{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T09:53:36Z","timestamp":1781430816521,"version":"3.54.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T00:00:00Z","timestamp":1781395200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T00:00:00Z","timestamp":1781395200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101088553"],"award-info":[{"award-number":["101088553"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"DOI":"10.1007\/s11548-026-03722-z","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T09:20:37Z","timestamp":1781428837000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Surg-NAT+: negation-aware vision\u2013language refinement for fine-grained surgical understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6030-8862","authenticated-orcid":false,"given":"Kun","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxi","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,14]]},"reference":[{"key":"3722_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103644","author":"K Yuan","year":"2025","unstructured":"Yuan K, Srivastav V, Yu T, Lavanchy JL, Marescaux J, Mascagni P, Navab N, Padoy N (2025) Learning multi-modal representations by watching hundreds of surgical video lectures. Med Image Anal. https:\/\/doi.org\/10.1016\/j.media.2025.103644","journal-title":"Med Image Anal"},{"key":"3722_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_29","author":"K Yuan","year":"2024","unstructured":"Yuan K, Srivastav V, Navab N, Padoy N (2024) Hecvl: hierarchical video-language pretraining for zero-shot surgical phase recognition. Int Conf Med Image Comput Comput-Assist Interv. https:\/\/doi.org\/10.1007\/978-3-031-72089-5_29","journal-title":"Int Conf Med Image Comput Comput-Assist Interv"},{"key":"3722_CR3","doi-asserted-by":"publisher","first-page":"122952","DOI":"10.52202\/079017-3907","volume":"37","author":"K Yuan","year":"2024","unstructured":"Yuan K, Vinkle S, Navab N, Padoy N (2024) Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation. Adv Neural Inf Process Syst 37:122952\u2013122983. https:\/\/doi.org\/10.52202\/079017-3907","journal-title":"Adv Neural Inf Process Syst"},{"key":"3722_CR4","doi-asserted-by":"publisher","unstructured":"L\u00fclf C, Lima M, Denis M, Vaz S, Marcos A, Zhou Y, Gieseke F (2024) CLIP-branches: interactive fine-tuning for text-image retrieval. Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval 2719\u20132723 . https:\/\/doi.org\/10.1145\/3626772.3657678","DOI":"10.1145\/3626772.3657678"},{"key":"3722_CR5","doi-asserted-by":"publisher","unstructured":"Tao M, Bao B-K, Tang H, Xu C (2023) Galip: generative adversarial clips for text-to-image synthesis. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) 14214\u201314223. https:\/\/doi.org\/10.1109\/cvpr52729.2023.01366","DOI":"10.1109\/cvpr52729.2023.01366"},{"key":"3722_CR6","doi-asserted-by":"publisher","unstructured":"Barraco M, Cornia M, Cascianelli S, Baraldi L, Cucchiara R (2022) The unreasonable effectiveness of clip features for image captioning: an experimental analysis. proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 4662\u20134670 . https:\/\/doi.org\/10.1109\/cvprw56347.2022.00512","DOI":"10.1109\/cvprw56347.2022.00512"},{"key":"3722_CR7","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/tmi.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda AP, Shehata S, Mutter D, Marescaux J, De Mathelin M, Padoy N (2016) Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imaging 36:86\u201397. https:\/\/doi.org\/10.1109\/tmi.2016.2593957","journal-title":"IEEE Trans Med Imaging"},{"key":"3722_CR8","doi-asserted-by":"publisher","first-page":"11709","DOI":"10.3390\/app132111709","volume":"13","author":"K Jiang","year":"2023","unstructured":"Jiang K, Pan S, Yang L, Yu J, Lin Y, Wang H (2023) Surgical instrument recognition based on improved YOLOv5. Appl Sci 13:11709. https:\/\/doi.org\/10.3390\/app132111709","journal-title":"Appl Sci"},{"key":"3722_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433","volume":"78","author":"CI