{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:06:06Z","timestamp":1790283966418,"version":"4.1.0"},"publisher-location":"Cham","reference-count":23,"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_55","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T20:56:37Z","timestamp":1790283397000},"page":"583-592","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SurgZSD: Zero-Shot Surgical Action Triplet Detection via\u00a0Attribute Composition and\u00a0Clinical Feasibility Inference"],"prefix":"10.1007","author":[{"given":"Zuxing","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"55_CR1","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Ren, H.: CAT-ViL: co-attention gated vision-language embedding for visual question localized-answering in robotic surgery. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 397\u2013407. Springer (2023)","DOI":"10.1007\/978-3-031-43996-4_38"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Seenivasan, L., Ren, H.: Surgical-VQLA: transformer with gated vision-language embedding for visual question localized-answering in robotic surgery. arXiv preprint arXiv:2305.11692 (2023)","DOI":"10.1109\/ICRA48891.2023.10160403"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Carstens, M., et al.: Artificial intelligence for surgical scene understanding: a systematic review and reporting quality meta-analysis. NPJ Digit. Med. (2025)","DOI":"10.1101\/2025.07.12.25330122"},{"key":"55_CR4","unstructured":"Chen, Y., et al.: ProstaTD: bridging surgical triplet from classification to fully supervised detection. arXiv preprint arXiv:2506.01130 (2025)"},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Hao, P., Wang, H., Yang, G., Zhu, L.: Enhancing visual reasoning with LLM-powered knowledge graphs for visual question localized-answering in robotic surgery. IEEE J. Biomed. Health Inform. (2025)","DOI":"10.1109\/JBHI.2025.3538324"},{"issue":"1","key":"55_CR6","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1002\/ags3.12513","volume":"6","author":"D Kitaguchi","year":"2022","unstructured":"Kitaguchi, D., Takeshita, N., Hasegawa, H., Ito, M.: Artificial intelligence-based computer vision in surgery: recent advances and future perspectives. Ann. Gastroenterol. Surg. 6(1), 29\u201336 (2022)","journal-title":"Ann. Gastroenterol. Surg."},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"55_CR8","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Open world compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5222\u20135230 (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"55_CR9","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":"55_CR10","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., Elgohary, K., Srinivas, A., Zaid, F., Lavanchy, J.L., Padoy, N.: CholecTrack20: a multi-perspective tracking dataset for surgical tools. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8942\u20138952 (2025)","DOI":"10.1109\/CVPR52734.2025.00836"},{"key":"55_CR11","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med. Image Anal. 78, 102433 (2022)","DOI":"10.1016\/j.media.2022.102433"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: CholecTriplet 2022: show me a tool and tell me the triplet\u2013an endoscopic vision challenge for surgical action triplet detection. Med. Image Anal. 89, 102888 (2023)","DOI":"10.1016\/j.media.2023.102888"},{"key":"55_CR13","doi-asserted-by":"crossref","unstructured":"Pei, J., Zhang, J., Qin, G., Wang, K., Jin, Y., Heng, P.A.: Instrument-tissue-guided surgical action triplet detection via textual-temporal trail exploration. IEEE Trans. Med. Imaging (2025)","DOI":"10.1109\/TMI.2025.3590457"},{"key":"55_CR14","unstructured":"Poudel, N., Simon, R., Linte, C.A.: Evaluating large vision-language models for surgical tool detection. arXiv preprint arXiv:2601.16895 (2026)"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Qu, Y., Li, L., Li, T., Zheng, J., Tang, W., Li, X.: Smart surgical telementoring system with patch-to-pixel point tracking method. EngMedicine 2(1), 100058 (2025)","DOI":"10.1016\/j.engmed.2025.100058"},{"key":"55_CR16","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"55_CR17","unstructured":"Sharma, S., Mutter, D., Padoy, N.: fine-CLIP: enhancing zero-shot fine-grained surgical action recognition with vision-language models. arXiv preprint arXiv:2503.19670 (2025)"},{"key":"55_CR18","doi-asserted-by":"crossref","unstructured":"Sharma, S., Nwoye, C.I., Mutter, D., Padoy, N.: Surgical action triplet detection by mixed supervised learning of instrument-tissue interactions. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 505\u2013514. Springer (2023)","DOI":"10.1007\/978-3-031-43996-4_48"},{"key":"55_CR19","unstructured":"Su, Z., Guo, J., Yang, X., Wang, Q., Coenen, F., Huang, K.: Navigating distribution shifts in medical image analysis: a survey. arXiv preprint arXiv:2411.05824 (2024)"},{"key":"55_CR20","unstructured":"Williams, S.C., et\u00a0al.: Artificial intelligence assisted surgical scene recognition: a comparative study amongst healthcare professionals. Ann. Surg. 10\u20131097 (2024)"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Williamson, T., Song, S.E.: Robotic surgery techniques to improve traditional laparoscopy. JSLS: J. Soc. Laparosc. Robot. Surg. 26(2), e2022\u201300002 (2022)","DOI":"10.4293\/JSLS.2022.00002"},{"key":"55_CR22","doi-asserted-by":"crossref","unstructured":"Yuan, K., et al.: Learning multi-modal representations by watching hundreds of surgical video lectures. Med. Image Anal. 103644 (2025)","DOI":"10.1016\/j.media.2025.103644"},{"issue":"5","key":"55_CR23","doi-asserted-by":"publisher","first-page":"2218","DOI":"10.1109\/TMI.2025.3529294","volume":"44","author":"J Zhang","year":"2025","unstructured":"Zhang, J., Zhou, S., Wang, Y., Zhao, H., Ding, H.: Knowledge-driven framework for anatomical landmark annotation in laparoscopic surgery. IEEE Trans. Med. Imaging 44(5), 2218\u20132229 (2025)","journal-title":"IEEE Trans. Med. Imaging"}],"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_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T20:56:41Z","timestamp":1790283401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38233-7_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032382320","9783032382337"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38233-7_55","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 declare no competing interests.","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"}}]}}