. In shot boundary (SB) detection task, four SB detectors have been developed and the results are merged using two merging algorithms. The framework developed for the high-level feature extraction task comprises four systems. The first system transforms a set of low-level descriptors into the semantic space using Latent Semantic Analysis and utilises neural networks for feature detection. The second system uses a Bayesian classifier trained with a "bag of subregions". The third system uses a multi-modal classifier based on SVMs and several descriptors. The fourth system uses two image classifiers based on ant colony optimisation and particle swarm optimisation respectively. The system submitted to the search task is an interactive retrieval application combining retrieval functionalities in various modalities with a user interface supporting automatic and interactive search over all queries submitted. Finally, the rushes task submission is based on a video summarisation and browsing system comprising two different interest curve algorithms and three features.en_US
dc.language.isoEnglishen_US
dc.source.title2007 TREC Video Retrieval Evaluation Notebook Papersen_US
dc.subjectAnt colony optimizationen_US
dc.subjectFeature extractionen_US
dc.subjectParticle swarm optimization (PSO)en_US
dc.subjectSemanticsen_US
dc.subjectUser interfacesen_US
dc.subjectAnt colony optimisationen_US
dc.subjectBayesian classifieren_US
dc.subjectHigh-level feature extractionsen_US
dc.subjectInteractive retrievalen_US
dc.subjectLatent Semantic Analysisen_US
dc.subjectLow level descriptorsen_US
dc.subjectParticle swarm optimisationen_US
dc.subjectVideo summarisationen_US
dc.subjectImage retrievalen_US
dc.titleThe COST292 experimental framework for TRECVID 2007en_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage1en_US
dc.citation.epage16en_US
dc.publisherNational Institute of Standards and Technologyen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record