Nwoye","year":"2022","unstructured":"Nwoye CI, Yu T, Gonzalez C, Seeliger B, Mascagni P, Mutter D, Marescaux J, Padoy N (2022) Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med Image Anal 78:102433. https:\/\/doi.org\/10.1016\/j.media.2022.102433","journal-title":"Med Image Anal"},{"key":"3722_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_52","author":"F Shakeri","year":"2024","unstructured":"Shakeri F, Huang Y, Silva-Rodr\u00edguez J, Bahig H, Tang A, Dolz J, Ben Ayed I (2024) Few-shot adaptation of medical vision-language models. Int Conf Med Image Comput Comput-Assist Interv. https:\/\/doi.org\/10.1007\/978-3-031-72390-2_52","journal-title":"Int Conf Med Image Comput Comput-Assist Interv"},{"key":"3722_CR11","doi-asserted-by":"publisher","unstructured":"Zanella M, Ben Ayed I (2024) Low-rank few-shot adaptation of vision-language models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 1593\u20131603. https:\/\/doi.org\/10.1109\/cvprw63382.2024.00166","DOI":"10.1109\/cvprw63382.2024.00166"},{"key":"3722_CR12","doi-asserted-by":"publisher","unstructured":"Wang M, Xing J, Mei J, Liu Y, Jiang Y (2023) Actionclip: adapting language-image pretrained models for video action recognition. IEEE transactions on neural networks and learning systems. https:\/\/doi.org\/10.1109\/tnnls.2023.3331841","DOI":"10.1109\/tnnls.2023.3331841"},{"key":"3722_CR13","doi-asserted-by":"publisher","first-page":"27896","DOI":"10.52202\/079017-0875","volume":"37","author":"D Jing","year":"2024","unstructured":"Jing D, He X, Luo Y, Fei N, Yang G, Wei W, Zhao H, Lu Z (2024) Fineclip: self-distilled region-based clip for better fine-grained understanding. Adv Neural Inf Process Syst 37:27896\u201327918. https:\/\/doi.org\/10.52202\/079017-0875","journal-title":"Adv Neural Inf Process Syst"},{"key":"3722_CR14","doi-asserted-by":"publisher","unstructured":"Li S, Liu F, Hao Z, Wang X, Li L, Liu X, Chen P, Ma W (2025) Logits deconfusion with CLIP for few-shot learning. Proceedings of the computer vision and pattern recognition conference 25411\u201325421 . https:\/\/doi.org\/10.1109\/cvpr52734.2025.02366","DOI":"10.1109\/cvpr52734.2025.02366"},{"key":"3722_CR15","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit 770\u2013778. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"3722_CR16","unstructured":"Jacob D, Ming-Wei C, Kenton L, Kristina T (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of naacL-HLT1 https:\/\/aclanthology.org\/N19-1423\/"},{"key":"3722_CR17","unstructured":"Alec R, Jong-Wook K, Chris H, Aditya R, Gabriel G, Sandhini A, Girish S, Amanda A, Pamela M, Jack C, Gretchen K, Ilya S (2021) Learning transferable visual models from natural language supervision. International conference on machine learning 8748\u20138763 . https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"3722_CR18","doi-asserted-by":"publisher","unstructured":"Huang Y, Shakeri F, Dolz J, Boudiaf M, Bahig H, Ben Ayed I (2024) Lp++: a surprisingly strong linear probe for few-shot CLIP. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 23773\u201323782. https:\/\/doi.org\/10.1109\/cvpr52733.2024.02244","DOI":"10.1109\/cvpr52733.2024.02244"},{"key":"3722_CR19","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao P, Geng S, Zhang R, Ma T, Fang R, Zhang Y, Li H, Qiao Y (2024) Clip-adapter: Better vision-language models with feature adapters. Int J Comput Vision 132:581\u2013595. https:\/\/doi.org\/10.1007\/s11263-023-01891-x","journal-title":"Int J Comput Vision"},{"key":"3722_CR20","doi-asserted-by":"publisher","unstructured":"Zhang R, Zhang W, Fang R, Gao P, Li K, Dai J, Qiao Y, Li H (2022) Tip-adapter: training-free adaption of CLIP for few-shot classification. European conference on computer vision 493\u2013510. https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"3722_CR21","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou K, Yang J, Loy CC, Liu Z (2022) Learning to prompt for vision-language models. Int J Comput Vision 130:2337\u20132348. https:\/\/doi.org\/10.1007\/s11263-022-01653-1","journal-title":"Int J Comput Vision"},{"key":"3722_CR22","doi-asserted-by":"publisher","unstructured":"Zhou K, Yang J, Loy CC, Liu Z (2022) Conditional prompt learning for vision-language models. