Matches in SemOpenAlex for { <https://semopenalex.org/work/W2079267072> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2079267072 abstract "We address the problem of localisation of objects as bounding boxes in images with weak labels. This weakly supervised object localisation problem has been tackled in the past using discriminative models where each object class is localised independently from other classes. We propose a novel framework based on Bayesian joint topic modelling. Our framework has three distinctive advantages over previous works: (1) All object classes and image backgrounds are modelled jointly together in a single generative model so that explaining away inference can resolve ambiguity and lead to better learning and localisation. (2) The Bayesian formulation of the model enables easy integration of prior knowledge about object appearance to compensate for limited supervision. (3) Our model can be learned with a mixture of weakly labelled and unlabelled data, allowing the large volume of unlabelled images on the Internet to be exploited for learning. Extensive experiments on the challenging VOC dataset demonstrate that our approach outperforms the state-of-the-art competitors." @default.
- W2079267072 created "2016-06-24" @default.
- W2079267072 creator A5005060833 @default.
- W2079267072 creator A5014436524 @default.
- W2079267072 creator A5087823932 @default.
- W2079267072 date "2013-12-01" @default.
- W2079267072 modified "2023-09-27" @default.
- W2079267072 title "Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation" @default.
- W2079267072 cites W2020477327 @default.
- W2079267072 cites W2024047694 @default.
- W2079267072 cites W2033012377 @default.
- W2079267072 cites W2061629163 @default.
- W2079267072 cites W2069678212 @default.
- W2079267072 cites W2099528205 @default.
- W2079267072 cites W2112343299 @default.
- W2079267072 cites W2115733720 @default.
- W2079267072 cites W2125337786 @default.
- W2079267072 cites W2128715914 @default.
- W2079267072 cites W2129004009 @default.
- W2079267072 cites W2145508099 @default.
- W2079267072 cites W2154840533 @default.
- W2079267072 cites W2168356304 @default.
- W2079267072 cites W2533218643 @default.
- W2079267072 cites W2963934231 @default.
- W2079267072 cites W4212863985 @default.
- W2079267072 cites W4248892431 @default.
- W2079267072 doi "https://doi.org/10.1109/iccv.2013.371" @default.
- W2079267072 hasPublicationYear "2013" @default.
- W2079267072 type Work @default.
- W2079267072 sameAs 2079267072 @default.
- W2079267072 citedByCount "57" @default.
- W2079267072 countsByYear W20792670722014 @default.
- W2079267072 countsByYear W20792670722015 @default.
- W2079267072 countsByYear W20792670722016 @default.
- W2079267072 countsByYear W20792670722017 @default.
- W2079267072 countsByYear W20792670722018 @default.
- W2079267072 countsByYear W20792670722019 @default.
- W2079267072 countsByYear W20792670722020 @default.
- W2079267072 countsByYear W20792670722021 @default.
- W2079267072 countsByYear W20792670722022 @default.
- W2079267072 crossrefType "proceedings-article" @default.
- W2079267072 hasAuthorship W2079267072A5005060833 @default.
- W2079267072 hasAuthorship W2079267072A5014436524 @default.
- W2079267072 hasAuthorship W2079267072A5087823932 @default.
- W2079267072 hasBestOaLocation W20792670722 @default.
- W2079267072 hasConcept C107673813 @default.
- W2079267072 hasConcept C119857082 @default.
- W2079267072 hasConcept C153180895 @default.
- W2079267072 hasConcept C154945302 @default.
- W2079267072 hasConcept C155846161 @default.
- W2079267072 hasConcept C160234255 @default.
- W2079267072 hasConcept C167966045 @default.
- W2079267072 hasConcept C199360897 @default.
- W2079267072 hasConcept C2776214188 @default.
- W2079267072 hasConcept C2780522230 @default.
- W2079267072 hasConcept C2781238097 @default.
- W2079267072 hasConcept C39890363 @default.
- W2079267072 hasConcept C41008148 @default.
- W2079267072 hasConcept C63584917 @default.
- W2079267072 hasConcept C97931131 @default.
- W2079267072 hasConceptScore W2079267072C107673813 @default.
- W2079267072 hasConceptScore W2079267072C119857082 @default.
- W2079267072 hasConceptScore W2079267072C153180895 @default.
- W2079267072 hasConceptScore W2079267072C154945302 @default.
- W2079267072 hasConceptScore W2079267072C155846161 @default.
- W2079267072 hasConceptScore W2079267072C160234255 @default.
- W2079267072 hasConceptScore W2079267072C167966045 @default.
- W2079267072 hasConceptScore W2079267072C199360897 @default.
- W2079267072 hasConceptScore W2079267072C2776214188 @default.
- W2079267072 hasConceptScore W2079267072C2780522230 @default.
- W2079267072 hasConceptScore W2079267072C2781238097 @default.
- W2079267072 hasConceptScore W2079267072C39890363 @default.
- W2079267072 hasConceptScore W2079267072C41008148 @default.
- W2079267072 hasConceptScore W2079267072C63584917 @default.
- W2079267072 hasConceptScore W2079267072C97931131 @default.
- W2079267072 hasLocation W20792670721 @default.
- W2079267072 hasLocation W20792670722 @default.
- W2079267072 hasOpenAccess W2079267072 @default.
- W2079267072 hasPrimaryLocation W20792670721 @default.
- W2079267072 hasRelatedWork W1576360539 @default.
- W2079267072 hasRelatedWork W1981814724 @default.
- W2079267072 hasRelatedWork W2154833362 @default.
- W2079267072 hasRelatedWork W2770426046 @default.
- W2079267072 hasRelatedWork W2890982112 @default.
- W2079267072 hasRelatedWork W2901597764 @default.
- W2079267072 hasRelatedWork W3007910378 @default.
- W2079267072 hasRelatedWork W3071470454 @default.
- W2079267072 hasRelatedWork W4319653897 @default.
- W2079267072 hasRelatedWork W4386243278 @default.
- W2079267072 isParatext "false" @default.
- W2079267072 isRetracted "false" @default.
- W2079267072 magId "2079267072" @default.
- W2079267072 workType "article" @default.