Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313019116> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4313019116 abstract "Visual Question Answering (VQA) is a computer vision task in which a system produces an accurate answer to a given image and a question that is relevant to the image. Medical VQA can be considered as a subfield of general VQA, which focuses on images and questions in the medical domain. The VQA model’s most crucial task is to learn the question-image joint representation to reflect the information related to the correct answer. Medical VQA remains a difficult task due to the ineffectiveness of question-image embeddings, despite recent research on general VQA models finding significant progress. To address this problem, we propose a new method for training VQA models that utilizes adversarial learning to improve the question-image embedding and illustrate how this embedding can be used as the ideal embedding for answer inference. For adversarial learning, we use two embedding generators (question–image embedding and a question-answer embedding generator) and a discriminator to differentiate the two embeddings. The questionanswer embedding is used as the ideal embedding and the question-image embedding is improved in reference to that. The experiment results indicate that pre-training the question-image embedding generation module using adversarial learning improves overall performance, implying the effectiveness of the proposed method." @default.
- W4313019116 created "2023-01-05" @default.
- W4313019116 creator A5017016872 @default.
- W4313019116 creator A5042418154 @default.
- W4313019116 creator A5042961247 @default.
- W4313019116 creator A5081567702 @default.
- W4313019116 date "2022-07-27" @default.
- W4313019116 modified "2023-09-29" @default.
- W4313019116 title "Adversarial Learning to Improve Question Image Embedding in Medical Visual Question Answering" @default.
- W4313019116 cites W2250539671 @default.
- W4313019116 cites W2901466771 @default.
- W4313019116 cites W2970231061 @default.
- W4313019116 cites W3198570286 @default.
- W4313019116 doi "https://doi.org/10.1109/mercon55799.2022.9906168" @default.
- W4313019116 hasPublicationYear "2022" @default.
- W4313019116 type Work @default.
- W4313019116 citedByCount "0" @default.
- W4313019116 crossrefType "proceedings-article" @default.
- W4313019116 hasAuthorship W4313019116A5017016872 @default.
- W4313019116 hasAuthorship W4313019116A5042418154 @default.
- W4313019116 hasAuthorship W4313019116A5042961247 @default.
- W4313019116 hasAuthorship W4313019116A5081567702 @default.
- W4313019116 hasConcept C111472728 @default.
- W4313019116 hasConcept C115961682 @default.
- W4313019116 hasConcept C119857082 @default.
- W4313019116 hasConcept C121332964 @default.
- W4313019116 hasConcept C138885662 @default.
- W4313019116 hasConcept C154945302 @default.
- W4313019116 hasConcept C162324750 @default.
- W4313019116 hasConcept C163258240 @default.
- W4313019116 hasConcept C187736073 @default.
- W4313019116 hasConcept C2776214188 @default.
- W4313019116 hasConcept C2776639384 @default.
- W4313019116 hasConcept C2780451532 @default.
- W4313019116 hasConcept C2780992000 @default.
- W4313019116 hasConcept C41008148 @default.
- W4313019116 hasConcept C41608201 @default.
- W4313019116 hasConcept C44291984 @default.
- W4313019116 hasConcept C62520636 @default.
- W4313019116 hasConceptScore W4313019116C111472728 @default.
- W4313019116 hasConceptScore W4313019116C115961682 @default.
- W4313019116 hasConceptScore W4313019116C119857082 @default.
- W4313019116 hasConceptScore W4313019116C121332964 @default.
- W4313019116 hasConceptScore W4313019116C138885662 @default.
- W4313019116 hasConceptScore W4313019116C154945302 @default.
- W4313019116 hasConceptScore W4313019116C162324750 @default.
- W4313019116 hasConceptScore W4313019116C163258240 @default.
- W4313019116 hasConceptScore W4313019116C187736073 @default.
- W4313019116 hasConceptScore W4313019116C2776214188 @default.
- W4313019116 hasConceptScore W4313019116C2776639384 @default.
- W4313019116 hasConceptScore W4313019116C2780451532 @default.
- W4313019116 hasConceptScore W4313019116C2780992000 @default.
- W4313019116 hasConceptScore W4313019116C41008148 @default.
- W4313019116 hasConceptScore W4313019116C41608201 @default.
- W4313019116 hasConceptScore W4313019116C44291984 @default.
- W4313019116 hasConceptScore W4313019116C62520636 @default.
- W4313019116 hasLocation W43130191161 @default.
- W4313019116 hasOpenAccess W4313019116 @default.
- W4313019116 hasPrimaryLocation W43130191161 @default.
- W4313019116 hasRelatedWork W2511279186 @default.
- W4313019116 hasRelatedWork W2617297150 @default.
- W4313019116 hasRelatedWork W2782118220 @default.
- W4313019116 hasRelatedWork W2794527914 @default.
- W4313019116 hasRelatedWork W2809632469 @default.
- W4313019116 hasRelatedWork W2950771721 @default.
- W4313019116 hasRelatedWork W2963058055 @default.
- W4313019116 hasRelatedWork W2970986790 @default.
- W4313019116 hasRelatedWork W4300649747 @default.
- W4313019116 hasRelatedWork W4310926268 @default.
- W4313019116 isParatext "false" @default.
- W4313019116 isRetracted "false" @default.
- W4313019116 workType "article" @default.