RECOD @ placing task of MediaEval 2015

dc.contributorUniversidade Estadual de Campinas (UNICAMP)
dc.contributorUniversidade de São Paulo (USP)
dc.contributorUniversity of Feira de Santana
dc.contributorSAMSUNG Research Institute
dc.contributorUniversidade Estadual Paulista (Unesp)
dc.contributorUniversidade Federal de Minas Gerais (UFMG)
dc.date.accessioned2018-12-11T16:43:57Z
dc.date.available2018-12-11T16:43:57Z
dc.date.created2018-12-11T16:43:57Z
dc.date.issued2015-01-01
dc.identifierCEUR Workshop Proceedings, v. 1436.
dc.identifier1613-0073
dc.identifierhttp://hdl.handle.net/11449/169000
dc.identifier2-s2.0-84989842269
dc.description.abstractIn this work, we describe the approach proposed by the RECOD team for the Placing Task, Locale-based sub-task, at MediaEval 2015. Our approach is based on the use of as much evidence as possible (textual, visual, and/or audio descriptors) to automatically assign geographical locations to images and videos.
dc.languageeng
dc.relationCEUR Workshop Proceedings
dc.relation0,167
dc.rightsAcesso aberto
dc.sourceScopus
dc.subjectDescriptors
dc.subjectGeographical locations
dc.subjectSubtasks
dc.titleRECOD @ placing task of MediaEval 2015
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución