Open Access System for Information Sharing

Login Library

 

Article
Cited 50 time in webofscience Cited 68 time in scopus
Metadata Downloads
Full metadata record
Files in This Item:
There are no files associated with this item.
DC FieldValueLanguage
dc.contributor.authorHam, Bumsub-
dc.contributor.authorCHO, MINSU-
dc.contributor.authorSchmid, Cordelia-
dc.contributor.authorPonce, Jean-
dc.date.accessioned2018-05-04T02:33:53Z-
dc.date.available2018-05-04T02:33:53Z-
dc.date.created2018-03-05-
dc.date.issued2018-01-
dc.identifier.issn0162-8828-
dc.identifier.urihttps://oasis.postech.ac.kr/handle/2014.oak/41190-
dc.description.abstractFinding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that the corresponding sparse proposal flow can effectively be transformed into a conventional dense flow field. We introduce two new challenging datasets that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use these benchmarks to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.-
dc.languageEnglish-
dc.publisherIEEE-
dc.relation.isPartOfIEEE Transactions on Pattern Analysis and Machine Intelligence-
dc.subjectArtificial intelligence-
dc.subjectClutter (information theory)-
dc.subjectComputer vision-
dc.subjectElectronic mail-
dc.subjectRobustness (control systems)-
dc.subjectBenchmark testing-
dc.subjectdense scene correspondence-
dc.subjectObject proposals-
dc.subjectOptical imaging-
dc.subjectProposals-
dc.subjectSemantics-
dc.titleProposal Flow: Semantic Correspondences from Object Proposals-
dc.typeArticle-
dc.identifier.doi10.1109/TPAMI.2017.2724510-
dc.type.rimsART-
dc.identifier.bibliographicCitationIEEE Transactions on Pattern Analysis and Machine Intelligence, v.40, no.7, pp.1711 - 1725-
dc.identifier.wosid000434294800013-
dc.citation.endPage1725-
dc.citation.number7-
dc.citation.startPage1711-
dc.citation.titleIEEE Transactions on Pattern Analysis and Machine Intelligence-
dc.citation.volume40-
dc.contributor.affiliatedAuthorCHO, MINSU-
dc.identifier.scopusid2-s2.0-85023646116-
dc.description.journalClass1-
dc.description.journalClass1-
dc.type.docTypeARTICLE-
dc.subject.keywordPlusBASE-LINE STEREO-
dc.subject.keywordPlusDENSE CORRESPONDENCES-
dc.subject.keywordPlusLOCATION-
dc.subject.keywordPlusMODELS-
dc.subject.keywordPlusPARTS-
dc.subject.keywordAuthorSemantic flow-
dc.subject.keywordAuthorobject proposals-
dc.subject.keywordAuthorscene alignment-
dc.subject.keywordAuthordense scene correspondence-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalResearchAreaEngineering-

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

조민수CHO, MINSU
Dept of Computer Science & Enginrg
Read more

Views & Downloads

Browse