{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:48:36Z","timestamp":1779382116038,"version":"3.53.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720857","type":"print"},{"value":"9783031720864","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\/978-3-031-72086-4_55","type":"book-chapter","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:34:45Z","timestamp":1727987685000},"page":"585-594","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Region-Specific Retrieval Augmentation for\u00a0Longitudinal Visual Question Answering: A Mix-and-Match Paradigm"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0048-3179","authenticated-orcid":false,"given":"Ka-Wai","family":"Yung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayaram","family":"Sivaraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0980-3227","authenticated-orcid":false,"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Loukogeorgakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0357-5996","authenticated-orcid":false,"given":"Evangelos B.","family":"Mazomenos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,4]]},"reference":[{"key":"55_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-016-0966-6","volume":"123","author":"A Agrawal","year":"2015","unstructured":"Agrawal, A., Lu, J., Antol, S., et\u00a0al.: Vqa: Visual question answering. Int. J. Comput. Vis. 123, 4 \u2013 31 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., et\u00a0al.: Counterfactual samples synthesizing for robust visual question answering. CVPR pp. 10797\u201310806 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"55_CR3","unstructured":"Chen, W., Hu, H., Saharia, C., Cohen, W.W.: Re-imagen: Retrieval-augmented text-to-image generator. In: ICLR (2023)"},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., \u00c7aglar G\u00fcl\u00e7ehre, et\u00a0al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Do, T., Nguyen, B.X., Tjiputra, E., et\u00a0al.: Multiple meta-model quantifying for medical visual question answering. In: MICCAI (2021)","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Gao, F., Ping, Q., Thattai, G., et\u00a0al.: Transform-retrieve-generate: Natural language-centric outside-knowledge visual question answering. CVPR pp. 5057\u20135067 (2022)","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Gokhale, T., Banerjee, P., Baral, C., et\u00a0al.: Mutant: A training paradigm for out-of-distribution generalization in visual question answering. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"55_CR8","doi-asserted-by":"crossref","unstructured":"Hu, X., Gu, L., An, Q., et\u00a0al.: Expert knowledge-aware image difference graph representation learning for difference-aware medical visual question answering. In: KDD. p. 4156-4165 (2023)","DOI":"10.1145\/3580305.3599819"},{"key":"55_CR9","unstructured":"Izacard, G., Lewis, P.S.H., Lomeli, M., et\u00a0al.: Atlas: Few-shot learning with retrieval augmented language models. J. Mach. Learn. Res. 24, 251:1\u2013251:43 (2023)"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, H., Misra, I., Rohrbach, M., et\u00a0al.: In defense of grid features for visual question answering. CVPR pp. 10264\u201310273 (2020)","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"55_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, A.E.W., Pollard, T.J., Berkowitz, S.J., et\u00a0al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. data 6 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"3","key":"55_CR12","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Karwande, G., Mbakawe, A., Wu, J.T., et\u00a0al.: Chexrelnet: An anatomy-aware model for tracking longitudinal relationships between chest x-rays. In: MICCAI. vol. 13431, pp. 581\u2013591 (2022)","DOI":"10.1007\/978-3-031-16431-6_55"},{"key":"55_CR14","doi-asserted-by":"crossref","unstructured":"Khare, Y., Bagal, V., Mathew, M., et\u00a0al.: Mmbert: Multimodal bert pretraining for improved medical vqa. ISBI pp. 1033\u20131036 (2021)","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"55_CR15","unstructured":"Lewis, P., Perez, E., Piktus, A., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. In: NIPS (2020)"},{"key":"55_CR16","first-page":"22003","volume":"35","author":"BY Lin","year":"2022","unstructured":"Lin, B.Y., Tan, K., Miller, C., et\u00a0al.: Unsupervised cross-task generalization via retrieval augmentation. NIPS 35, 22003\u201322017 (2022)","journal-title":"NIPS"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Wu, X.M.: Contrastive pre-training and representation distillation for medical visual question answering based on radiology images. In: MICCAI (2021)","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"55_CR18","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. ISBI pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"55_CR19","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. ArXiv abs\/1807.03748 (2018)"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Pellegrini, C., Keicher, M., \u00d6zsoy, E., other: Rad-restruct: A novel vqa benchmark and method for structured radiology reporting. In: MICCAI. pp. 409\u2013419 (2023)","DOI":"10.1007\/978-3-031-43904-9_40"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Yamamoto, S., Nakashima, K., et\u00a0al.: Describing and localizing multiple changes with transformers. In: ICCV. pp. 1951\u20131960 (2021)","DOI":"10.1109\/ICCV48922.2021.00198"},{"issue":"6","key":"55_CR22","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.B., et\u00a0al.: Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"55_CR23","doi-asserted-by":"crossref","unstructured":"van Sonsbeek, T., Derakhshani, M.M., Najdenkoska, I., et\u00a0al.: Open-ended medical visual question answering through prefix tuning of language models. In: MICCAI. pp. 726\u2013736 (2023)","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"55_CR24","doi-asserted-by":"crossref","unstructured":"Tascon-Morales, S., M\u00e1rquez-Neila, P., Sznitman, R.: Localized questions in medical visual question answering. In: MICCAI. pp. 361\u2013370 (2023)","DOI":"10.1007\/978-3-031-43895-0_34"},{"key":"55_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., et\u00a0al.: A question-centric model for visual question answering in medical imaging. IEEE Trans Med Imaging 39, 2856\u20132868 (2020)","journal-title":"IEEE Trans Med Imaging"},{"key":"55_CR26","doi-asserted-by":"crossref","unstructured":"Yao, L., Wang, W., Jin, Q.: Image difference captioning with pre-training and contrastive learning. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"55_CR27","doi-asserted-by":"crossref","unstructured":"Zakka, C., Shad, R., Chaurasia, A., et\u00a0al.: Almanac-retrieval-augmented language models for clinical medicine. NEJM AI 1(2), AIoa2300068 (2024)","DOI":"10.1056\/AIoa2300068"},{"key":"55_CR28","doi-asserted-by":"crossref","unstructured":"Zhan, L.M., Liu, B., Fan, L., et\u00a0al.: Medical visual question answering via conditional reasoning. ACM-MM (2020)","DOI":"10.1145\/3394171.3413761"},{"key":"55_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Mathai, T.S., Mukherjee, P., et\u00a0al.: Utilizing longitudinal chest x-rays and reports to pre-fill radiology reports. In: MICCAI. vol. 14224, pp. 189\u2013198 (2023)","DOI":"10.1007\/978-3-031-43904-9_19"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72086-4_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:42:24Z","timestamp":1727988144000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72086-4_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720857","9783031720864"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72086-4_55","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":"4 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}