Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304092130> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4304092130 abstract "Medical Visual Question Answering as a specific-domain task requires substantive prior knowledge of medicine. However, deep learning techniques encounter severe problems of limited supervision due to the scarcity of well-annotated large-scale medical VQA datasets. As an alternative to facing the data limitation problem, image captioning can be introduced to learn summary information about the picture, which is beneficial to question answering. To this end, we propose a caption-aware VQA method that can read the summary information of image content and clinic diagnoses from plenty of medical images and answer the medical question with richer multimodality features. The proposed method consists of two novel components emphasizing semantic locations and semantic content respectively. Firstly, to extract and leverage the semantic locations implied in image captioning, similarity analysis is designed to summarize the attention maps generated from image captioning by their relevance and guide the visual model to focus on the semantic-rich regions. Besides, to combine the semantic content in the generated captions, we propose a Progressive Compact Bilinear Interactions structure to achieve cross-modality comprehension over the image, question and caption features by performing bilinear attention in a gradual manner. Qualitative and quantitative experiments on various medical datasets exhibit the superiority of the proposed approach compared to the state-of-the-art methods." @default.
- W4304092130 created "2022-10-10" @default.
- W4304092130 creator A5011919230 @default.
- W4304092130 creator A5036948844 @default.
- W4304092130 creator A5085073312 @default.
- W4304092130 creator A5088568072 @default.
- W4304092130 date "2022-10-10" @default.
- W4304092130 modified "2023-10-17" @default.
- W4304092130 title "Caption-Aware Medical VQA via Semantic Focusing and Progressive Cross-Modality Comprehension" @default.
- W4304092130 cites W2064675550 @default.
- W4304092130 cites W2108598243 @default.
- W4304092130 cites W2157331557 @default.
- W4304092130 cites W2194775991 @default.
- W4304092130 cites W2250539671 @default.
- W4304092130 cites W2895902247 @default.
- W4304092130 cites W2901466771 @default.
- W4304092130 cites W2913340405 @default.
- W4304092130 cites W2963150162 @default.
- W4304092130 cites W2963954913 @default.
- W4304092130 cites W2979525559 @default.
- W4304092130 cites W2981694290 @default.
- W4304092130 cites W2997591391 @default.
- W4304092130 cites W3015965768 @default.
- W4304092130 cites W3091588028 @default.
- W4304092130 cites W3094950914 @default.
- W4304092130 cites W3098325931 @default.
- W4304092130 cites W3100297028 @default.
- W4304092130 cites W3165058054 @default.
- W4304092130 cites W3203247393 @default.
- W4304092130 cites W3203255640 @default.
- W4304092130 doi "https://doi.org/10.1145/3503161.3548122" @default.
- W4304092130 hasPublicationYear "2022" @default.
- W4304092130 type Work @default.
- W4304092130 citedByCount "3" @default.
- W4304092130 countsByYear W43040921302023 @default.
- W4304092130 crossrefType "proceedings-article" @default.
- W4304092130 hasAuthorship W4304092130A5011919230 @default.
- W4304092130 hasAuthorship W4304092130A5036948844 @default.
- W4304092130 hasAuthorship W4304092130A5085073312 @default.
- W4304092130 hasAuthorship W4304092130A5088568072 @default.
- W4304092130 hasConcept C115961682 @default.
- W4304092130 hasConcept C130318100 @default.
- W4304092130 hasConcept C142724271 @default.
- W4304092130 hasConcept C153083717 @default.
- W4304092130 hasConcept C154945302 @default.
- W4304092130 hasConcept C157657479 @default.
- W4304092130 hasConcept C199360897 @default.
- W4304092130 hasConcept C204321447 @default.
- W4304092130 hasConcept C23123220 @default.
- W4304092130 hasConcept C2780226545 @default.
- W4304092130 hasConcept C36464697 @default.
- W4304092130 hasConcept C41008148 @default.
- W4304092130 hasConcept C44291984 @default.
- W4304092130 hasConcept C511192102 @default.
- W4304092130 hasConcept C534262118 @default.
- W4304092130 hasConcept C71924100 @default.
- W4304092130 hasConceptScore W4304092130C115961682 @default.
- W4304092130 hasConceptScore W4304092130C130318100 @default.
- W4304092130 hasConceptScore W4304092130C142724271 @default.
- W4304092130 hasConceptScore W4304092130C153083717 @default.
- W4304092130 hasConceptScore W4304092130C154945302 @default.
- W4304092130 hasConceptScore W4304092130C157657479 @default.
- W4304092130 hasConceptScore W4304092130C199360897 @default.
- W4304092130 hasConceptScore W4304092130C204321447 @default.
- W4304092130 hasConceptScore W4304092130C23123220 @default.
- W4304092130 hasConceptScore W4304092130C2780226545 @default.
- W4304092130 hasConceptScore W4304092130C36464697 @default.
- W4304092130 hasConceptScore W4304092130C41008148 @default.
- W4304092130 hasConceptScore W4304092130C44291984 @default.
- W4304092130 hasConceptScore W4304092130C511192102 @default.
- W4304092130 hasConceptScore W4304092130C534262118 @default.
- W4304092130 hasConceptScore W4304092130C71924100 @default.
- W4304092130 hasFunder F4320335777 @default.
- W4304092130 hasLocation W43040921301 @default.
- W4304092130 hasOpenAccess W4304092130 @default.
- W4304092130 hasPrimaryLocation W43040921301 @default.
- W4304092130 hasRelatedWork W207304934 @default.
- W4304092130 hasRelatedWork W2295744208 @default.
- W4304092130 hasRelatedWork W2745461083 @default.
- W4304092130 hasRelatedWork W2951590222 @default.
- W4304092130 hasRelatedWork W2952322859 @default.
- W4304092130 hasRelatedWork W2972206754 @default.
- W4304092130 hasRelatedWork W4288115461 @default.
- W4304092130 hasRelatedWork W4385572364 @default.
- W4304092130 hasRelatedWork W4385805088 @default.
- W4304092130 hasRelatedWork W4386380747 @default.
- W4304092130 isParatext "false" @default.
- W4304092130 isRetracted "false" @default.
- W4304092130 workType "article" @default.