Adjusted Reasoning Module for Deep Visual Question Answering Using Vision Transformer
Source abstract
Abstract
Visual Question Answering (VQA) is an interdisciplinary artificial intelligence (AI) activity that integrates computer vision and natural language processing. Its purpose is to empower machines to respond to questions by util... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Robotics and Automated Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (63)
Show source-provided references
1. Improving visual question answering for bridge inspection by pre-training with external data of image-text pairs10.1111/mice.13086 ↗
2. Vision-language pre-training: Basics, recent advances, and future trends10.1561/0600000105 ↗
3. Visual question answering: A survey of methods and datasets10.1016/j.cviu.2017.05.001 ↗
4. Novel approach to integrate various feature extraction techniques for the visual question answering system with skeletal images in the healthcare sector10.17762/ijritcc.v11i9.9781 ↗
5. Application of a neural network-based visual question answering system in preschool language education10.5573/IEIESPC.2023.12.5.419 ↗
6. Worldly Wise (WoW)-cross-lingual knowledge fusion for fact-based visual spoken-question answering
7. PAM: Understanding product images in cross product category attribute extraction
8. Multiscale feature extraction and fusion of image and text in VQA10.1007/s44196-023-00233-6 ↗
9. Explaining autonomous driving actions with visual question answering
10. TG-VQA: Ternary game of video question answering
11. Learning neighbor-enhanced region representations and question-guided visual representations for visual question answering10.1016/j.eswa.2023.122239 ↗
12. Z. Zhang, A. Zhang, M. Li, H. Zhao, G. Karypis and A. Smola, “Multimodal chain-of-thought reasoning in language models,” Feb. 2023. doi: 10.48550/arXiv.2302.00923.
13. Weakly supervised grounding for VQA in vision-language transformers10.1007/978-3-031-19833-5_38 ↗
14. Multi visual and textual embedding on visual question answering for blind people10.1016/j.neucom.2021.08.117 ↗
15. An effective Med-VQA method using a transformer with weights fusion of multiple fine-tuned models10.3390/app13179735 ↗
16. ST-VQA: Shrinkage transformer with accurate alignment for visual question answering10.1007/s10489-023-04564-x ↗
17. TRANS-VQA: Fully transformer-based image question-answering model using question-guided vision attention10.4114/intartif.vol27iss73pp111-128 ↗
18. COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter10.3389/frai.2023.1023281 ↗
19. A BERT framework to sentiment analysis of tweets10.3390/s23010506 ↗
20. The performance of BERT as data representation of text clustering10.1186/s40537-022-00564-9 ↗
21. RoBERTa-GRU: A hybrid deep learning model for enhanced sentiment analysis10.3390/app13063915 ↗
22. Y. Liu et al., “RoBERTa: A robustly optimized BERT pretraining approach,” Jul. 2019. doi: 10.48550/arXiv.1907.11692.
23. Enhancing fashion classification with Vision Transformer (ViT) and developing recommendation fashion systems using DINOVA210.3390/electronics12204263 ↗
24. Exploiting data-efficient image transformer-based transfer learning for valvular heart diseases detection10.1109/ACCESS.2024.3357946 ↗
25. H. Bao, L. Dong, S. Piao, and F. Wei, “BEIT: BERT pre-training of image transformers,” 2022. doi: 10.48550/arXiv.2106.08254.
26. Stacked attention networks for image question answering
27. Clevrer: Collision events for video representation and reasoning
28. Neural-symbolic VQA: Disentangling reasoning from vision and language understanding
29. BPI-MVQA: A bi-branch model for medical visual question answering10.1186/s12880-022-00800-x ↗
30. Grad-CAM: Visual explanations from deep networks via gradient-based localization10.1007/s11263-019-01228-7 ↗
31. Joint embedding VQA model based on dynamic word vector10.7717/peerj-cs.353 ↗
32. Spatial-temporal interval aware individual future trajectory prediction10.1109/TKDE.2023.3332929 ↗
33. Exploring models and data for image question answering
34. Explain by evidence: An explainable memory-based neural network for question answering
35. Component analysis for visual question answering architectures
36. The multi-modal fusion in visual question answering: A review of attention mechanisms10.7717/peerj-cs.1400 ↗
37. Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions10.1016/j.inffus.2022.09.025 ↗
38. L. B. Jimmy, R. K. Jamie, and G. E. Hinton, “Layer normalization,” 2016. doi: 10.48550/arXiv.1607.06450.
39. Understanding and improving layer normalization
40. A focus fusion attention mechanism integrated with image captions for knowledge graph-based visual question answering10.1007/s11760-024-03013-7 ↗
41. C. Kervadec, G. Antipov, M. Baccouche, and C. Wolf, “Estimating semantic structure for the VQA answer space,” 2020, arXiv2006.05726.
42. Ö. Özdemir and E. Akagündüz, “Enhancing visual question answering through question-driven image captions as prompts,” Apr. 2024. doi: 10.1109/CVPRW63382.2024.00163.10.1109/CVPRW63382.2024.00163 ↗
43. A modification of Wu and Palmer semantic similarity measure
44. M. A. Pratama and R. Mandala, “Improving query expansion performances with pseudo relevance feedback and wu-palmer similarity on cross language information retrieval,” 2022. doi: 10.1109/ICAICTA56449.2022.9932984.10.1109/ICAICTA56449.2022.9932984 ↗
45. Vision-language model for visual question answering in medical imagery10.3390/bioengineering10030380 ↗
46. Visual question generation from remote sensing images10.1109/JSTARS.2023.3261361 ↗
47. XAI for image captioning using SHAP
48. Safety compliance checking of construction behaviors using visual question answering10.1016/j.autcon.2022.104580 ↗
49. Bi-modal transformer-based approach for visual question answering in remote sensing imagery10.1109/TGRS.2022.3192460 ↗
50. Unified vision-language pre-training for image captioning and VQA
51. Weight analysis for various prohibitory sign detection and recognition using deep learning10.1007/s11042-020-09509-x ↗
52. Vision-language transformer for interpretable pathology visual question answering10.1109/JBHI.2022.3163751 ↗
53. K-PathVQA: Knowledge-aware multimodal representation for pathology visual question answering10.1109/JBHI.2023.3294249 ↗
54. Image captioning as an assistive technology: Lessons learned from VizWiz 2020 challenge10.1613/jair.1.13113 ↗
55. VizWiz grand challenge: Answering visual questions from blind people
56. van Sonsbeek · Lecture Notes in Computer Science · 2023 · 72610.1007/978-3-031-43904-9_70 ↗
57. Bottom-up and top-down attention for image captioning and visual question answering
58. Overcoming data limitation in medical visual question answering10.1007/978-3-030-32251-9_57 ↗
59. Multiple meta-model quantifying for medical visual question answering10.1007/978-3-030-87240-3_7 ↗
60. VQAMix: Conditional triplet mixup for medical visual question answering10.1109/TMI.2022.3185008 ↗
61. AMAM: An attention-based multimodal alignment model for medical visual question answering
62. Making the V in VQA matter: Elevating the role of image understanding in visual question answering10.1007/s11263-018-1116-0 ↗
63. V. Kazemi and A. Elqursh, “Show, ask, attend, and answer: A strong baseline for visual question answering,” Apr. 2017. doi: 10.48550/arXiv.1704.03162.