{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:05:25Z","timestamp":1790283925901,"version":"4.1.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032382320","type":"print"},{"value":"9783032382337","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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\/978-3-032-38233-7_54","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T20:57:49Z","timestamp":1790283469000},"page":"573-582","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary"],"prefix":"10.1007","author":[{"given":"Jingyi","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"54_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"54_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"54_CR3","doi-asserted-by":"crossref","unstructured":"Bain, M., Huh, J., Han, T., Zisserman, A.: WhisperX: time-accurate speech transcription of long-form audio. arXiv preprint arXiv:2303.00747 (2023)","DOI":"10.21437\/Interspeech.2023-78"},{"key":"54_CR4","unstructured":"Bi, Y., Zhou, Y., Liu, P., Li, F., Jiang, Z., Navab, N.: From scanning guidelines to action: a robotic ultrasound agent with LLM-based reasoning. arXiv preprint arXiv:2603.14393 (2026)"},{"key":"54_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: VideoLLM-online: online video large language model for streaming video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18407\u201318418 (2024)","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"54_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Zeng, Z., Lin, Y., Li, W., Ma, Z., Shou, M.Z.: LiveCC: learning video LLM with streaming speech transcription at scale. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29083\u201329095 (2025)","DOI":"10.1109\/CVPR52734.2025.02708"},{"key":"54_CR7","unstructured":"Jiang, S., et\u00a0al.: Hulu-med: a transparent generalist model towards holistic medical vision-language understanding. arXiv preprint arXiv:2510.08668 (2025)"},{"key":"54_CR8","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, W., Cao, X., Yuan, L.: Chat-UniVi: unified visual representation empowers large language models with image and video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13700\u201313710 (2024)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"54_CR9","doi-asserted-by":"crossref","unstructured":"Kim, J.W., et\u00a0al.: SRT-H: a hierarchical framework for autonomous surgery via language-conditioned imitation learning. Sci. Robot. 10(104), eadt5254 (2025)","DOI":"10.1126\/scirobotics.adt5254"},{"key":"54_CR10","doi-asserted-by":"crossref","unstructured":"Lavanchy, J.L., et al.: Challenges in multi-centric generalization: phase and step recognition in roux-en-y gastric bypass surgery. Int. J. Comput. Assist. Radiol. Surg. (2024)","DOI":"10.1007\/s11548-024-03166-3"},{"key":"54_CR11","unstructured":"Li, J., et al.: LLaVA-surg: towards multimodal surgical assistant via structured surgical video learning. arXiv preprint arXiv:2408.07981 (2024)"},{"key":"54_CR12","unstructured":"Li, J., Liu, C., Bai, W., Arcucci, R., Bercea, C.I., Schnabel, J.A.: Enhancing abnormality grounding for vision language models with knowledge descriptions. arXiv preprint arXiv:2503.03278 (2025)"},{"key":"54_CR13","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":"54_CR14","doi-asserted-by":"publisher","unstructured":"Long, Y., et al.: Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery. Sci. Robot. 10(104), eadt3093 (2025). https:\/\/doi.org\/10.1126\/scirobotics.adt3093","DOI":"10.1126\/scirobotics.adt3093"},{"key":"54_CR15","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: Video-chatGPT: towards detailed video understanding via large vision and language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12585\u201312602 (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"54_CR16","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: CholecTriplet 2021: a benchmark challenge for surgical action triplet recognition. Med. Image Anal. 86, 102803 (2023)","DOI":"10.1016\/j.media.2023.102803"},{"key":"54_CR17","unstructured":"Rojas-Mu\u00f1oz, E., Couperus, K., Wachs, J.: DAISI: Database for ai surgical instruction (2020). https:\/\/arxiv.org\/abs\/2004.02809"},{"key":"54_CR18","doi-asserted-by":"publisher","unstructured":"Twinanda, A., Shehata, S., Mutter, D., Marescaux, J., Mathelin, M.D., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36 (02 2016).https:\/\/doi.org\/10.1109\/TMI.2016.2593957","DOI":"10.1109\/TMI.2016.2593957"},{"key":"54_CR19","unstructured":"Wang, G., et\u00a0al.: SurgVidLM: towards multi-grained surgical video understanding with large language model. arXiv preprint arXiv:2506.17873 (2025)"},{"key":"54_CR20","doi-asserted-by":"crossref","unstructured":"Wang, T.D., Bastian, L., Czempiel, T., Heiliger, C., Navab, N.: Beyond role-based surgical domain modeling: generalizable re-identification in the operating room. Med. Image Anal. 105, 103687 (2025)","DOI":"10.1016\/j.media.2025.103687"},{"key":"54_CR21","doi-asserted-by":"crossref","unstructured":"Wei, M., et al.: Where it moves, it matters: referring surgical instrument segmentation via motion. arXiv preprint arXiv:2601.12224 (2026)","DOI":"10.1609\/aaai.v40i13.38027"},{"key":"54_CR22","unstructured":"Xu, R., Xiao, G., Chen, Y., He, L., Peng, K., Lu, Y., Han, S.: Streamingvlm: Real-time understanding for infinite video streams. arXiv preprint arXiv:2510.09608 (2025)"},{"key":"54_CR23","doi-asserted-by":"publisher","first-page":"122952","DOI":"10.52202\/079017-3907","volume":"37","author":"K Yuan","year":"2024","unstructured":"Yuan, K., Navab, N., Padoy, N., et al.: Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation. Adv. Neural. Inf. Process. Syst. 37, 122952\u2013122983 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"54_CR24","doi-asserted-by":"crossref","unstructured":"Yuan, K., Srivastav, V., Navab, N., Padoy, N.: HecVL: hierarchical video-language pretraining for zero-shot surgical phase recognition. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 306\u2013316. Springer (2024)","DOI":"10.1007\/978-3-031-72089-5_29"},{"key":"54_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Bi, Y., Tong, W., Wang, W., Navab, N., Jiang, Z.: UltraAD: fine-grained ultrasound anomaly classification via few-shot clip adaptation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 625\u2013635. Springer (2025)","DOI":"10.1007\/978-3-032-04971-1_59"},{"key":"54_CR26","unstructured":"Zhou, Y., et al.: Look-closer-then-diagnose: confidence-aware ultrasound VQA via active zooming. arXiv preprint arXiv:2605.21652 (2026)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38233-7_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T20:57:53Z","timestamp":1790283473000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38233-7_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032382320","9783032382337"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38233-7_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"25 September 2026","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","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}