Matches in SemOpenAlex for { <https://semopenalex.org/work/W4364305678> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4364305678 abstract "In the domains of Natural Language Processing (NLP) and Computer Vision (CV) Visual Question Answering (VQA) is a multidisciplinary task, in which an image and a question are given to a VQA system, which is responsible for giving the answer. The VQA system is used for a variety of real-world applications, such as providing situational information based on visual material, making judgments using a vast quantity of surveillance data, interacting with robots, and helping individuals who are blind or visually impaired. Although it is required yet challenging to complete comprehensive VQA, Fact-based VQA (FVQA) approaches in which external knowledge is required to process with image and question. Existing FVQA methods combine all types of data without fine-grained selection, thereby generating unexpected noise while reasoning about the final result. The problem solution should be able to collect complementary-information evidence based on question-attention. We represent an image with different layers of information by a multimodal knowledge graph relating to the features of visual, factual, and semantic. We propose a multimodal knowledge graph-convolutional-network (GCN) to collect relevant-information evidence from different information layers based on the given question. In particular, intra-modal knowledge graph attention takes evidence from each modality, while inter-modal knowledge graph attention gets evidence across the different information layers. To get an optimal answer, we stack this process multiple times to perform a reasoning mechanism. Over the FVQA dataset, we achieved state-of-the-art results by improving 10.86% test accuracy, which demonstrates the usefulness and interpretability of our approach." @default.
- W4364305678 created "2023-04-12" @default.
- W4364305678 creator A5017459474 @default.
- W4364305678 creator A5017535635 @default.
- W4364305678 creator A5049422969 @default.
- W4364305678 creator A5063716138 @default.
- W4364305678 date "2022-10-01" @default.
- W4364305678 modified "2023-09-26" @default.
- W4364305678 title "Multimodal Knowledge Reasoning for Enhanced Visual Question Answering" @default.
- W4364305678 cites W1933349210 @default.
- W4364305678 cites W2142192571 @default.
- W4364305678 cites W2506483933 @default.
- W4364305678 cites W2604314403 @default.
- W4364305678 cites W2745461083 @default.
- W4364305678 cites W2891394954 @default.
- W4364305678 cites W2899630722 @default.
- W4364305678 cites W2904910963 @default.
- W4364305678 cites W2911286998 @default.
- W4364305678 cites W2963477107 @default.
- W4364305678 cites W2964072591 @default.
- W4364305678 cites W2964303913 @default.
- W4364305678 cites W2990158537 @default.
- W4364305678 cites W2997547717 @default.
- W4364305678 cites W2998631105 @default.
- W4364305678 cites W3168481435 @default.
- W4364305678 cites W3170526917 @default.
- W4364305678 cites W3202727304 @default.
- W4364305678 cites W4214824212 @default.
- W4364305678 cites W4312561350 @default.
- W4364305678 doi "https://doi.org/10.1109/sitis57111.2022.00048" @default.
- W4364305678 hasPublicationYear "2022" @default.
- W4364305678 type Work @default.
- W4364305678 citedByCount "0" @default.
- W4364305678 crossrefType "proceedings-article" @default.
- W4364305678 hasAuthorship W4364305678A5017459474 @default.
- W4364305678 hasAuthorship W4364305678A5017535635 @default.
- W4364305678 hasAuthorship W4364305678A5049422969 @default.
- W4364305678 hasAuthorship W4364305678A5063716138 @default.
- W4364305678 hasConcept C119857082 @default.
- W4364305678 hasConcept C132525143 @default.
- W4364305678 hasConcept C154945302 @default.
- W4364305678 hasConcept C204321447 @default.
- W4364305678 hasConcept C23123220 @default.
- W4364305678 hasConcept C2781067378 @default.
- W4364305678 hasConcept C41008148 @default.
- W4364305678 hasConcept C44291984 @default.
- W4364305678 hasConcept C80444323 @default.
- W4364305678 hasConceptScore W4364305678C119857082 @default.
- W4364305678 hasConceptScore W4364305678C132525143 @default.
- W4364305678 hasConceptScore W4364305678C154945302 @default.
- W4364305678 hasConceptScore W4364305678C204321447 @default.
- W4364305678 hasConceptScore W4364305678C23123220 @default.
- W4364305678 hasConceptScore W4364305678C2781067378 @default.
- W4364305678 hasConceptScore W4364305678C41008148 @default.
- W4364305678 hasConceptScore W4364305678C44291984 @default.
- W4364305678 hasConceptScore W4364305678C80444323 @default.
- W4364305678 hasLocation W43643056781 @default.
- W4364305678 hasOpenAccess W4364305678 @default.
- W4364305678 hasPrimaryLocation W43643056781 @default.
- W4364305678 hasRelatedWork W128392744 @default.
- W4364305678 hasRelatedWork W3006943036 @default.
- W4364305678 hasRelatedWork W3012234327 @default.
- W4364305678 hasRelatedWork W3107474891 @default.
- W4364305678 hasRelatedWork W3191046242 @default.
- W4364305678 hasRelatedWork W3203961807 @default.
- W4364305678 hasRelatedWork W4205364923 @default.
- W4364305678 hasRelatedWork W4206534706 @default.
- W4364305678 hasRelatedWork W4229079080 @default.
- W4364305678 hasRelatedWork W4294031299 @default.
- W4364305678 isParatext "false" @default.
- W4364305678 isRetracted "false" @default.
- W4364305678 workType "article" @default.