{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T18:04:16Z","timestamp":1771005856945,"version":"3.50.1"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032176103","type":"print"},{"value":"9783032176110","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-17611-0_14","type":"book-chapter","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:13:20Z","timestamp":1771002800000},"page":"137-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MATEX: Multi-scale Attention and\u00a0Text-Guided Explainability of\u00a0Medical Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Muhammad","family":"Imran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yugyung","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,14]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4190\u20134197 (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"14_CR2","unstructured":"Boecking, B., et al.: Making the most of text semantics to improve biomedical vision-language processing. In: Computer Vision\u2013ECCV 2022: 17th European Conference, pp. 387\u2013405 (2022)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"14_CR5","unstructured":"Ma, Y., Bertsimas, D.: M3H: multimodal multitask machine learning for healthcare. In: Advancements in Medical Foundation Models Workshop, NeurIPS (2024)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: a multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of ICCV, pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"14_CR7","unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, pp. 4765\u20134774 (2017)"},{"key":"14_CR8","unstructured":"Petsiuk, V., Das, A., Saenko, K.: Rise: randomized input sampling for explanation of black-box models. In: British Machine Vision Conference (2018)"},{"key":"14_CR9","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Intern. Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D., et al.: Grad-cam: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336\u2013359 (2020)","DOI":"10.1007\/s11263-019-01228-7"},{"key":"14_CR12","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)"},{"key":"14_CR13","unstructured":"Simonyan, K., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: International Conference on Learning Representations (2014)"},{"key":"14_CR14","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning, volume\u00a070 of PMLR, pp. 3319\u20133328 (2017)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Mai, S., Zeng, Y., Hu, H.: Multimodal information bottleneck: learning minimal sufficient unimodal and multimodal representations. IEEE Trans. Multimedia 25, 4121\u20134134 (2023)","DOI":"10.1109\/TMM.2022.3171679"},{"key":"14_CR16","unstructured":"Baniecki, H., Biecek, P., Arnaiz-Gonz\u00e1lez, \u00c1., et al.: Towards evaluating explanations of vision transformers for medical imaging. In: MICCAI (2023)"},{"key":"14_CR17","unstructured":"Zhao, J., Rodriguez, M., Chen, Y.: Gradient-based visual explanations in medical transformer networks. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 12745\u201312754 (2024)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Huang, L., Zhou, T., Fu, H., Shao, L.: Visual-textual attentive semantic consistency for medical report generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3985\u20133994 (2021)","DOI":"10.1109\/ICCV48922.2021.00395"}],"container-title":["Lecture Notes in Computer Science","Interpretability of Machine Intelligence in Medical Image Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-17611-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:13:31Z","timestamp":1771002811000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-17611-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032176103","9783032176110"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-17611-0_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"iMIMIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Interpretability of Machine Intelligence in Medical Image Computing","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":"27 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":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"imimic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/imimic-workshop.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}