Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206922148> ?p ?o ?g. }
- W4206922148 abstract "Image captioning is an interesting and challenging task. The previously established image captioning approach is based mainly on the encoder-decoder architecture, but it suffers from problems such as inaccurate captioning information, and the generated captioning sentences are not sufficiently rich. This paper proposes a novel image captioning model that is based on a self-attention network and a scene graph relationship network. First, an improved self-attention network is added to the extraction of visual features to evaluate the effectiveness of image global information for image generation. Then, we design a visual intensity parameter to coordinate the strategies of visual features and language model for word generation. Finally, a graph convolutional network is designed to extract the relationships from the scene information to render the generated caption more exciting and to increase the accuracy of the fine-grained captioning. We demonstrated the satisfactory performance of the model on the MS-COCO and Flickr 30K datasets. The experimental results demonstrate that the proposed model realizes state-of-the-art performance." @default.
- W4206922148 created "2022-01-26" @default.
- W4206922148 creator A5016469515 @default.
- W4206922148 creator A5017371862 @default.
- W4206922148 creator A5039318759 @default.
- W4206922148 creator A5069672411 @default.
- W4206922148 date "2021-12-01" @default.
- W4206922148 modified "2023-10-18" @default.
- W4206922148 title "Joint Scence Network and Attention-Guided for Image Captioning" @default.
- W4206922148 cites W1905882502 @default.
- W4206922148 cites W2550553598 @default.
- W4206922148 cites W2745461083 @default.
- W4206922148 cites W2795151422 @default.
- W4206922148 cites W2885013662 @default.
- W4206922148 cites W2887585070 @default.
- W4206922148 cites W2888039742 @default.
- W4206922148 cites W2944965479 @default.
- W4206922148 cites W2963084599 @default.
- W4206922148 cites W2963101956 @default.
- W4206922148 cites W2979739834 @default.
- W4206922148 cites W2982553922 @default.
- W4206922148 cites W2985051484 @default.
- W4206922148 cites W2996421194 @default.
- W4206922148 cites W2997026866 @default.
- W4206922148 cites W2997226123 @default.
- W4206922148 cites W2997591391 @default.
- W4206922148 cites W3003478339 @default.
- W4206922148 cites W3024534448 @default.
- W4206922148 cites W3028688913 @default.
- W4206922148 cites W3034984754 @default.
- W4206922148 cites W3035323998 @default.
- W4206922148 cites W3038571929 @default.
- W4206922148 cites W3047875366 @default.
- W4206922148 cites W3080813890 @default.
- W4206922148 cites W3093309253 @default.
- W4206922148 cites W3125154076 @default.
- W4206922148 cites W3126207269 @default.
- W4206922148 cites W3127216151 @default.
- W4206922148 cites W3128826581 @default.
- W4206922148 cites W3129050402 @default.
- W4206922148 cites W3130531605 @default.
- W4206922148 cites W3134428106 @default.
- W4206922148 cites W3134991666 @default.
- W4206922148 doi "https://doi.org/10.1109/icdm51629.2021.00201" @default.
- W4206922148 hasPublicationYear "2021" @default.
- W4206922148 type Work @default.
- W4206922148 citedByCount "1" @default.
- W4206922148 countsByYear W42069221482022 @default.
- W4206922148 crossrefType "proceedings-article" @default.
- W4206922148 hasAuthorship W4206922148A5016469515 @default.
- W4206922148 hasAuthorship W4206922148A5017371862 @default.
- W4206922148 hasAuthorship W4206922148A5039318759 @default.
- W4206922148 hasAuthorship W4206922148A5069672411 @default.
- W4206922148 hasConcept C111919701 @default.
- W4206922148 hasConcept C115961682 @default.
- W4206922148 hasConcept C118505674 @default.
- W4206922148 hasConcept C127413603 @default.
- W4206922148 hasConcept C132525143 @default.
- W4206922148 hasConcept C138885662 @default.
- W4206922148 hasConcept C153180895 @default.
- W4206922148 hasConcept C154945302 @default.
- W4206922148 hasConcept C157657479 @default.
- W4206922148 hasConcept C162324750 @default.
- W4206922148 hasConcept C170154142 @default.
- W4206922148 hasConcept C175154964 @default.
- W4206922148 hasConcept C18555067 @default.
- W4206922148 hasConcept C187736073 @default.
- W4206922148 hasConcept C204321447 @default.
- W4206922148 hasConcept C2780451532 @default.
- W4206922148 hasConcept C31972630 @default.
- W4206922148 hasConcept C41008148 @default.
- W4206922148 hasConcept C41895202 @default.
- W4206922148 hasConcept C52622490 @default.
- W4206922148 hasConcept C80444323 @default.
- W4206922148 hasConcept C90805587 @default.
- W4206922148 hasConceptScore W4206922148C111919701 @default.
- W4206922148 hasConceptScore W4206922148C115961682 @default.
- W4206922148 hasConceptScore W4206922148C118505674 @default.
- W4206922148 hasConceptScore W4206922148C127413603 @default.
- W4206922148 hasConceptScore W4206922148C132525143 @default.
- W4206922148 hasConceptScore W4206922148C138885662 @default.
- W4206922148 hasConceptScore W4206922148C153180895 @default.
- W4206922148 hasConceptScore W4206922148C154945302 @default.
- W4206922148 hasConceptScore W4206922148C157657479 @default.
- W4206922148 hasConceptScore W4206922148C162324750 @default.
- W4206922148 hasConceptScore W4206922148C170154142 @default.
- W4206922148 hasConceptScore W4206922148C175154964 @default.
- W4206922148 hasConceptScore W4206922148C18555067 @default.
- W4206922148 hasConceptScore W4206922148C187736073 @default.
- W4206922148 hasConceptScore W4206922148C204321447 @default.
- W4206922148 hasConceptScore W4206922148C2780451532 @default.
- W4206922148 hasConceptScore W4206922148C31972630 @default.
- W4206922148 hasConceptScore W4206922148C41008148 @default.
- W4206922148 hasConceptScore W4206922148C41895202 @default.
- W4206922148 hasConceptScore W4206922148C52622490 @default.
- W4206922148 hasConceptScore W4206922148C80444323 @default.
- W4206922148 hasConceptScore W4206922148C90805587 @default.
- W4206922148 hasFunder F4320321001 @default.
- W4206922148 hasLocation W42069221481 @default.
- W4206922148 hasOpenAccess W4206922148 @default.