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 16816\u201316825. https:\/\/doi.org\/10.1109\/cvpr52688.2022.01631","DOI":"10.1109\/cvpr52688.2022.01631"},{"key":"3722_CR23","doi-asserted-by":"publisher","first-page":"2491","DOI":"10.1109\/TPAMI.2023.3346405","volume":"46","author":"X Sun","year":"2024","unstructured":"Sun X, Hu P, Saenko K (2024) Dualcoop++: fast and effective adaptation to multi-label recognition with limited annotations. IEEE Trans Pattern Anal Mach Intell(TPAMI) 46:2491\u20132507. https:\/\/doi.org\/10.1109\/TPAMI.2023.3346405","journal-title":"IEEE Trans Pattern Anal Mach Intell(TPAMI)"},{"key":"3722_CR24","doi-asserted-by":"publisher","unstructured":"Britty B, Vinkle S, Pooja PJ, Kun Y, Pietro M, Nicolas P (2025) Multi-modal representations for fine-grained multi-label critical view of safety recognition. International conference on medical image computing and computer-assisted intervention 423\u2013432. https:\/\/doi.org\/10.1007\/978-3-032-05141-7_41","DOI":"10.1007\/978-3-032-05141-7_41"},{"key":"3722_CR25","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/TMI.2023.3333034","volume":"43","author":"M Aditya","year":"2024","unstructured":"Aditya M, Deepak A, Pietro M, Armine V, Alain G, Nariaki O, Didier M, Nicolas P (2024) Latent graph representations for critical view of safety assessment. IEEE Trans Med Imaging 43:1247\u20131258. https:\/\/doi.org\/10.1109\/TMI.2023.3333034","journal-title":"IEEE Trans Med Imaging"},{"key":"3722_CR26","doi-asserted-by":"publisher","unstructured":"Huang Y, Bai L, Cui B, Yuan K, Wang G, Hoque MI, Padoy N, Navab N, Ren H (2025) SurgTPGS: semantic 3D surgical scene understanding with text promptable gaussian splatting. International conference on medical image computing and computer-assisted intervention 584\u2013594. https:\/\/doi.org\/10.1007\/978-3-032-05114-1_56","DOI":"10.1007\/978-3-032-05114-1_56"},{"key":"3722_CR27","doi-asserted-by":"publisher","unstructured":"Madani A, Namazi B, Altieri MS, Hashimoto DA, Rivera AM, Pucher PH, Navarrete-Welton A, Sankaranarayanan G, Brunt LM, Okrainec A, Alseidi A (2022) Artificial intelligence for intraoperative guidance: using semantic segmentation to identify surgical anatomy during laparoscopic cholecystectomy. Ann Surg 276:363\u2013369. https:\/\/doi.org\/10.1097\/SLA.0000000000004594","DOI":"10.1097\/SLA.0000000000004594"},{"key":"3722_CR28","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s11548-025-03341-0","volume":"20","author":"T Chen","year":"2025","unstructured":"Chen T, Kun Y, Vinkle S, Nassir N, Padoy N (2025) Text-driven adaptation of foundation models for few-shot surgical workflow analysis. Int J Comput Assist Radiol Surg 20:1175\u20131183. https:\/\/doi.org\/10.1007\/s11548-025-03341-0","journal-title":"Int J Comput Assist Radiol Surg"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03722-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03722-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03722-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T09:20:38Z","timestamp":1781428838000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03722-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,14]]},"references-count":28,"alternative-id":["3722"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03722-z","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,14]]},"assertion":[{"value":"20 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study does not involve human participants or animal studies requiring ethical approval.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors consent to the publication of this article in IJCARS.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This study uses publicly available datasets that do not contain personally identifiable information.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}