{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:35:00Z","timestamp":1777487700451,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819958467","type":"print"},{"value":"9789819958474","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-5847-4_15","type":"book-chapter","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T20:30:00Z","timestamp":1693341000000},"page":"202-214","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MAMF: A Multi-Level Attention-Based Multimodal Fusion Model for Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Shaopei","family":"Long","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyong","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,30]]},"reference":[{"key":"15_CR1","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the International Conference on Machine Learning, pp. 1126\u20131135 (2017)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Proceedings of the International Conference on Artificial Neural Networks, pp. 52\u201359 (2011)","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"15_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Hao, T., Li, X., He, Y., Wang, F.L., Qu, Y.: Recent progress in leveraging deep learning methods for question answering. Neural Comput. Appl. 34, 2765\u20132783 (2022)","DOI":"10.1007\/s00521-021-06748-3"},{"key":"15_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., Ben Abacha, A., 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":"15_CR6","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR8","unstructured":"Abacha, A.B., Gayen, S., Lau, J.J., Rajaraman, S., Demner-Fushman, D.: NLM at ImageCLEF 2018 visual question answering in the medical domain. In: Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum (CEUR Workshop Proceedings, Vol. 2125). CEUR WS.org, Avignon, France (2018)"},{"key":"15_CR9","unstructured":"Abacha, A.B., Hasan, S.A., Datla, V.V., Liu, J., Demner-Fushman, D., M\u00fcller, H.: VQA-Med: overview of the medical visual question answering task at ImageCLEF 2019. In: Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum (CEUR Workshop Proceedings, vol. 2380). CEUR-WS.org, Lugano, Switzerland (2019)"},{"key":"15_CR10","unstructured":"Raghu, M., Zhang, C., Kleinberg, J., Bengio, S.: Trans-fusion: understanding transfer learning for medical imaging. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems, pp. 3342\u20133352. NeurIPS, Vancouver, BC, Canada (2019)"},{"key":"15_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-32251-9_57","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"BD Nguyen","year":"2019","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: Shen, D., Liu, T., Peters, T.M., Staib, L.H., Essert, C., Zhou, S., Yap, P.-T., Khan, A. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 522\u2013530. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_57"},{"key":"15_CR12","unstructured":"Brown, T., et al.: Language Models are Few-Shot Learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"15_CR13","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)","DOI":"10.1145\/3394171.3413761"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: A Bi-level representation learning model for medical visual question answering. J. Biomed. Inform. 134, 104183 (2022)","DOI":"10.1016\/j.jbi.2022.104183"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"15_CR16","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus, R.: Simple baseline for visual question answering. arXiv preprint arXiv:1512.02167 (2015)"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016).https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"15_CR18","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q. V.: XLNet: generalized autoregressive pretraining for language understanding. arXiv preprint arXiv:1906.08237 (2019)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"15_CR20","unstructured":"Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T.: Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016)"},{"key":"15_CR21","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. arXiv preprint arXiv:1805.07932 (2018)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Do, T., Nguyen, B.X., Tjiputra, E., Tran, M., Tran, Q.D., Nguyen, A.: Multiple Meta-Model Quantifying for Medical Visual Question Answering. arXiv preprint arXiv:2105.08913 (2021)","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"15_CR23","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. arXiv preprint arXiv:2105.00136 (2021)","DOI":"10.1145\/3460426.3463584"},{"key":"15_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-87196-3_20","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Bo Liu","year":"2021","unstructured":"Liu, Bo., Zhan, L.-M., Wu, X.-M.: Contrastive Pre-training and representation distillation for medical visual question answering based on radiology images. In: de Bruijne, M., Cattin, P.C., Cotin, S., Padoy, N., Speidel, S., Zheng, Y., Essert, C. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 210\u2013220. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_20"},{"issue":"9","key":"15_CR25","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1109\/TMI.2020.2978284","volume":"39","author":"MH Vu","year":"2020","unstructured":"Vu, M.H., L\u00f6fstedt, T., Nyholm, T., Sznitman, R.: A question-centric model for visual question answering in medical imaging. IEEE Trans. Med. Imaging 39(9), 2856\u20132868 (2020)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"15_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-98390-1","volume":"11","author":"D Sharma","year":"2021","unstructured":"Sharma, D., Purushotham, S., Reddy, C.K.: MedFuseNet: an attention-based multimodal deep learning model for visual question answering in the medical domain. Sci. Rep. 11(1), 1\u201318 (2021)","journal-title":"Sci. Rep."},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: Proceedings of SSST@EMNLP 2014, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103\u2013111. Association for Computational Linguistics, Doha, Qatar (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: PathVQA: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"15_CR30","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"}],"container-title":["Communications in Computer and Information Science","International Conference on Neural Computing for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-5847-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T20:32:46Z","timestamp":1693341166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-5847-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819958467","9789819958474"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-5847-4_15","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NCAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Computing for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ncaa2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dl2link.com\/ncaa2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"83","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.67","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}