{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T20:26:24Z","timestamp":1775766384662,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720857","type":"print"},{"value":"9783031720864","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72086-4_45","type":"book-chapter","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:34:45Z","timestamp":1727987685000},"page":"480-489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MMQL: Multi-Question Learning for\u00a0Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Qishen","family":"Chen","sequence":"first","affiliation":[]},{"given":"Minjie","family":"Bian","sequence":"additional","affiliation":[]},{"given":"Huahu","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,4]]},"reference":[{"key":"45_CR1","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In: Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes. 9-12 September 2019 (2019)"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Cong, F., Xu, S., Guo, L., Tian, Y.: Caption-aware medical vqa via semantic focusing and progressive cross-modality comprehension. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 3569\u20133577 (2022), 10.1145\/3503161.3548122","DOI":"10.1145\/3503161.3548122"},{"key":"45_CR3","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: Pubmedclip: How much does clip benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023. pp. 1151\u20131163 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Gong, H., Chen, G., Liu, S., Yu, Y., Li, G.: Cross-modal self-attention with multi-task pre-training for medical visual question answering. In: Proceedings of the 2021 international conference on multimedia retrieval. pp. 456\u2013460 (2021), 10.1145\/3460426.3463584","DOI":"10.1145\/3460426.3463584"},{"key":"45_CR5","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International conference on machine learning. pp. 1321\u20131330. PMLR (2017)"},{"key":"45_CR6","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT. pp. 4171\u20134186 (2019), 10.18653\/v1\/n19-1423"},{"key":"45_CR7","doi-asserted-by":"crossref","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. IEEE (2021), 10.1109\/ISBI48211.2021.9434063","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"45_CR8","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. Advances in neural information processing systems 31 (2018)"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Lei, C., Wu, L., Liu, D., Li, Z., Wang, G., Tang, H., Li, H.: Multi-question learning for visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 11328\u201311335 (2020), 10.1609\/aaai.v34i07.6794","DOI":"10.1609\/aaai.v34i07.6794"},{"key":"45_CR10","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), 10.1109\/ISBI48211.2021.9434010","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Liu, J., Shen, D., Zhang, Y., Dolan, B., Carin, L., Chen, W.: What makes good in-context examples for gpt-3? DeeLIO 2022 p.\u00a0100 (2022), 10.18653\/v1\/2022.deelio-1.10","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Liu, L., Su, X.: How well apply multimodal mixup and simple mlps backbone to medical visual question answering? In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). pp. 2648\u20132655. IEEE (2022), 10.1109\/BIBM55620.2022.9995347","DOI":"10.1109\/BIBM55620.2022.9995347"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 10012\u201310022 (2021), 10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Lu, Y., Bartolo, M., Moore, A., Riedel, S., Stenetorp, P.: Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 8086\u20138098 (2022), 2022.acl-long.556","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, B.D., Do, T.T., Nguyen, B.X., Do, T., Tjiputra, E., Tran, Q.D.: Overcoming data limitation in medical visual question answering. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part IV 22. pp. 522\u2013530. Springer (2019), 10.1007\/978-3-030-32251-9_57","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Pan, H., He, S., Zhang, K., Qu, B., Chen, C., Shi, K.: Amam: An attention-based multimodal alignment model for medical visual question answering. Knowledge-Based Systems 255, 109763 (2022), 10.1016\/j.knosys.2022.109763","DOI":"10.1016\/j.knosys.2022.109763"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Yang, Z., Garcia, N., Chu, C., Otani, M., Nakashima, Y., Takemura, H.: Bert representations for video question answering. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1556\u20131565 (2020)","DOI":"10.1109\/WACV45572.2020.9093596"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Jin, Q., Tan, C., Zhao, Z., Yuan, H., Huang, F., Huang, S.: Ramm: Retrieval-augmented biomedical visual question answering with multi-modal pre-training. arXiv e-prints pp. arXiv\u20132303 (2023), 10.48550\/arXiv.2303.00534","DOI":"10.1145\/3581783.3611830"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Zhan, L.M., Liu, B., Fan, L., Chen, J., Wu, X.M.: Medical visual question answering via conditional reasoning. In: Proceedings of the 28th ACM International Conference on Multimedia. pp. 2345\u20132354 (2020), 10.1145\/3394171.3413761","DOI":"10.1145\/3394171.3413761"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4486\u20134496 (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"45_CR21","unstructured":"Zhang, X., Wu, C., Zhao, Z., Lin, W., Zhang, Y., Wang, Y., Xie, W.: Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Jiang, X., Cai, D., Xiao, J., He, X., Pu, S.: Multi-turn video question answering via multi-stream hierarchical attention context network. In: IJCAI. vol.\u00a02018, p.\u00a027th (2018)","DOI":"10.24963\/ijcai.2018\/513"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72086-4_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:39:59Z","timestamp":1727987999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72086-4_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720857","9783031720864"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72086-4_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"4 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}