Matches in SemOpenAlex for { <https://semopenalex.org/work/W2026377462> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2026377462 abstract "Recently the use of image attributes as image descriptors has drawn great attention. This is because the resulting descriptors extracted using these attributes are human understandable as well as machine readable. Although the image attributes are generally semantically meaningful, they may not be discriminative. As such, prior works often consider a discriminative learning approach that could discover discriminative attributes. Nevertheless, the resulting learned attributes could lose their semantic meaning. To that end, in the present work, we study two properties of attributes: discriminative power and reliability. We then propose a novel greedy algorithm called Discriminative and Reliable Attribute Learning (DRAL) which selects a subset of attributes which maximises an objective function incorporating the two properties. We compare our proposed system to the recent state-of-the-art approach, called Direct Attribute Prediction (DAP) for the zero-shot learning task on the Animal with Attributes (AwA) dataset. The results show that our proposed approach can achieve similar performance to this state-of-the-art approach while using a significantly smaller number of attributes." @default.
- W2026377462 created "2016-06-24" @default.
- W2026377462 creator A5018607348 @default.
- W2026377462 creator A5058539660 @default.
- W2026377462 creator A5063048878 @default.
- W2026377462 creator A5089800102 @default.
- W2026377462 date "2014-08-01" @default.
- W2026377462 modified "2023-10-17" @default.
- W2026377462 title "Automatic Image Attribute Selection for Zero-Shot Learning of Object Categories" @default.
- W2026377462 cites W157861987 @default.
- W2026377462 cites W1964763677 @default.
- W2026377462 cites W1994676165 @default.
- W2026377462 cites W2038765747 @default.
- W2026377462 cites W2045659016 @default.
- W2026377462 cites W2046589280 @default.
- W2026377462 cites W2067936711 @default.
- W2026377462 cites W2083704848 @default.
- W2026377462 cites W2084435358 @default.
- W2026377462 cites W2098411764 @default.
- W2026377462 cites W2113584252 @default.
- W2026377462 cites W2119605622 @default.
- W2026377462 cites W2139212933 @default.
- W2026377462 cites W2144502914 @default.
- W2026377462 cites W2151103935 @default.
- W2026377462 cites W2154683974 @default.
- W2026377462 cites W2157032868 @default.
- W2026377462 cites W2161969291 @default.
- W2026377462 cites W2162762921 @default.
- W2026377462 cites W2244035566 @default.
- W2026377462 cites W2294130536 @default.
- W2026377462 cites W2536626143 @default.
- W2026377462 cites W4205398292 @default.
- W2026377462 cites W2072141295 @default.
- W2026377462 doi "https://doi.org/10.1109/icpr.2014.452" @default.
- W2026377462 hasPublicationYear "2014" @default.
- W2026377462 type Work @default.
- W2026377462 sameAs 2026377462 @default.
- W2026377462 citedByCount "16" @default.
- W2026377462 countsByYear W20263774622015 @default.
- W2026377462 countsByYear W20263774622016 @default.
- W2026377462 countsByYear W20263774622017 @default.
- W2026377462 countsByYear W20263774622018 @default.
- W2026377462 countsByYear W20263774622019 @default.
- W2026377462 countsByYear W20263774622020 @default.
- W2026377462 countsByYear W20263774622022 @default.
- W2026377462 crossrefType "proceedings-article" @default.
- W2026377462 hasAuthorship W2026377462A5018607348 @default.
- W2026377462 hasAuthorship W2026377462A5058539660 @default.
- W2026377462 hasAuthorship W2026377462A5063048878 @default.
- W2026377462 hasAuthorship W2026377462A5089800102 @default.
- W2026377462 hasConcept C115961682 @default.
- W2026377462 hasConcept C119857082 @default.
- W2026377462 hasConcept C153180895 @default.
- W2026377462 hasConcept C154945302 @default.
- W2026377462 hasConcept C162324750 @default.
- W2026377462 hasConcept C187736073 @default.
- W2026377462 hasConcept C2780451532 @default.
- W2026377462 hasConcept C2781238097 @default.
- W2026377462 hasConcept C41008148 @default.
- W2026377462 hasConcept C52622490 @default.
- W2026377462 hasConcept C75294576 @default.
- W2026377462 hasConcept C81917197 @default.
- W2026377462 hasConcept C97931131 @default.
- W2026377462 hasConceptScore W2026377462C115961682 @default.
- W2026377462 hasConceptScore W2026377462C119857082 @default.
- W2026377462 hasConceptScore W2026377462C153180895 @default.
- W2026377462 hasConceptScore W2026377462C154945302 @default.
- W2026377462 hasConceptScore W2026377462C162324750 @default.
- W2026377462 hasConceptScore W2026377462C187736073 @default.
- W2026377462 hasConceptScore W2026377462C2780451532 @default.
- W2026377462 hasConceptScore W2026377462C2781238097 @default.
- W2026377462 hasConceptScore W2026377462C41008148 @default.
- W2026377462 hasConceptScore W2026377462C52622490 @default.
- W2026377462 hasConceptScore W2026377462C75294576 @default.
- W2026377462 hasConceptScore W2026377462C81917197 @default.
- W2026377462 hasConceptScore W2026377462C97931131 @default.
- W2026377462 hasLocation W20263774621 @default.
- W2026377462 hasOpenAccess W2026377462 @default.
- W2026377462 hasPrimaryLocation W20263774621 @default.
- W2026377462 hasRelatedWork W2037311958 @default.
- W2026377462 hasRelatedWork W2285052147 @default.
- W2026377462 hasRelatedWork W2406522397 @default.
- W2026377462 hasRelatedWork W2565656575 @default.
- W2026377462 hasRelatedWork W2738461075 @default.
- W2026377462 hasRelatedWork W2806866760 @default.
- W2026377462 hasRelatedWork W2905846897 @default.
- W2026377462 hasRelatedWork W2940977206 @default.
- W2026377462 hasRelatedWork W3005023910 @default.
- W2026377462 hasRelatedWork W3120710434 @default.
- W2026377462 isParatext "false" @default.
- W2026377462 isRetracted "false" @default.
- W2026377462 magId "2026377462" @default.
- W2026377462 workType "article" @default.