Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220842168> ?p ?o ?g. }
- W4220842168 endingPage "444" @default.
- W4220842168 startingPage "431" @default.
- W4220842168 abstract "The transformer architecture has been the dominant framework for today's image captioning tasks because of its superior performance. However, existing methods based on transformer often lack the integrated use of multi-level semantic information and are weak in maintaining the relevance of captions to the image. In this paper, a semantic-meshed and content-guided transformer network is introduced for image captioning to solve these problems. The semantic-meshed mechanism allows the model to generate words by selecting semantic information of multiple interaction levels adaptively through attention-based reconstruction. And the content-guided module guides the words generation by using attribute features that represent the image content, which aims to keep the generated caption consistent with the main content of the image. Experiments on dataset on the MSCOCO captioning dataset are conducted to validate the authors’ model and achieve superior results compared to other state-of-the-art method approaches." @default.
- W4220842168 created "2022-04-03" @default.
- W4220842168 creator A5005905514 @default.
- W4220842168 creator A5027937292 @default.
- W4220842168 creator A5059827848 @default.
- W4220842168 creator A5074960174 @default.
- W4220842168 date "2022-03-29" @default.
- W4220842168 modified "2023-09-26" @default.
- W4220842168 title "Semantic‐meshed and content‐guided transformer for image captioning" @default.
- W4220842168 cites W1861492603 @default.
- W4220842168 cites W1905882502 @default.
- W4220842168 cites W1931639407 @default.
- W4220842168 cites W1947481528 @default.
- W4220842168 cites W1956340063 @default.
- W4220842168 cites W1987835821 @default.
- W4220842168 cites W2019370496 @default.
- W4220842168 cites W2062955551 @default.
- W4220842168 cites W2064675550 @default.
- W4220842168 cites W2122710056 @default.
- W4220842168 cites W2133459682 @default.
- W4220842168 cites W2157331557 @default.
- W4220842168 cites W2194775991 @default.
- W4220842168 cites W2277195237 @default.
- W4220842168 cites W2506483933 @default.
- W4220842168 cites W2550553598 @default.
- W4220842168 cites W2552161745 @default.
- W4220842168 cites W2575842049 @default.
- W4220842168 cites W2745461083 @default.
- W4220842168 cites W2885013662 @default.
- W4220842168 cites W2887585070 @default.
- W4220842168 cites W2890531016 @default.
- W4220842168 cites W2904551248 @default.
- W4220842168 cites W2963084599 @default.
- W4220842168 cites W2963101956 @default.
- W4220842168 cites W2983141445 @default.
- W4220842168 cites W2986670728 @default.
- W4220842168 cites W2990069284 @default.
- W4220842168 cites W2990818246 @default.
- W4220842168 cites W2998988444 @default.
- W4220842168 cites W3034472074 @default.
- W4220842168 cites W3034655362 @default.
- W4220842168 cites W3035160838 @default.
- W4220842168 cites W3035284526 @default.
- W4220842168 cites W3093088671 @default.
- W4220842168 cites W3103651098 @default.
- W4220842168 cites W3183824823 @default.
- W4220842168 cites W68733909 @default.
- W4220842168 doi "https://doi.org/10.1049/cvi2.12099" @default.
- W4220842168 hasPublicationYear "2022" @default.
- W4220842168 type Work @default.
- W4220842168 citedByCount "2" @default.
- W4220842168 countsByYear W42208421682022 @default.
- W4220842168 countsByYear W42208421682023 @default.
- W4220842168 crossrefType "journal-article" @default.
- W4220842168 hasAuthorship W4220842168A5005905514 @default.
- W4220842168 hasAuthorship W4220842168A5027937292 @default.
- W4220842168 hasAuthorship W4220842168A5059827848 @default.
- W4220842168 hasAuthorship W4220842168A5074960174 @default.
- W4220842168 hasBestOaLocation W42208421681 @default.
- W4220842168 hasConcept C115961682 @default.
- W4220842168 hasConcept C121332964 @default.
- W4220842168 hasConcept C154945302 @default.
- W4220842168 hasConcept C157657479 @default.
- W4220842168 hasConcept C165801399 @default.
- W4220842168 hasConcept C204321447 @default.
- W4220842168 hasConcept C23123220 @default.
- W4220842168 hasConcept C31972630 @default.
- W4220842168 hasConcept C41008148 @default.
- W4220842168 hasConcept C62520636 @default.
- W4220842168 hasConcept C66322947 @default.
- W4220842168 hasConceptScore W4220842168C115961682 @default.
- W4220842168 hasConceptScore W4220842168C121332964 @default.
- W4220842168 hasConceptScore W4220842168C154945302 @default.
- W4220842168 hasConceptScore W4220842168C157657479 @default.
- W4220842168 hasConceptScore W4220842168C165801399 @default.
- W4220842168 hasConceptScore W4220842168C204321447 @default.
- W4220842168 hasConceptScore W4220842168C23123220 @default.
- W4220842168 hasConceptScore W4220842168C31972630 @default.
- W4220842168 hasConceptScore W4220842168C41008148 @default.
- W4220842168 hasConceptScore W4220842168C62520636 @default.
- W4220842168 hasConceptScore W4220842168C66322947 @default.
- W4220842168 hasIssue "5" @default.
- W4220842168 hasLocation W42208421681 @default.
- W4220842168 hasLocation W42208421682 @default.
- W4220842168 hasOpenAccess W4220842168 @default.
- W4220842168 hasPrimaryLocation W42208421681 @default.
- W4220842168 hasRelatedWork W2130228941 @default.
- W4220842168 hasRelatedWork W2161229648 @default.
- W4220842168 hasRelatedWork W2547835662 @default.
- W4220842168 hasRelatedWork W2905654560 @default.
- W4220842168 hasRelatedWork W2923366293 @default.
- W4220842168 hasRelatedWork W2993674027 @default.
- W4220842168 hasRelatedWork W3008515501 @default.
- W4220842168 hasRelatedWork W3183824823 @default.
- W4220842168 hasRelatedWork W4307856881 @default.
- W4220842168 hasRelatedWork W4320016117 @default.
- W4220842168 hasVolume "16" @default.
- W4220842168 isParatext "false" @default.