Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989779801> ?p ?o ?g. }
- W2989779801 abstract "Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for visual-semantic embedding, while neglecting the effect of learning discriminative visual features. In this paper, we study the significance of the discriminative region localization. We propose a semantic-guided multi-attention localization model, which automatically discovers the most discriminative parts of objects for zero-shot learning without any human annotations. Our model jointly learns cooperative global and local features from the whole object as well as the detected parts to categorize objects based on semantic descriptions. Moreover, with the joint supervision of embedding softmax loss and class-center triplet loss, the model is encouraged to learn features with high inter-class dispersion and intra-class compactness. Through comprehensive experiments on three widely used zero-shot learning benchmarks, we show the efficacy of the multi-attention localization and our proposed approach improves the state-of-the-art results by a considerable margin." @default.
- W2989779801 created "2019-12-05" @default.
- W2989779801 creator A5022800038 @default.
- W2989779801 creator A5028927697 @default.
- W2989779801 creator A5029036789 @default.
- W2989779801 creator A5039640321 @default.
- W2989779801 creator A5041455283 @default.
- W2989779801 date "2019-03-01" @default.
- W2989779801 modified "2023-09-27" @default.
- W2989779801 title "Semantic-Guided Multi-Attention Localization for Zero-Shot Learning" @default.
- W2989779801 cites W1797268635 @default.
- W2989779801 cites W1861492603 @default.
- W2989779801 cites W1928906481 @default.
- W2989779801 cites W1959608418 @default.
- W2989779801 cites W2099471712 @default.
- W2989779801 cites W2108598243 @default.
- W2989779801 cites W2123024445 @default.
- W2989779801 cites W2171061940 @default.
- W2989779801 cites W2207849498 @default.
- W2989779801 cites W2289084343 @default.
- W2989779801 cites W2295107390 @default.
- W2989779801 cites W2328434568 @default.
- W2989779801 cites W2462457117 @default.
- W2989779801 cites W2479109623 @default.
- W2989779801 cites W2518965973 @default.
- W2989779801 cites W2520774990 @default.
- W2989779801 cites W2533598788 @default.
- W2989779801 cites W2552383788 @default.
- W2989779801 cites W2601450892 @default.
- W2989779801 cites W2605805765 @default.
- W2989779801 cites W2611632661 @default.
- W2989779801 cites W2737725206 @default.
- W2989779801 cites W2751303714 @default.
- W2989779801 cites W2773003563 @default.
- W2989779801 cites W2791906491 @default.
- W2989779801 cites W2799215068 @default.
- W2989779801 cites W2950276680 @default.
- W2989779801 cites W2951538594 @default.
- W2989779801 cites W2952073179 @default.
- W2989779801 cites W2962677366 @default.
- W2989779801 cites W2962858109 @default.
- W2989779801 cites W2963341924 @default.
- W2989779801 cites W2963499153 @default.
- W2989779801 cites W2963960318 @default.
- W2989779801 cites W2963971375 @default.
- W2989779801 cites W2964304707 @default.
- W2989779801 cites W2965638232 @default.
- W2989779801 cites W2969462325 @default.
- W2989779801 cites W2970733445 @default.
- W2989779801 cites W2981720610 @default.
- W2989779801 cites W3101227480 @default.
- W2989779801 cites W603908379 @default.
- W2989779801 cites W652269744 @default.
- W2989779801 cites W93016980 @default.
- W2989779801 hasPublicationYear "2019" @default.
- W2989779801 type Work @default.
- W2989779801 sameAs 2989779801 @default.
- W2989779801 citedByCount "4" @default.
- W2989779801 countsByYear W29897798012019 @default.
- W2989779801 countsByYear W29897798012020 @default.
- W2989779801 countsByYear W29897798012021 @default.
- W2989779801 crossrefType "posted-content" @default.
- W2989779801 hasAuthorship W2989779801A5022800038 @default.
- W2989779801 hasAuthorship W2989779801A5028927697 @default.
- W2989779801 hasAuthorship W2989779801A5029036789 @default.
- W2989779801 hasAuthorship W2989779801A5039640321 @default.
- W2989779801 hasAuthorship W2989779801A5041455283 @default.
- W2989779801 hasConcept C103278499 @default.
- W2989779801 hasConcept C108583219 @default.
- W2989779801 hasConcept C115961682 @default.
- W2989779801 hasConcept C119857082 @default.
- W2989779801 hasConcept C120665830 @default.
- W2989779801 hasConcept C121332964 @default.
- W2989779801 hasConcept C130318100 @default.
- W2989779801 hasConcept C153180895 @default.
- W2989779801 hasConcept C154945302 @default.
- W2989779801 hasConcept C188441871 @default.
- W2989779801 hasConcept C192209626 @default.
- W2989779801 hasConcept C204321447 @default.
- W2989779801 hasConcept C2777212361 @default.
- W2989779801 hasConcept C2781238097 @default.
- W2989779801 hasConcept C41008148 @default.
- W2989779801 hasConcept C41608201 @default.
- W2989779801 hasConcept C774472 @default.
- W2989779801 hasConcept C94124525 @default.
- W2989779801 hasConcept C97931131 @default.
- W2989779801 hasConceptScore W2989779801C103278499 @default.
- W2989779801 hasConceptScore W2989779801C108583219 @default.
- W2989779801 hasConceptScore W2989779801C115961682 @default.
- W2989779801 hasConceptScore W2989779801C119857082 @default.
- W2989779801 hasConceptScore W2989779801C120665830 @default.
- W2989779801 hasConceptScore W2989779801C121332964 @default.
- W2989779801 hasConceptScore W2989779801C130318100 @default.
- W2989779801 hasConceptScore W2989779801C153180895 @default.
- W2989779801 hasConceptScore W2989779801C154945302 @default.
- W2989779801 hasConceptScore W2989779801C188441871 @default.
- W2989779801 hasConceptScore W2989779801C192209626 @default.
- W2989779801 hasConceptScore W2989779801C204321447 @default.
- W2989779801 hasConceptScore W2989779801C2777212361 @default.
- W2989779801 hasConceptScore W2989779801C2781238097 @default.