Show simple item record

dc.contributor.authorMohedano, Eva
dc.contributor.authorSalvador Aguilera, Amaia
dc.contributor.authorMcGuinness, Kevin
dc.contributor.authorMarqués Acosta, Fernando
dc.contributor.authorO'Connor, Noel
dc.contributor.authorGiró Nieto, Xavier
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2016-11-22T11:05:05Z
dc.date.available2016-11-22T11:05:05Z
dc.date.issued2016
dc.identifier.citationMohedano, E., Salvador, A., McGuinness, K., Marques, F., O'Connor, N., Giro, X. Bags of local convolutional features for scalable instance search. A: ACM International Conference on Multimedia Retrieval. "Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval". New York City: Association for Computing Machinery (ACM), 2016, p. 327-331.
dc.identifier.isbn978-1-4503-4359-6
dc.identifier.urihttp://hdl.handle.net/2117/96981
dc.description.abstractThis work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an assignment map, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtaining object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.
dc.format.extent5 p.
dc.language.isoeng
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshNeural networks (Computer science)
dc.subject.otherInstance retrieval
dc.subject.otherConvolutional neural networks
dc.subject.otherBag of words
dc.titleBags of local convolutional features for scalable instance search
dc.typeConference lecture
dc.subject.lemacXarxes neuronals (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1145/2911996.2912061
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://dl.acm.org/citation.cfm?id=2912061&CFID=802652264&CFTOKEN=23661596
dc.rights.accessOpen Access
local.identifier.drac18567536
dc.description.versionPreprint
local.citation.authorMohedano, E.; Salvador, A.; McGuinness, K.; Marques, F.; O'Connor, N.; Giro, X.
local.citation.contributorACM International Conference on Multimedia Retrieval
local.citation.pubplaceNew York City
local.citation.publicationNameProceedings of the 2016 ACM on International Conference on Multimedia Retrieval
local.citation.startingPage327
local.citation.endingPage331


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record