Show simple item record

dc.contributor.authorGölge, Erenen_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialZurich, Switzerland
dc.date.accessioned2016-02-08T11:41:48Zen_US
dc.date.available2016-02-08T11:41:48Zen_US
dc.date.issued2014-09en_US
dc.identifier.urihttp://hdl.handle.net/11693/27008
dc.descriptionDate of Conference: 6-12 September, 2014
dc.descriptionConference name: 13 th European Conference on Computer Vision Computer Vision – ECCV 2014
dc.description.abstractWe attack the problem of learning concepts automatically from noisy Web image search results. The idea is based on discovering common characteristics shared among subsets of images by posing a method that is able to organise the data while eliminating irrelevant instances. We propose a novel clustering and outlier detection method, namely Concept Map (CMAP). Given an image collection returned for a concept query, CMAP provides clusters pruned from outliers. Each cluster is used to train a model representing a different characteristics of the concept. The proposed method outperforms the state-of-the-art studies on the task of learning from noisy web data for low-level attributes, as well as high level object categories. It is also competitive with the supervised methods in learning scene concepts. Moreover, results on naming faces support the generalisation capability of the CMAP framework to different domains. CMAP is capable to work at large scale with no supervision through exploiting the available sources. © 2014 Springer International Publishing.en_US
dc.language.isoEnglishen_US
dc.source.title13 th European Conference on Computer Vision Computer Vision – ECCV 2014en_US
dc.relation.isversionofhttps://doi.org/10.1007/978-3-319-10584-0_29en_US
dc.subjectAttributesen_US
dc.subjectClustering and outlier detectionen_US
dc.subjectConceptMapen_US
dc.subjectObject detectionen_US
dc.subjectScene classificationen_US
dc.subjectSemi- supervised model learningen_US
dc.subjectWeakly-labelled dataen_US
dc.subjectArtificial intelligenceen_US
dc.subjectComputer scienceen_US
dc.subjectComputersen_US
dc.subjectModel learningen_US
dc.subjectOutlier Detectionen_US
dc.subjectStatisticsen_US
dc.titleConceptMap: mining noisy web data for concept learningen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage439en_US
dc.citation.epage455en_US
dc.identifier.doi10.1007/978-3-319-10584-0_29en_US
dc.publisherSpringeren_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record