{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:59:01Z","timestamp":1783439941843,"version":"3.54.6"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723520","type":"print"},{"value":"9783031723537","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\/978-3-031-72353-7_22","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:04:02Z","timestamp":1726499042000},"page":"299-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["MISS: A Generative Pre-training and\u00a0Fine-Tuning Approach for\u00a0Med-VQA"],"prefix":"10.1007","author":[{"given":"Jiawei","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"22_CR1","unstructured":"Stein, A., Carol\u00a0Wu, C.C., et\u00a0al.: RSNA pneumonia detection challenge (2018). https:\/\/kaggle.com\/competitions\/rsna-pneumonia-detection-challenge"},{"key":"22_CR2","doi-asserted-by":"publisher","unstructured":"Chen, C., Zhong, A., Wu, D., et\u00a0al.: Contrastive masked image-text modeling for medical visual representation learning. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14224, pp. 493\u2013503. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43904-9_48","DOI":"10.1007\/978-3-031-43904-9_48"},{"key":"22_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Z., Du, Y., Hu, J., et\u00a0al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) 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":"22_CR4","doi-asserted-by":"crossref","unstructured":"Cong, F., Xu, S., et\u00a0al.: Caption-aware medical VQA via semantic focusing and progressive cross-modality comprehension. In: ACM MM, pp. 3569\u20133577 (2022)","DOI":"10.1145\/3503161.3548122"},{"key":"22_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., et\u00a0al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"22_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":"22_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., et\u00a0al.: An empirical study of training end-to-end vision-and-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"22_CR9","unstructured":"Eslami, S., de\u00a0Melo, G., Meinel, C.: Does CLIP benefit visual question answering in the medical domain as much as it does in the general domain? CoRR abs\/2112.13906 (2021). https:\/\/arxiv.org\/abs\/2112.13906"},{"key":"22_CR10","doi-asserted-by":"publisher","unstructured":"Gong, H., Chen, G., Mao, M., et\u00a0al.: VQAMix: conditional triplet mixup for medical visual question answering. IEEE Trans. Med. Imaging 41(11), 3332\u20133343 (2022). https:\/\/doi.org\/10.1109\/TMI.2022.3185008","DOI":"10.1109\/TMI.2022.3185008"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., et\u00a0al.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., et\u00a0al.: Momentum contrast for unsupervised visual representation learning, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Lau, J.J., Gayen, S., et\u00a0al.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(1), 1\u201310 (2018)","DOI":"10.1038\/sdata.2018.251"},{"key":"22_CR14","doi-asserted-by":"publisher","unstructured":"Lei, Y., Yang, D., Li, M., Wang, S., Chen, J., Zhang, L.: Text-oriented modality reinforcement network for multimodal sentiment analysis from unaligned multimodal sequences. In: Fang, L., Pei, J., Zhai, G., Wang, R. (eds.) CICAI 2023. LNCS, vol. 14474, pp. 189\u2013200. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-9119-8_18","DOI":"10.1007\/978-981-99-9119-8_18"},{"key":"22_CR15","unstructured":"Li, C., Wong, C., Zhang, S., et\u00a0al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"22_CR16","unstructured":"Li, C., et al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. In: Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 28541\u201328564. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/5abcdf8ecdcacba028c6662789194572-Paper-Datasets_and_Benchmarks.pdf"},{"key":"22_CR17","unstructured":"Li, J., Li, D., Xiong, C., et\u00a0al.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICCV, pp. 12888\u201312900 (2022)"},{"key":"22_CR18","unstructured":"Li, J., Selvaraju, R., Gotmare, A., et\u00a0al.: Align before fuse: vision and language representation learning with momentum distillation. In: NIPS, vol. 34, pp. 9694\u20139705 (2021)"},{"key":"22_CR19","unstructured":"Li, L.H., Yatskar, M., Yin, D., et\u00a0al.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"22_CR20","doi-asserted-by":"publisher","unstructured":"Li, P., Liu, G., He, J., et\u00a0al.: Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14220, pp. 374\u2013383. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43907-0_36","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"22_CR21","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":"22_CR22","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., et\u00a0al.: 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":"22_CR23","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., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 522\u2013530. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_57"},{"key":"22_CR24","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. KBS 255, 109763 (2022)","journal-title":"KBS"},{"key":"22_CR25","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":"22_CR26","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Subramanian, S., Wang, L.L., Mehta, S., et\u00a0al.: MedICaT: a dataset of medical images, captions, and textual references. In: Findings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"22_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: NIPS, vol. 30 (2017)"},{"key":"22_CR29","unstructured":"Zhang, S., Xu, Y., Usuyama, N., et\u00a0al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv preprint arXiv:2303.00915 (2023)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72353-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:21:25Z","timestamp":1726500085000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72353-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723520","9783031723537"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72353-7_22","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":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}