{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:18:35Z","timestamp":1743124715288,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031466762"},{"type":"electronic","value":"9783031466779"}],"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\/978-3-031-46677-9_32","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:02:29Z","timestamp":1699102949000},"page":"466-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Effective Pre-trained Visual Encoder for\u00a0Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Yefan","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"32_CR1","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PMLR (2020)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.-H., Wan, X.: Generating radiology reports via memory-driven transformer. ArXiv, abs\/2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"32_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Z., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI 2022. MICCAI 2022. LNCS, vol. 13435, pp. 679\u2013689. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_65","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"32_CR4","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: MM, pp. 3569\u20133577 (2022)","DOI":"10.1145\/3503161.3548122"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Delbrouck, J.-B., et al.: ViLMedic: a framework for research at the intersection of vision and language in medical AI. In: ACL, pp. 23\u201334 (2022)","DOI":"10.18653\/v1\/2022.acl-demo.3"},{"key":"32_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-030-87240-3_7","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","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. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 64\u201374. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_7"},{"key":"32_CR7","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, abs\/2112.13906 (2021)"},{"key":"32_CR8","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: ICMR, pp. 456\u2013460 (2021)","DOI":"10.1145\/3460426.3463584"},{"key":"32_CR9","first-page":"3332","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. TMI 41, 3332\u20133343 (2022)","journal-title":"TMI"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E.P., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. ArXiv, abs\/2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"issue":"2","key":"32_CR11","first-page":"103241","volume":"60","author":"J Huang","year":"2023","unstructured":"Huang, J., et al.: Medical knowledge-based network for patient-oriented visual question answering. IP &M 60(2), 103241 (2023)","journal-title":"IP &M"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: a multimodal global-local representation learning framework for label-efficient medical image recognition. In: ICCV, pp. 3922\u20133931 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, X., Liu, F., Huang, G.: OVQA: a clinically generated visual question answering dataset. In: SIGIR, pp. 2924\u20132938 (2022)","DOI":"10.1145\/3477495.3531724"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: ChExpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI, vol. 33, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"32_CR15","unstructured":"Johnson, A.E.W., et al.: Mimic-CXR: a large publicly available database of labeled chest radiographs. ArXiv, abs\/1901.07042 (2019)"},{"key":"32_CR16","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: ISBI, pp. 1033\u20131036 (2021)","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"32_CR17","first-page":"1571","volume":"31","author":"J-H Kim","year":"2018","unstructured":"Kim, J.-H., Jun, J., Zhang, B.-T.: Bilinear attention networks. NeurIPS 31, 1571\u20131581 (2018)","journal-title":"NeurIPS"},{"key":"32_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. abs\/1412.6980 (2015)"},{"issue":"1","key":"32_CR19","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), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., Tan, L., Liao, J., Zhong, S.: Self-supervised vision-language pretraining for medical visual question answering. ArXiv, abs\/2211.13594 (2022)","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"32_CR21","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. ArXiv, abs\/2111.10056 (2021)"},{"key":"32_CR22","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":"B Liu","year":"2021","unstructured":"Liu, B., Zhan, L.-M., Wu, X.-M.: Contrastive pre-training and\u00a0representation distillation for\u00a0medical visual question answering based on\u00a0radiology images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 210\u2013220. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_20"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: ISBI, pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, B.D., Do, T.-T., Nguyen, B.X., Do, T.K.L., Tjiputra, E., Tran, Q.D.: Overcoming data limitation in medical visual question answering. In: MICCAI, pp. 522\u2013530 (2019)","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"32_CR25","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. vol. 32, pp. 8024\u20138035 (2019)"},{"key":"32_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-030-01364-6_20","volume-title":"Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis","author":"O Pelka","year":"2018","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. (eds.) LABELS\/CVII\/STENT -2018. LNCS, vol. 11043, pp. 180\u2013189. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01364-6_20"},{"key":"32_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"32_CR28","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821\u20138831. PMLR (2021)"},{"key":"32_CR29","doi-asserted-by":"publisher","first-page":"50626","DOI":"10.1109\/ACCESS.2020.2980024","volume":"8","author":"F Ren","year":"2020","unstructured":"Ren, F., Zhou, Y.: CGMVQA: a new classification and generative model for medical visual question answering. IEEE Access 8, 50626\u201350636 (2020)","journal-title":"IEEE Access"},{"key":"32_CR30","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2014)","journal-title":"IJCV"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Schl\u00fcter, R., Ney, H.: LSTM neural networks for language modeling. In: Interspeech (2012)","DOI":"10.21437\/Interspeech.2012-65"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329 (2015)","DOI":"10.1109\/CVPR.2016.10"},{"key":"32_CR33","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: MM, pp. 2345\u20132354 (2020)","DOI":"10.1145\/3394171.3413761"},{"key":"32_CR34","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.: Contrastive learning of medical visual representations from paired images and text. ArXiv, abs\/2010.00747 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46677-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:26:11Z","timestamp":1699104371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46677-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466762","9783031466779"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46677-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","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":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","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":"216","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":"43% - 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":"2.97","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":"3.77","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)"}}]}}