Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386867323> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4386867323 abstract "In this paper, we present a novel approach for tackling the challenging task of Visual Question Answering (VQA). Our method combines sparse cross-attention and masked self-attention techniques to improve the accuracy of answer prediction by effectively integrating visual and textual information. By leveraging cross-attention mechanisms, we establish strong relationships between visual and textual features, enhancing the model’s ability to comprehend the question and the visual content. Additionally, we introduce masked self-attention to further refine the answer prediction process. This module selectively focuses on relevant textual features while disregarding the answer, enabling the model to concentrate on the most informative aspects of the question. To evaluate the effectiveness of our proposed approach, we conduct experiments on the COCO VQA dataset. We compare our method against state-of-the-art approaches and demonstrate its competitive performance in terms of accuracy. Overall, our approach offers a promising solution for improving the efficiency, interpretability, and accuracy of VQA systems." @default.
- W4386867323 created "2023-09-20" @default.
- W4386867323 creator A5031288729 @default.
- W4386867323 creator A5032906498 @default.
- W4386867323 date "2023-08-17" @default.
- W4386867323 modified "2023-09-27" @default.
- W4386867323 title "An Visual Question Answering System using Cross-Attention Network" @default.
- W4386867323 cites W2546696630 @default.
- W4386867323 cites W2560920409 @default.
- W4386867323 cites W2732016772 @default.
- W4386867323 cites W2735608653 @default.
- W4386867323 cites W2896902935 @default.
- W4386867323 cites W2963191264 @default.
- W4386867323 cites W2963398599 @default.
- W4386867323 cites W2963466731 @default.
- W4386867323 cites W2963925437 @default.
- W4386867323 cites W2963954913 @default.
- W4386867323 doi "https://doi.org/10.1109/icoac59537.2023.10249985" @default.
- W4386867323 hasPublicationYear "2023" @default.
- W4386867323 type Work @default.
- W4386867323 citedByCount "0" @default.
- W4386867323 crossrefType "proceedings-article" @default.
- W4386867323 hasAuthorship W4386867323A5031288729 @default.
- W4386867323 hasAuthorship W4386867323A5032906498 @default.
- W4386867323 hasConcept C111919701 @default.
- W4386867323 hasConcept C119857082 @default.
- W4386867323 hasConcept C154945302 @default.
- W4386867323 hasConcept C162324750 @default.
- W4386867323 hasConcept C187736073 @default.
- W4386867323 hasConcept C23123220 @default.
- W4386867323 hasConcept C2780451532 @default.
- W4386867323 hasConcept C2781067378 @default.
- W4386867323 hasConcept C2993807640 @default.
- W4386867323 hasConcept C36464697 @default.
- W4386867323 hasConcept C41008148 @default.
- W4386867323 hasConcept C44291984 @default.
- W4386867323 hasConcept C98045186 @default.
- W4386867323 hasConceptScore W4386867323C111919701 @default.
- W4386867323 hasConceptScore W4386867323C119857082 @default.
- W4386867323 hasConceptScore W4386867323C154945302 @default.
- W4386867323 hasConceptScore W4386867323C162324750 @default.
- W4386867323 hasConceptScore W4386867323C187736073 @default.
- W4386867323 hasConceptScore W4386867323C23123220 @default.
- W4386867323 hasConceptScore W4386867323C2780451532 @default.
- W4386867323 hasConceptScore W4386867323C2781067378 @default.
- W4386867323 hasConceptScore W4386867323C2993807640 @default.
- W4386867323 hasConceptScore W4386867323C36464697 @default.
- W4386867323 hasConceptScore W4386867323C41008148 @default.
- W4386867323 hasConceptScore W4386867323C44291984 @default.
- W4386867323 hasConceptScore W4386867323C98045186 @default.
- W4386867323 hasLocation W43868673231 @default.
- W4386867323 hasOpenAccess W4386867323 @default.
- W4386867323 hasPrimaryLocation W43868673231 @default.
- W4386867323 hasRelatedWork W2051167396 @default.
- W4386867323 hasRelatedWork W219090214 @default.
- W4386867323 hasRelatedWork W3006943036 @default.
- W4386867323 hasRelatedWork W4200511449 @default.
- W4386867323 hasRelatedWork W4206534706 @default.
- W4386867323 hasRelatedWork W4229079080 @default.
- W4386867323 hasRelatedWork W4299487748 @default.
- W4386867323 hasRelatedWork W4385957992 @default.
- W4386867323 hasRelatedWork W4385965371 @default.
- W4386867323 hasRelatedWork W4386025632 @default.
- W4386867323 isParatext "false" @default.
- W4386867323 isRetracted "false" @default.
- W4386867323 workType "article" @default.