Matches in SemOpenAlex for { <https://semopenalex.org/work/W2604415738> ?p ?o ?g. }
- W2604415738 endingPage "4127" @default.
- W2604415738 startingPage "4116" @default.
- W2604415738 abstract "Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize new categories that have never seen before. Two fundamental challenges in it are visual-semantic embedding and domain adaptation in cross-modality learning and unseen class prediction steps, respectively. This paper presents two corresponding methods named Adaptive STructural Embedding (ASTE) and Self-PAced Selective Strategy (SPASS) for both challenges. Specifically, ASTE formulates the visual-semantic interactions in a latent structural support vector machine framework by adaptively adjusting the slack variables to embody different reliablenesses among training instances. To alleviate the domain shift problem in ZSL, SPASS borrows the idea from self-paced learning by iteratively selecting the unseen instances from reliable to less reliable to gradually adapt the knowledge from the seen domain to the unseen domain. Consequently, by combining SPASS and ASTE, we present a self-paced Transductive ASTE (TASTE) method to progressively reinforce the classification capacity. Extensive experiments on three benchmark data sets (i.e., AwA, CUB, and aPY) demonstrate the superiorities of ASTE and TASTE. Furthermore, we also propose a fast training (FT) strategy to improve the efficiency of most existing ZSL methods. The FT strategy is surprisingly simple and general enough, which speeds up the training time of most existing ZSL methods by 4~300 times while holding the previous performance." @default.
- W2604415738 created "2017-04-14" @default.
- W2604415738 creator A5005367680 @default.
- W2604415738 creator A5060291357 @default.
- W2604415738 creator A5079650655 @default.
- W2604415738 creator A5086887025 @default.
- W2604415738 date "2018-09-01" @default.
- W2604415738 modified "2023-10-15" @default.
- W2604415738 title "Transductive Zero-Shot Learning With Adaptive Structural Embedding" @default.
- W2604415738 cites W1596905899 @default.
- W2604415738 cites W1805946669 @default.
- W2604415738 cites W1960364170 @default.
- W2604415738 cites W1981658663 @default.
- W2604415738 cites W2041280778 @default.
- W2604415738 cites W2098411764 @default.
- W2604415738 cites W2104068492 @default.
- W2604415738 cites W2109317801 @default.
- W2604415738 cites W2121238376 @default.
- W2604415738 cites W2141350700 @default.
- W2604415738 cites W2157032868 @default.
- W2604415738 cites W2163345210 @default.
- W2604415738 cites W2209594346 @default.
- W2604415738 cites W2250539671 @default.
- W2604415738 cites W2289084343 @default.
- W2604415738 cites W2296073425 @default.
- W2604415738 cites W2307425316 @default.
- W2604415738 cites W2334493732 @default.
- W2604415738 cites W2346746376 @default.
- W2604415738 cites W2405223529 @default.
- W2604415738 cites W2463762378 @default.
- W2604415738 cites W2520613337 @default.
- W2604415738 cites W2535579023 @default.
- W2604415738 cites W2559832977 @default.
- W2604415738 cites W2962714319 @default.
- W2604415738 cites W2963325024 @default.
- W2604415738 cites W2963955958 @default.
- W2604415738 cites W2964086552 @default.
- W2604415738 cites W3100093508 @default.
- W2604415738 cites W3106051827 @default.
- W2604415738 cites W3143107425 @default.
- W2604415738 doi "https://doi.org/10.1109/tnnls.2017.2753852" @default.
- W2604415738 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29035229" @default.
- W2604415738 hasPublicationYear "2018" @default.
- W2604415738 type Work @default.
- W2604415738 sameAs 2604415738 @default.
- W2604415738 citedByCount "32" @default.
- W2604415738 countsByYear W26044157382017 @default.
- W2604415738 countsByYear W26044157382018 @default.
- W2604415738 countsByYear W26044157382019 @default.
- W2604415738 countsByYear W26044157382020 @default.
- W2604415738 countsByYear W26044157382021 @default.
- W2604415738 countsByYear W26044157382022 @default.
- W2604415738 countsByYear W26044157382023 @default.
- W2604415738 crossrefType "journal-article" @default.
- W2604415738 hasAuthorship W2604415738A5005367680 @default.
- W2604415738 hasAuthorship W2604415738A5060291357 @default.
- W2604415738 hasAuthorship W2604415738A5079650655 @default.
- W2604415738 hasAuthorship W2604415738A5086887025 @default.
- W2604415738 hasBestOaLocation W26044157382 @default.
- W2604415738 hasConcept C119857082 @default.
- W2604415738 hasConcept C120665830 @default.
- W2604415738 hasConcept C121332964 @default.
- W2604415738 hasConcept C13280743 @default.
- W2604415738 hasConcept C134306372 @default.
- W2604415738 hasConcept C139807058 @default.
- W2604415738 hasConcept C154945302 @default.
- W2604415738 hasConcept C185798385 @default.
- W2604415738 hasConcept C205649164 @default.
- W2604415738 hasConcept C2776434776 @default.
- W2604415738 hasConcept C2777212361 @default.
- W2604415738 hasConcept C33923547 @default.
- W2604415738 hasConcept C36503486 @default.
- W2604415738 hasConcept C41008148 @default.
- W2604415738 hasConcept C41608201 @default.
- W2604415738 hasConcept C95623464 @default.
- W2604415738 hasConceptScore W2604415738C119857082 @default.
- W2604415738 hasConceptScore W2604415738C120665830 @default.
- W2604415738 hasConceptScore W2604415738C121332964 @default.
- W2604415738 hasConceptScore W2604415738C13280743 @default.
- W2604415738 hasConceptScore W2604415738C134306372 @default.
- W2604415738 hasConceptScore W2604415738C139807058 @default.
- W2604415738 hasConceptScore W2604415738C154945302 @default.
- W2604415738 hasConceptScore W2604415738C185798385 @default.
- W2604415738 hasConceptScore W2604415738C205649164 @default.
- W2604415738 hasConceptScore W2604415738C2776434776 @default.
- W2604415738 hasConceptScore W2604415738C2777212361 @default.
- W2604415738 hasConceptScore W2604415738C33923547 @default.
- W2604415738 hasConceptScore W2604415738C36503486 @default.
- W2604415738 hasConceptScore W2604415738C41008148 @default.
- W2604415738 hasConceptScore W2604415738C41608201 @default.
- W2604415738 hasConceptScore W2604415738C95623464 @default.
- W2604415738 hasFunder F4320321001 @default.
- W2604415738 hasIssue "9" @default.
- W2604415738 hasLocation W26044157381 @default.
- W2604415738 hasLocation W26044157382 @default.
- W2604415738 hasLocation W26044157383 @default.
- W2604415738 hasOpenAccess W2604415738 @default.
- W2604415738 hasPrimaryLocation W26044157381 @default.