Show simple item record

dc.contributor.authorPatraucean, Viorica
dc.contributor.authorOvsjanikov, M
dc.date.accessioned2015-05-28T11:18:10Z
dc.date.available2015-05-28T11:18:10Z
dc.date.issued2015
dc.identifier.citation14th IAPR International Conference on Machine Vision Applications (MVA), 2015, 14 - 17. DOI: 10.1109/MVA.2015.7153122
dc.identifier.isbn9784901122153
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/248058
dc.description.abstractObject instance recognition approaches based on the bag-of-words model are severely affected by the loss of spatial consistency during retrieval. As a result, costly RANSAC verification is needed to ensure geometric consistency between the query and the retrieved images. A common alternative is to inject geometric informa- tion directly into the retrieval procedure, by endowing the visual words with additional information. Most of the existing approaches in this category can efficiently handle only restricted classes of geometric transfor- mations, including scale and translation. In this pa- per, we propose a simple and efficient scheme that can cover the more complex class of full affine transforma- tions. We demonstrate the usefulness of our approach in the case of planar object instance recognition, such as recognition of books, logos, traffic signs, etc.
dc.description.sponsorshipThis work was funded by a Google Faculty Research Award, the Marie Curie grant CIG-334283-HRGP, a CNRS chaire d'excellence.
dc.languageEnglish
dc.language.isoen
dc.publisherIEEE
dc.titleAffine invariant visual phrases for object instance recognition
dc.typeConference Object
dc.description.versionThis is the author accepted manuscript. The final version is available at http://dx.doi.org/10.1109/MVA.2015.7153122
prism.endingPage17
prism.publicationDate2015
prism.publicationNameProceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
prism.startingPage14
rioxxterms.versionofrecord10.1109/MVA.2015.7153122
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2015-05-28
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.conference-name2015 14th IAPR International Conference on Machine Vision Applications (MVA)
pubs.conference-start-date2015-05-18
pubs.conference-finish-date2015-05-22


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record