Matches in SemOpenAlex for { <https://semopenalex.org/work/W2582159720> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2582159720 abstract "Zero-shot Learning (ZSL) can leverage attributes to recognise unseen instances. However, the training data is limited and cannot adequately discriminate fine-grained classes with similar attributes. In this paper, we propose a complementary procedure that inversely makes use of attributes to infer discriminative visual features for unseen classes. In this way, ZSL is fully converted into conventional supervised classification, where robust classifiers can be employed to address the fine-grained problem. To infer high-quality unseen data, we propose a novel algorithm named Orthogonal Semantic-Visual Embedding (OSVE) that can discover the tiny visual differences between different instances under the same attribute by an orthogonal embedding space. On two fine-grained benchmarks, CUB and SUN, our method remarkably improves the state-of-the-art results under standard ZSL settings. We further challenge the Open ZSL problem where the number of seen classes is significantly smaller than that of unseen classes. Substantial experiments manifest that the inferred visual features can be successfully fed to SVM which can effectively discriminate unseen classes from fine-grained open candidates." @default.
- W2582159720 created "2017-02-03" @default.
- W2582159720 creator A5011037821 @default.
- W2582159720 creator A5063481044 @default.
- W2582159720 creator A5082634513 @default.
- W2582159720 date "2017-03-01" @default.
- W2582159720 modified "2023-09-26" @default.
- W2582159720 title "Towards Fine-Grained Open Zero-Shot Learning: Inferring Unseen Visual Features from Attributes" @default.
- W2582159720 cites W1902024696 @default.
- W2582159720 cites W1944630830 @default.
- W2582159720 cites W1992454046 @default.
- W2582159720 cites W1999818274 @default.
- W2582159720 cites W2003723718 @default.
- W2582159720 cites W2032699694 @default.
- W2582159720 cites W2077071968 @default.
- W2582159720 cites W2088227600 @default.
- W2582159720 cites W2098411764 @default.
- W2582159720 cites W2109317801 @default.
- W2582159720 cites W2116447720 @default.
- W2582159720 cites W2128532956 @default.
- W2582159720 cites W2157032868 @default.
- W2582159720 cites W2209594346 @default.
- W2582159720 cites W2289084343 @default.
- W2582159720 cites W2313079257 @default.
- W2582159720 cites W2334493732 @default.
- W2582159720 cites W2398118205 @default.
- W2582159720 cites W2405223529 @default.
- W2582159720 cites W2523479226 @default.
- W2582159720 cites W2581186283 @default.
- W2582159720 cites W2592773426 @default.
- W2582159720 cites W2964086552 @default.
- W2582159720 cites W3100093508 @default.
- W2582159720 cites W3143107425 @default.
- W2582159720 doi "https://doi.org/10.1109/wacv.2017.110" @default.
- W2582159720 hasPublicationYear "2017" @default.
- W2582159720 type Work @default.
- W2582159720 sameAs 2582159720 @default.
- W2582159720 citedByCount "12" @default.
- W2582159720 countsByYear W25821597202017 @default.
- W2582159720 countsByYear W25821597202018 @default.
- W2582159720 countsByYear W25821597202019 @default.
- W2582159720 countsByYear W25821597202020 @default.
- W2582159720 countsByYear W25821597202021 @default.
- W2582159720 countsByYear W25821597202022 @default.
- W2582159720 crossrefType "proceedings-article" @default.
- W2582159720 hasAuthorship W2582159720A5011037821 @default.
- W2582159720 hasAuthorship W2582159720A5063481044 @default.
- W2582159720 hasAuthorship W2582159720A5082634513 @default.
- W2582159720 hasBestOaLocation W25821597202 @default.
- W2582159720 hasConcept C138885662 @default.
- W2582159720 hasConcept C154945302 @default.
- W2582159720 hasConcept C178790620 @default.
- W2582159720 hasConcept C185592680 @default.
- W2582159720 hasConcept C2778344882 @default.
- W2582159720 hasConcept C2780813799 @default.
- W2582159720 hasConcept C41008148 @default.
- W2582159720 hasConcept C41895202 @default.
- W2582159720 hasConceptScore W2582159720C138885662 @default.
- W2582159720 hasConceptScore W2582159720C154945302 @default.
- W2582159720 hasConceptScore W2582159720C178790620 @default.
- W2582159720 hasConceptScore W2582159720C185592680 @default.
- W2582159720 hasConceptScore W2582159720C2778344882 @default.
- W2582159720 hasConceptScore W2582159720C2780813799 @default.
- W2582159720 hasConceptScore W2582159720C41008148 @default.
- W2582159720 hasConceptScore W2582159720C41895202 @default.
- W2582159720 hasLocation W25821597201 @default.
- W2582159720 hasLocation W25821597202 @default.
- W2582159720 hasOpenAccess W2582159720 @default.
- W2582159720 hasPrimaryLocation W25821597201 @default.
- W2582159720 hasRelatedWork W2092417575 @default.
- W2582159720 hasRelatedWork W2160983719 @default.
- W2582159720 hasRelatedWork W2301135490 @default.
- W2582159720 hasRelatedWork W2387675639 @default.
- W2582159720 hasRelatedWork W2981091784 @default.
- W2582159720 hasRelatedWork W3107474891 @default.
- W2582159720 hasRelatedWork W4296181602 @default.
- W2582159720 hasRelatedWork W4306975314 @default.
- W2582159720 hasRelatedWork W4307059355 @default.
- W2582159720 hasRelatedWork W4307315102 @default.
- W2582159720 isParatext "false" @default.
- W2582159720 isRetracted "false" @default.
- W2582159720 magId "2582159720" @default.
- W2582159720 workType "article" @default.