{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T13:37:51Z","timestamp":1783690671602,"version":"3.55.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439063","type":"print"},{"value":"9783031439070","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\/978-3-031-43907-0_36","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:08:57Z","timestamp":1696115337000},"page":"374-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":64,"title":["Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-32251-9_57","volume":"4","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. MICCAI 4, 522\u2013530 (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_57","journal-title":"MICCAI"},{"key":"36_CR2","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-030-87240-3_7","volume":"5","author":"T Do","year":"2021","unstructured":"Do, T., Nguyen, B.X., Tjiputra, E., Tran, M., Tran, Q.D., Nguyen, A.: Multiple meta-model quantifying for medical visual question answering. MICCAI 5, 64\u201374 (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_7","journal-title":"MICCAI"},{"key":"36_CR3","doi-asserted-by":"publisher","unstructured":"Pelka, O., Koitka, S., R\u00fcckert, J., Nensa, F., Friedrich, C.M.: Radiology objects in context (ROCO): a multimodal image dataset. In: Stoyanov, D., et al. Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. LABELS CVII STENT 2018 2018 2018. Lecture Notes in Computer Science, vol. 11043, pp. 180\u2013189. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01364-6_20","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Subramanian, S., Wang, L.L., Bogin, B., et al.: Medicat: a dataset of medical images, captions, and textual references. In: Findings of the Association for Computational Linguistics, EMNLP 2020, pp. 2112\u20132120 (2020). https:\/\/github.com\/allenai\/medicat","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"36_CR5","unstructured":"Ruckert, J., Abacha, A.B., Herrera, A.G., et al.: Overview of ImageCLEF medical 2022-caption prediction and concept detection. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction (2022). https:\/\/www.imageclef.org\/2022"},{"key":"36_CR6","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-87196-3_20","volume":"2","author":"B Liu","year":"2021","unstructured":"Liu, B., Zhan, L.M., Wu, X.M., et al.: Contrastive pre-training and representation distillation for medical visual question answering based on radiology images. MICCAI 2, 210\u2013220 (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_20","journal-title":"MICCAI"},{"key":"36_CR7","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"36_CR8","unstructured":"Eslami, S., de Melo, G., Meinel, C.: Does clip benefit visual question answering in the medical domain as much as it does in the general domain? arXiv preprint arXiv: 2112.13906 (2021)"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Cong, F., Xu, S., Li, G., et al.: Caption-aware medical VQA via semantic focusing and progressive cross-modality comprehension. ACM Multimedia, pp. 3569\u20133577 (2022)","DOI":"10.1145\/3503161.3548122"},{"key":"36_CR10","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-031-16443-9_65","volume":"5","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Du, Y., Hu, J., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. MICCAI 5, 679\u2013689 (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_65","journal-title":"MICCAI"},{"key":"36_CR11","doi-asserted-by":"crossref","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). https:\/\/osf.io\/bd96f","DOI":"10.1038\/sdata.2018.251"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Towards visual question answering on pathology images. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP, pp. 708\u2013718 (2021). https:\/\/github.com\/UCSD-AI4H\/PathVQA","DOI":"10.18653\/v1\/2021.acl-short.90"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., et al.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: ISBI, IEEE, pp. 1650\u20131654 (2021). https:\/\/www.med-vqa.com\/slake\/","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., et al.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"36_CR15","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NeurIPS 30 (2017)"},{"key":"36_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"36_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv: 1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., et al.: Girshick: momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"36_CR20","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A., et al.: Align before fuse: Vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR21","unstructured":"Li, J., Li, D, Xiong, C, et al.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning. PMLR, pp. 12888\u201312900 (2022)"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., et al.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15979\u201315988 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., et al.: Scaling Language-Image Pre-training via Masking. arXiv preprint arXiv: 2212.00794 (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., et al.: Randaugment: practical automated data augmentation with a reduced search space. In: CVPR Workshops, pp. 3008\u20133017 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"36_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv: 1711.05101 (2017)"},{"key":"36_CR26","doi-asserted-by":"publisher","first-page":"109763","DOI":"10.1016\/j.knosys.2022.109763","volume":"255","author":"H Pan","year":"2022","unstructured":"Pan, H., He, S., Zhang, K., et al.: AMAM: an attention-based multimodal alignment model for medical visual question answering. Knowl.-Based Syst. 255, 109763 (2022)","journal-title":"Knowl.-Based Syst."},{"issue":"11","key":"36_CR27","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1109\/TMI.2022.3185008","volume":"41","author":"H Gong","year":"2022","unstructured":"Gong, H., Chen, G., Mao, M., Li, Z., Li, G.: VQAMix: conditional triplet mixup for medical visual question answering. IEEE Trans. Med. Imaging 41(11), 3332\u20133343 (2022)","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43907-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T18:25:46Z","timestamp":1709835946000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43907-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439063","9783031439070"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43907-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","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":"730","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":"0","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":"32% - 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","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":"5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}