{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:02:30Z","timestamp":1749268950640,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819663880","type":"print"},{"value":"9789819663897","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-6389-7_17","type":"book-chapter","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T06:59:35Z","timestamp":1749193175000},"page":"200-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Question Answering for\u00a0Medical Data Using a\u00a0Visio-Linguistic Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5235-7808","authenticated-orcid":false,"given":"Van Hieu","family":"Bui","sequence":"first","affiliation":[]},{"given":"Quang Duc","family":"Tran","sequence":"additional","affiliation":[]},{"given":"Kim Thanh Tran","family":"Thi","sequence":"additional","affiliation":[]},{"given":"Viet Tien","family":"Le","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,7]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: visual question answering. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2425\u20132433. IEEE Computer Society, Los Alamitos, CA, USA (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"17_CR2","unstructured":"Dong, N., Xing, E.: Few-shot semantic segmentation with prototype learning. arXiv preprint arXiv:1804.04754 (2018)"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Khare, Y., Bagal, V., Mathew, M., Devi, A., Priyakumar, U.D., Jawahar, C.: Mmbert: multimodal bert pretraining for improved medical vqa. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1033\u20131036 (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434063","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"17_CR4","unstructured":"Kumar, A., et al.: Ask me anything: Dynamic memory networks for natural language processing. In: Proceedings of the International Conference on Machine Learning (2016)"},{"key":"17_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Abacha, A.B., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5, 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"17_CR6","unstructured":"Le, H., Tran, T., Venkatesh, S.: Self-attentive associative memory. In: Proceedings of the International Conference on Machine Learning, pp. 5682\u20135691 (2020)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., He, J., Zhao, Z., Zhong, S.: Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering. In: Lecture Notes in Computer Science, pp. 374\u2013383 (2023)","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"17_CR8","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. arXiv preprint arXiv:2111.10056 (2022)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"17_CR10","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Pellegrini, C., Keicher, M., \u00d6zsoy, E., Navab, N.: Radrestruct: A novel vqa benchmark and method for structured radiology reporting. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 409\u2013419. Springer Nature Switzerland (October 2023)","DOI":"10.1007\/978-3-031-43904-9_40"},{"key":"17_CR12","unstructured":"Ramsauer, H., et al.: Hopfield networks is all you need. arXiv preprint arXiv:2008.02217 (2020)"},{"key":"17_CR13","unstructured":"Sato, A., Yamada, K.: Generalized learning vector quantization. In: Advances in Neural Information Processing Systems, vol. 8 (NeurIPS), pp. 423\u2013429 (1996)"},{"key":"17_CR14","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"17_CR15","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1038\/s41591-020-0942-0","volume":"26","author":"P Tschandl","year":"2020","unstructured":"Tschandl, P., et al.: Human-computer collaboration for skin cancer recognition. Nat. Med. 26, 1229\u20131234 (2020)","journal-title":"Nat. Med."},{"key":"17_CR16","unstructured":"Weston, J., Chopra, S., Bordes, A.: Memory networks. arXiv preprint arXiv:1410.3916 (2014)"},{"key":"17_CR17","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of the International Conference on Machine Learning (2015)"},{"key":"17_CR18","doi-asserted-by":"publisher","unstructured":"Yan, A., et al.: Radbert: Adapting transformer-based language models to radiology. Radiology: Artif. Intell. 4(4) (2022https:\/\/doi.org\/10.1148\/ryai.210258","DOI":"10.1148\/ryai.210258"},{"key":"17_CR19","doi-asserted-by":"publisher","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29, 5947\u20135959 (2018). https:\/\/doi.org\/10.1109\/TNNLS.2018.2817340","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"17_CR20","unstructured":"Zhang, X., et al.: Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"17_CR21","unstructured":"Zhang, Z., et al.: Challenges and solutions for out-of-distribution generalization in medical visual question answering. arXiv preprint (arXiv:2203.07564) (2022). https:\/\/arxiv.org\/abs\/2203.07564"}],"container-title":["Lecture Notes in Computer Science","Computational Data and Social Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6389-7_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T06:59:44Z","timestamp":1749193184000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6389-7_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819663880","9789819663897"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6389-7_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"7 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CSoNet","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Data and Social Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"csonet2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/csonet-conf.github.io\/csonet24\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}