{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T14:01:50Z","timestamp":1784469710370,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233779","type":"print"},{"value":"9789819233786","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3378-6_15","type":"book-chapter","created":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:01:54Z","timestamp":1784466114000},"page":"178-189","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CARR: Cross-Modal Adaptation with Reverse Reasoning for Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Wentao","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangping","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"issue":"1","key":"15_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., et al.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data. 5(1), 180251 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.251","journal-title":"Sci. Data"},{"key":"15_CR2","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., et al.: Overcoming data limitation in medical visual question answering. In: Shen, D., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019, pp. 522\u2013530. Springer International Publishing, Cham (2019)"},{"key":"15_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611","volume":"143","author":"Z Lin","year":"2023","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. Artif. Intell. Med. 143, 102611 (2023). https:\/\/doi.org\/10.1016\/j.artmed.2023.102611","journal-title":"Artif. Intell. Med."},{"issue":"1","key":"15_CR4","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E.J.: High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25(1), 44\u201356 (2019). https:\/\/doi.org\/10.1038\/s41591-018-0300-7","journal-title":"Nat. Med."},{"key":"15_CR5","doi-asserted-by":"publisher","unstructured":"Zhang, X. et al.: PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering (2023). https:\/\/arxiv.org\/abs\/2305.10415. doi:https:\/\/doi.org\/10.48550\/arXiv.2305.10415.","DOI":"10.48550\/arXiv.2305.10415"},{"issue":"1","key":"15_CR6","doi-asserted-by":"publisher","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","volume":"16","author":"C Wu","year":"2025","unstructured":"Wu, C., et al.: Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. Nat. Commun. 16(1), 7866 (2025)","journal-title":"Nat. Commun."},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Li, C. et al.: LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day (2023). https:\/\/arxiv.org\/abs\/2306.00890. doi:https:\/\/doi.org\/10.48550\/arXiv.2306.00890.","DOI":"10.48550\/arXiv.2306.00890"},{"key":"15_CR8","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: Vision-and-language transformer without convolution or region supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. PMLR (2021)."},{"key":"15_CR9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2110.09348","volume-title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","author":"L Jing","year":"2021","unstructured":"Jing, L., et al.: Understanding Dimensional Collapse in Contrastive Self-supervised Learning (2021). https:\/\/doi.org\/10.48550\/ARXIV.2110.09348"},{"key":"15_CR10","first-page":"4971","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"T Gu","year":"2024","unstructured":"Gu, T., Yang, K., Liu, D., Cai, W.: LaPA: latent prompt assist model for medical visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 4971\u20134980 (2024)"},{"key":"15_CR11","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., et al.: A visual-language foundation model for pathology image analysis using medical Twitter. Nat. Med. 29, 2307\u20132316 (2023)","journal-title":"Nat. Med."},{"key":"15_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103464","volume":"101","author":"C Zhan","year":"2025","unstructured":"Zhan, C., et al.: UnICLAM: contrastive representation learning with adversarial masking for unified and interpretable medical vision question answering. Med. Image Anal. 101, 103464 (2025). https:\/\/doi.org\/10.1016\/j.media.2025.103464","journal-title":"Med. Image Anal."},{"key":"15_CR13","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1109\/ISBI48211.2021.9434010","volume-title":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","author":"B Liu","year":"2021","unstructured":"Liu, B., et al.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE, Nice, France (2021)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6649\u20136658 (2019).","DOI":"10.1109\/CVPR.2019.00681"},{"issue":"12","key":"15_CR15","doi-asserted-by":"publisher","first-page":"4430","DOI":"10.1109\/TMI.2024.3425533","volume":"43","author":"L Cai","year":"2024","unstructured":"Cai, L., et al.: Counterfactual causal-effect intervention for interpretable medical visual question answering. IEEE Trans. Med. Imaging. 43(12), 4430\u20134441 (2024)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"15_CR16","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/BIBM62325.2024.10822825","volume-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"L Fan","year":"2024","unstructured":"Fan, L., et al.: Tri-VQA: triangular reasoning medical visual question answering for multi-attribute analysis. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1485\u20131488. IEEE, Lisbon, Portugal (2024)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21\u201329 (2016).","DOI":"10.1109\/CVPR.2016.10"},{"key":"15_CR18","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1109\/ISBI48211.2021.9434063","volume-title":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","author":"Y Khare","year":"2021","unstructured":"Khare, Y., et al.: MMBERT: multimodal BERT pretraining for improved medical VQA. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1033\u20131036. IEEE, Nice, France (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434063"},{"key":"15_CR19","volume-title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","author":"S Eslami","year":"2021","unstructured":"Eslami, S. et al.: Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?. https:\/\/arxiv.org\/abs\/2112.13906 (2021)."},{"key":"15_CR20","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-031-16443-9_65","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","author":"Z Chen","year":"2022","unstructured":"Chen, Z., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: Wang, L., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022, pp. 679\u2013689. Springer Nature Switzerland, Cham (2022)"},{"key":"15_CR21","volume-title":"BiomedCLIP: A Multimodal Biomedical Foundation Model Pretrained from Fifteen Million Scientific Image-Text Pairs","author":"S Zhang","year":"2023","unstructured":"Zhang, S. et al.: BiomedCLIP: A Multimodal Biomedical Foundation Model Pretrained from Fifteen Million Scientific Image-Text Pairs., https:\/\/arxiv.org\/abs\/2303.00915, (2023)."},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12700\u201312710 (2021).","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16000\u201316009 (2022).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR24","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-032-04978-0_19","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025. LNCS","author":"X Wan","year":"2026","unstructured":"Wan, X., et al.: Eliminating language bias for medical visual question answering with counterfactual contrastive training. In: Gee, J.C., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025. LNCS, vol. 15965, pp. 194\u2013204. Springer (2026). https:\/\/doi.org\/10.1007\/978-3-032-04978-0_19"},{"key":"15_CR25","unstructured":"Abacha, A.B., et al.: VQA-Med: overview of the medical visual question answering task at ImageCLEF 2019. In: CLEF (Working Notes), vol. 2 (2019)."},{"key":"15_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128730","volume":"613","author":"A Lameesa","year":"2025","unstructured":"Lameesa, A., et al.: VG-CALF: a vision-guided cross-attention and late-fusion network for radiology images in medical visual question answering. Neurocomputing. 613, 128730 (2025). https:\/\/doi.org\/10.1016\/j.neucom.2024.128730","journal-title":"Neurocomputing"},{"key":"15_CR27","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. LNCS","author":"O Pelka","year":"2018","unstructured":"Pelka, O., et al.: Radiology objects in COntext (ROCO): a multimodal image dataset. In: Stoyanov, D., et al. (eds.) Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. LNCS, vol. 11043, pp. 180\u2013189. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01364-6_20"},{"key":"15_CR28","doi-asserted-by":"publisher","unstructured":"Subramanian, S. 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:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.191.","DOI":"10.18653\/v1\/2020.findings-emnlp.191"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3378-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T13:01:57Z","timestamp":1784466117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3378-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"ISBN":["9789819233779","9789819233786"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3378-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"assertion":[{"value":"20 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}