{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:26:56Z","timestamp":1786130816539,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609079","type":"print"},{"value":"9789819609086","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0908-6_6","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:26:44Z","timestamp":1733513204000},"page":"98-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["MedBLIP: Bootstrapping Language-Image Pretraining from\u00a03D Medical Images and\u00a0Texts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1210-1306","authenticated-orcid":false,"given":"Qiuhui","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9065-3691","authenticated-orcid":false,"given":"Yi","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"6_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR2","unstructured":"Bai, F., Du, Y., Huang, T., Meng, M.Q.H., Zhao, B.: M3d: Advancing 3d medical image analysis with multi-modal large language models. arXiv preprint arXiv:2404.00578 (2024)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bannur, S., Hyland, S., Liu, Q., Perez-Garcia, F., Ilse, M., Castro, D.C., Boecking, B., Sharma, H., Bouzid, K., Thieme, A., et\u00a0al.: Learning to exploit temporal structure for biomedical vision-language processing. arXiv preprint arXiv:2301.04558 (2023)","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"6_CR4","first-page":"32897","volume":"35","author":"H Bao","year":"2022","unstructured":"Bao, H., Wang, W., Dong, L., Liu, Q., Mohammed, O.K., Aggarwal, K., Som, S., Piao, S., Wei, F.: Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. Adv. Neural. Inf. Process. Syst. 35, 32897\u201332912 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3","key":"6_CR5","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1097\/WAD.0b013e318142774e","volume":"21","author":"DL Beekly","year":"2007","unstructured":"Beekly, D.L., Ramos, E.M., Lee, W.W., Deitrich, W.D., Jacka, M.E., Wu, J., Hubbard, J.L., Koepsell, T.D., Morris, J.C., Kukull, W.A., et al.: The national alzheimer\u2019s coordinating center (nacc) database: the uniform data set. Alzheimer Disease & Associated Disorders 21(3), 249\u2013258 (2007)","journal-title":"Alzheimer Disease & Associated Disorders"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Guo, H., Yi, K., Li, B., Elhoseiny, M.: Visualgpt: Data-efficient adaptation of pretrained language models for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18030\u201318040 (2022)","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"6_CR7","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., Gehrmann, S., et\u00a0al.: Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"6_CR8","unstructured":"Chung, H.W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, E., Wang, X., Dehghani, M., Brahma, S., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"6_CR9","unstructured":"Dodge, J., Sap, M., Marasovic, A., Agnew, W., Ilharco, G., Groeneveld, D., Gardner, M.: Documenting the english colossal clean crawled corpus. arXiv preprint arXiv:2104.08758 (2021)"},{"key":"6_CR10","unstructured":"Driess, D., Xia, F., Sajjadi, M.S., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T., et\u00a0al.: Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"issue":"4","key":"6_CR11","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1017\/S1041610209009405","volume":"21","author":"KA Ellis","year":"2009","unstructured":"Ellis, K.A., Bush, A.I., Darby, D., De Fazio, D., Foster, J., Hudson, P., Lautenschlager, N.T., Lenzo, N., Martins, R.N., Maruff, P., et al.: The australian imaging, biomarkers and lifestyle (aibl) study of aging: methodology and baseline characteristics of 1112 individuals recruited for a longitudinal study of alzheimer\u2019s disease. Int. Psychogeriatr. 21(4), 672\u2013687 (2009)","journal-title":"Int. Psychogeriatr."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Fang, Y., Wang, W., Xie, B., Sun, Q., Wu, L., Wang, X., Huang, T., Wang, X., Cao, Y.: Eva: Exploring the limits of masked visual representation learning at scale. arXiv preprint arXiv:2211.07636 (2022)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"6_CR13","unstructured":"Gao, L., Biderman, S., Black, S., Golding, L., Hoppe, T., Foster, C., Phang, J., He, H., Thite, A., Nabeshima, N., et\u00a0al.: The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"6_CR15","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Jain, S.M.: Hugging face. In: Introduction to Transformers for NLP: With the Hugging Face Library and Models to Solve Problems, pp. 51\u201367. Springer (2022)","DOI":"10.1007\/978-1-4842-8844-3_4"},{"key":"6_CR17","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning. pp. 4904\u20134916. PMLR (2021)"},{"key":"6_CR18","unstructured":"Koh, J.Y., Salakhutdinov, R., Fried, D.: