Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310068879> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4310068879 endingPage "104591" @default.
- W4310068879 startingPage "104591" @default.
- W4310068879 abstract "The performance of image captioning has been significantly improved recently through deep neural network architectures combining with attention mechanisms and reinforcement learning optimization. Exploring visual relationships and interactions between different objects appearing in the image, however, is far from being investigated. In this paper, we present a novel approach that combines scene graphs with Transformer, which we call SGT, to explicitly encode available visual relationships between detected objects. Specifically, we pretrain an scene graph generation model to predict graph representations for images. After that, for each graph node, a Graph Convolutional Network (GCN) is employed to acquire relationship knowledge by aggregating the information of its local neighbors. As we train the captioning model, we feed the potential relation-aware information into the Transformer to generate descriptive sentence. Experiments on the MSCOCO dataset and the Flickr30k dataset validate the superiority of our SGT model, which can realize state-of-the-art results in terms of all the standard evaluation metrics." @default.
- W4310068879 created "2022-11-30" @default.
- W4310068879 creator A5028931239 @default.
- W4310068879 creator A5049801163 @default.
- W4310068879 creator A5053794277 @default.
- W4310068879 creator A5076598143 @default.
- W4310068879 date "2023-01-01" @default.
- W4310068879 modified "2023-10-14" @default.
- W4310068879 title "Modeling graph-structured contexts for image captioning" @default.
- W4310068879 cites W2088049833 @default.
- W4310068879 cites W2564898401 @default.
- W4310068879 cites W2896348597 @default.
- W4310068879 cites W2981165461 @default.
- W4310068879 cites W3096407995 @default.
- W4310068879 cites W3154362247 @default.
- W4310068879 cites W3162954998 @default.
- W4310068879 cites W4214917601 @default.
- W4310068879 doi "https://doi.org/10.1016/j.imavis.2022.104591" @default.
- W4310068879 hasPublicationYear "2023" @default.
- W4310068879 type Work @default.
- W4310068879 citedByCount "1" @default.
- W4310068879 countsByYear W43100688792023 @default.
- W4310068879 crossrefType "journal-article" @default.
- W4310068879 hasAuthorship W4310068879A5028931239 @default.
- W4310068879 hasAuthorship W4310068879A5049801163 @default.
- W4310068879 hasAuthorship W4310068879A5053794277 @default.
- W4310068879 hasAuthorship W4310068879A5076598143 @default.
- W4310068879 hasConcept C104317684 @default.
- W4310068879 hasConcept C115961682 @default.
- W4310068879 hasConcept C121332964 @default.
- W4310068879 hasConcept C132525143 @default.
- W4310068879 hasConcept C153180895 @default.
- W4310068879 hasConcept C154945302 @default.
- W4310068879 hasConcept C157657479 @default.
- W4310068879 hasConcept C165801399 @default.
- W4310068879 hasConcept C179372163 @default.
- W4310068879 hasConcept C185592680 @default.
- W4310068879 hasConcept C204321447 @default.
- W4310068879 hasConcept C205711294 @default.
- W4310068879 hasConcept C2777530160 @default.
- W4310068879 hasConcept C2993807640 @default.
- W4310068879 hasConcept C36464697 @default.
- W4310068879 hasConcept C41008148 @default.
- W4310068879 hasConcept C55493867 @default.
- W4310068879 hasConcept C62520636 @default.
- W4310068879 hasConcept C66322947 @default.
- W4310068879 hasConcept C66746571 @default.
- W4310068879 hasConcept C80444323 @default.
- W4310068879 hasConcept C81363708 @default.
- W4310068879 hasConceptScore W4310068879C104317684 @default.
- W4310068879 hasConceptScore W4310068879C115961682 @default.
- W4310068879 hasConceptScore W4310068879C121332964 @default.
- W4310068879 hasConceptScore W4310068879C132525143 @default.
- W4310068879 hasConceptScore W4310068879C153180895 @default.
- W4310068879 hasConceptScore W4310068879C154945302 @default.
- W4310068879 hasConceptScore W4310068879C157657479 @default.
- W4310068879 hasConceptScore W4310068879C165801399 @default.
- W4310068879 hasConceptScore W4310068879C179372163 @default.
- W4310068879 hasConceptScore W4310068879C185592680 @default.
- W4310068879 hasConceptScore W4310068879C204321447 @default.
- W4310068879 hasConceptScore W4310068879C205711294 @default.
- W4310068879 hasConceptScore W4310068879C2777530160 @default.
- W4310068879 hasConceptScore W4310068879C2993807640 @default.
- W4310068879 hasConceptScore W4310068879C36464697 @default.
- W4310068879 hasConceptScore W4310068879C41008148 @default.
- W4310068879 hasConceptScore W4310068879C55493867 @default.
- W4310068879 hasConceptScore W4310068879C62520636 @default.
- W4310068879 hasConceptScore W4310068879C66322947 @default.
- W4310068879 hasConceptScore W4310068879C66746571 @default.
- W4310068879 hasConceptScore W4310068879C80444323 @default.
- W4310068879 hasConceptScore W4310068879C81363708 @default.
- W4310068879 hasFunder F4320321001 @default.
- W4310068879 hasFunder F4320322768 @default.
- W4310068879 hasLocation W43100688791 @default.
- W4310068879 hasOpenAccess W4310068879 @default.
- W4310068879 hasPrimaryLocation W43100688791 @default.
- W4310068879 hasRelatedWork W159132833 @default.
- W4310068879 hasRelatedWork W2767651786 @default.
- W4310068879 hasRelatedWork W2888321701 @default.
- W4310068879 hasRelatedWork W2903179935 @default.
- W4310068879 hasRelatedWork W2912288872 @default.
- W4310068879 hasRelatedWork W3025136821 @default.
- W4310068879 hasRelatedWork W3035237998 @default.
- W4310068879 hasRelatedWork W4224931701 @default.
- W4310068879 hasRelatedWork W4283375995 @default.
- W4310068879 hasRelatedWork W4310068879 @default.
- W4310068879 hasVolume "129" @default.
- W4310068879 isParatext "false" @default.
- W4310068879 isRetracted "false" @default.
- W4310068879 workType "article" @default.