{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T09:51:10Z","timestamp":1781517070892,"version":"3.54.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049803","type":"print"},{"value":"9783032049810","type":"electronic"}],"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\/978-3-032-04981-0_63","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:12:41Z","timestamp":1758258761000},"page":"669-679","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unleashing the\u00a0Power of\u00a0LLMs for\u00a0Medical Video Answer Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5573-6195","authenticated-orcid":false,"given":"Junbin","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6784-1627","authenticated-orcid":false,"given":"Liang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"63_CR1","unstructured":"Diwan, A., Peng, P., Mooney, R.: Zero-shot video moment retrieval with off-the-shelf models. In: Transfer Learning for Natural Language Processing Workshop, pp. 10\u201321. PMLR (2023)"},{"key":"63_CR2","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: VideoAgent: a memory-augmented multimodal agent for video understanding. In: European Conference on Computer Vision, pp. 75\u201392. Springer (2024)","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"63_CR3","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: Temporal activity localization via language query. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"issue":"1","key":"63_CR4","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41597-023-02036-y","volume":"10","author":"D Gupta","year":"2023","unstructured":"Gupta, D., Attal, K., Demner-Fushman, D.: A dataset for medical instructional video classification and question answering. Sci. Data 10(1), 158 (2023)","journal-title":"Sci. Data"},{"key":"63_CR5","doi-asserted-by":"crossref","unstructured":"Gupta, D., Demner-Fushman, D.: Overview of the MedVidQA 2022 shared task on medical video question-answering. In: Proceedings of the 21st Workshop on Biomedical Language Processing, pp. 264\u2013274 (2022)","DOI":"10.18653\/v1\/2022.bionlp-1.25"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Jung, M., Xiao, J., Zhang, B.T., Yao, A.: On the consistency of video large language models in temporal comprehension. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13713\u201313722 (2025)","DOI":"10.1109\/CVPR52734.2025.01280"},{"key":"63_CR7","first-page":"11846","volume":"34","author":"J Lei","year":"2021","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. Adv. Neural. Inf. Process. Syst. 34, 11846\u201311858 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"63_CR8","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"63_CR9","doi-asserted-by":"crossref","unstructured":"Li, S., Li, B., Sun, B., Weng, Y.: Towards visual-prompt temporal answer grounding in instructional video. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201318 (2024)","DOI":"10.36227\/techrxiv.22182736"},{"key":"63_CR10","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLaVA: learning united visual representation by alignment before projection. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 5971\u20135984 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"63_CR11","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., et al.: UniVTG: towards unified video-language temporal grounding. In: IEEE\/CVF International Conference on Computer Vision, pp. 2794\u20132804 (2023)","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"63_CR12","doi-asserted-by":"crossref","unstructured":"Luo, D., Huang, J., Gong, S., Jin, H., Liu, Y.: Zero-shot video moment retrieval from frozen vision-language models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5464\u20135473 (2024)","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"63_CR13","unstructured":"Meinardus, B., Batra, A., Rohrbach, A., Rohrbach, M.: The surprising effectiveness of multimodal large language models for video moment retrieval. arXiv preprint arXiv:2406.18113 (2024)"},{"key":"63_CR14","doi-asserted-by":"crossref","unstructured":"Qin, H., Xiao, J., Yao, A.: Question-answering dense video events. arXiv preprint arXiv:2409.04388 (2024)","DOI":"10.1145\/3726302.3729945"},{"key":"63_CR15","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"63_CR16","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"63_CR17","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"63_CR18","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: TimeChat: a time-sensitive multimodal large language model for long video understanding. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14313\u201314323 (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"63_CR19","doi-asserted-by":"crossref","unstructured":"Shi, Y., et al.: EMScore: evaluating video captioning via coarse-grained and fine-grained embedding matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17929\u201317938 (2022)","DOI":"10.1109\/CVPR52688.2022.01740"},{"key":"63_CR20","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: COIN: a large-scale dataset for comprehensive instructional video analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1207\u20131216 (2019)","DOI":"10.1109\/CVPR.2019.00130"},{"key":"63_CR21","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"63_CR22","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, Y., Zohar, O., Yeung-Levy, S.: VideoAgent: long-form video understanding with large language model as agent. In: European Conference on Computer Vision, pp. 58\u201376. Springer (2024)","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"63_CR23","doi-asserted-by":"crossref","unstructured":"Wattasseril, J.I., Shekhar, S., D\u00f6llner, J., Trapp, M.: Zero-shot video moment retrieval using blip-based models. In: International Symposium on Visual Computing, pp. 160\u2013171. Springer (2023)","DOI":"10.1007\/978-3-031-47969-4_13"},{"key":"63_CR24","doi-asserted-by":"crossref","unstructured":"Xiao, J., et\u00a0al.: VideoQA in the era of LLMs: an empirical study. Int. J. Comput. Vision 3970\u20133993 (2025)","DOI":"10.1007\/s11263-025-02385-8"},{"key":"63_CR25","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Li, Y., Chua, T.S.: Can i trust your answer? Visually grounded video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13204\u201313214 (2024)","DOI":"10.1109\/CVPR52733.2024.01254"},{"issue":"5","key":"63_CR26","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.3390\/app14051894","volume":"14","author":"Y Xu","year":"2024","unstructured":"Xu, Y., Sun, Y., Xie, Z., Zhai, B., Du, S.: VTG-GPT: tuning-free zero-shot video temporal grounding with GPT. Appl. Sci. 14(5), 1894 (2024)","journal-title":"Appl. Sci."},{"key":"63_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Zero-shot video moment retrieval via off-the-shelf multimodal large language models. arXiv preprint arXiv:2501.07972 (2025)","DOI":"10.1609\/aaai.v39i9.32971"},{"key":"63_CR28","unstructured":"Zeng, A., et\u00a0al.: Socratic models: composing zero-shot multimodal reasoning with language. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"63_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: A simple LLM framework for long-range video question-answering. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 21715\u201321737 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"63_CR30","doi-asserted-by":"crossref","unstructured":"Zheng, M., Cai, X., Chen, Q., Peng, Y., Liu, Y.: Training-free video temporal grounding using large-scale pre-trained models. In: European Conference on Computer Vision, pp. 20\u201337. Springer (2024)","DOI":"10.1007\/978-3-031-73007-8_2"}],"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\/978-3-032-04981-0_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:33:51Z","timestamp":1767418431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04981-0_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049803","9783032049810"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04981-0_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}