Grounding language models to images for multimodal generation. arXiv preprint arXiv:2301.13823 (2023)"},{"key":"6_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"6_CR20","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning. pp. 12888\u201312900. PMLR (2022)"},{"key":"6_CR21","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: 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":"6_CR22","unstructured":"Li, Y., Liang, F., Zhao, L., Cui, Y., Ouyang, W., Shao, J., Yu, F., Yan, J.: Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., Liu, T.Y.: Biogpt: generative pre-trained transformer for biomedical text generation and mining. Briefings in Bioinformatics 23(6) (2022)","DOI":"10.1093\/bib\/bbac409"},{"key":"6_CR24","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.neuroimage.2012.12.044","volume":"70","author":"IB Malone","year":"2013","unstructured":"Malone, I.B., Cash, D., Ridgway, G.R., MacManus, D.G., Ourselin, S., Fox, N.C., Schott, J.M.: Miriad-public release of a multiple time point alzheimer\u2019s mr imaging dataset. Neuroimage 70, 33\u201336 (2013)","journal-title":"Neuroimage"},{"issue":"9","key":"6_CR25","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1162\/jocn.2007.19.9.1498","volume":"19","author":"DS Marcus","year":"2007","unstructured":"Marcus, D.S., Wang, T.H., Parker, J., Csernansky, J.G., Morris, J.C., Buckner, R.L.: Open access series of imaging studies (oasis): cross-sectional mri data in young, middle aged, nondemented, and demented older adults. J. Cogn. Neurosci. 19(9), 1498\u20131507 (2007)","journal-title":"J. Cogn. Neurosci."},{"key":"6_CR26","unstructured":"Moor, M., Huang, Q., Wu, S., Yasunaga, M., Dalmia, Y., Leskovec, J., Zakka, C., Reis, E.P., Rajpurkar, P.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H). pp. 353\u2013367. PMLR (2023)"},{"key":"6_CR27","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"issue":"3","key":"6_CR28","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1212\/WNL.0b013e3181cb3e25","volume":"74","author":"RC Petersen","year":"2010","unstructured":"Petersen, R.C., Aisen, P.S., Beckett, L.A., Donohue, M.C., Gamst, A.C., Harvey, D.J., Jack, C.R., Jagust, W.J., Shaw, L.M., Toga, A.W., et al.: Alzheimer\u2019s disease neuroimaging initiative (adni): clinical characterization. Neurology 74(3), 201\u2013209 (2010)","journal-title":"Neurology"},{"key":"6_CR29","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"issue":"7972","key":"6_CR30","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K., Azizi, S., Tu, T., Mahdavi, S.S., Wei, J., Chung, H.W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al.: Large language models encode clinical knowledge. Nature 620(7972), 172\u2013180 (2023)","journal-title":"Nature"},{"key":"6_CR31","unstructured":"Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Hou, L., Clark, K., Pfohl, S., Cole-Lewis, H., Neal, D., et\u00a0al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"van Sonsbeek, T., Derakhshani, M.M., Najdenkoska, I., Snoek, C.G., Worring, M.: Open-ended medical visual question answering through prefix tuning of language models. arXiv preprint arXiv:2303.05977 (2023)","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Tiu, E., Talius, E., Patel, P., Langlotz, C.P., Ng, A.Y., Rajpurkar, P.: Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nature Biomedical Engineering pp.\u00a01\u20138 (2022)","DOI":"10.1038\/s41551-022-00936-9"},{"key":"6_CR34","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"6_CR35","first-page":"200","volume":"34","author":"M Tsimpoukelli","year":"2021","unstructured":"Tsimpoukelli, M., Menick, J.L., Cabi, S., Eslami, S., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. Adv. Neural. Inf. Process. Syst. 34, 200\u2013212 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR36","unstructured":"Venigalla, A., Frankle, J., Carbin, M.: Biomedlm: a domain-specific large language model for biomedical text. MosaicML. Accessed: Dec 23 (2022)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Z., Ouyang, X., Wang, Q., Shen, D.: Chatcad: Interactive computer-aided diagnosis on medical image using large language models. arXiv preprint arXiv:2302.07257 (2023)","DOI":"10.1038\/s44172-024-00271-8"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Lin, Y., Cao, Y., Hu, H., Bai, X.: A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model. arXiv preprint arXiv:2112.14757 (2021)","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"6_CR40","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"6_CR42","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X.V., et\u00a0al.: Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:09:43Z","timestamp":1733515783000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}