{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T07:12:22Z","timestamp":1758438742407,"version":"3.44.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032051844"},{"type":"electronic","value":"9783032051851"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-05185-1_36","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:46:30Z","timestamp":1758325590000},"page":"369-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Med-BiasX: Robust Medical Visual Question Answering with\u00a0Language Biases"],"prefix":"10.1007","author":[{"given":"Huanjia","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Yishu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Chengju","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Bingzhi","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Basu, A., Addepalli, S., Babu, R.V.: Rmlvqa: A margin loss approach for visual question answering with language biases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11671\u201311680 (2023)","DOI":"10.1109\/CVPR52729.2023.01123"},{"key":"36_CR3","unstructured":"Cadene, R., Dancette, C., Ben-younes, H., Cord, M., Parikh, D.: Rubi: Reducing unimodal biases in visual question answering. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS). vol.\u00a032 (2019)"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10800\u201310809 (2020)","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 679\u2013689. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"36_CR6","doi-asserted-by":"crossref","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: Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 64\u201374. Springer (2021)","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Han, X., Wang, S., Su, C.: Greedy gradient ensemble for robust visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1584\u20131593 (2021)","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"36_CR8","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS). vol.\u00a031 (2018)"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Kolling, C., More, M., Gavenski, N., Pooch, E., Parraga, O., Barros, R.C.: Efficient counterfactual debiasing for visual question answering. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3001\u20133010 (2022)","DOI":"10.1109\/WACV51458.2022.00263"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5(1), 1\u201310 (2018)","DOI":"10.1038\/sdata.2018.251"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Liang, Z., Hu, H., Zhu, J.: Lpf: A language-prior feedback objective function for de-biased visual question answering. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 1955\u20131959 (2021)","DOI":"10.1145\/3404835.3462981"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Liang, Z., Jiang, W., Hu, H., Zhu, J.: Learning to contrast the counterfactual samples for robust visual question answering. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3285\u20133292 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"36_CR13","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: Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 210\u2013220. Springer (2021)","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: 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 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Wu, X.M.: Medical visual question answering via conditional reasoning and contrastive learning. IEEE Transactions on Medical Imaging (TMI) 42(5), 1532\u20131545 (2022)","DOI":"10.1109\/TMI.2022.3232411"},{"key":"36_CR16","unstructured":"Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS). vol.\u00a033, pp. 21464\u201321475 (2020)"},{"key":"36_CR17","doi-asserted-by":"crossref","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: Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 522\u2013530. Springer (2019)","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"36_CR18","unstructured":"Wen, Z., Xu, G., Tan, M., Wu, Q., Wu, Q.: Debiased visual question answering from feature and sample perspectives. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS). vol.\u00a034, pp. 3784\u20133796 (2021)"},{"key":"36_CR19","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":"36_CR20","doi-asserted-by":"crossref","unstructured":"Yao, Z., Lai, Z., Liu, W.: A symmetric kl divergence based spatiogram similarity measure. In: 2011 18th IEEE International Conference on Image Processing, pp. 193\u2013196. IEEE (2011)","DOI":"10.1109\/ICIP.2011.6115851"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Zhan, C., et al.: Debiasing medical visual question answering via counterfactual training. In: Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 382\u2013393. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_36"},{"key":"36_CR23","unstructured":"Zhu, H., Liu, Y., Zhou, C., Lu, G., Chen, B.: Cause-effect driven optimization for robust medical visual question answering with language biases. arXiv preprint arXiv:2506.17903 (2025)"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, J., et al.: Combating visual question answering hallucinations via robust multi-space co-debias learning. In: Proceedings of the ACM International Conference on Multimedia (MM), pp. 955\u2013964 (2024)","DOI":"10.1145\/3664647.3681663"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05185-1_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:46:45Z","timestamp":1758325605000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05185-1_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051844","9783032051851"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05185-1_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are 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":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}