{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:54:27Z","timestamp":1781589267900,"version":"3.54.5"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:00:00Z","timestamp":1770163200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"name":"Research Grants Council of Hong Kong","award":["No. G-HKUST605\/24"],"award-info":[{"award-number":["No. G-HKUST605\/24"]}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007156","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","award":["No. GHP\/006\/22GD and ITCPD\/17-9"],"award-info":[{"award-number":["No. GHP\/006\/22GD and ITCPD\/17-9"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02403-0","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:24:24Z","timestamp":1770193464000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Large-scale self-supervised video foundation model for intelligent surgery"],"prefix":"10.1038","volume":"9","author":[{"given":"Shu","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengtao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leon","family":"Mayer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuxiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00d6mer","family":"S\u00fcmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuchang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex Qinyang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy YuenChun","family":"Teoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lena","family":"Maier-Hein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"key":"2403_CR1","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1038\/s41551-023-01010-8","volume":"7","author":"D Kiyasseh","year":"2023","unstructured":"Kiyasseh, D. et al. A vision transformer for decoding surgeon activity from surgical videos. Nat. Biomed. Eng. 7, 780\u2013796 (2023).","journal-title":"Nat. Biomed. Eng."},{"key":"2403_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00738-y","volume":"5","author":"R Ma","year":"2022","unstructured":"Ma, R. et al. Surgical gestures as a method to quantify surgical performance and predict patient outcomes. NPJ Digit. Med. 5, 187 (2022).","journal-title":"NPJ Digit. Med."},{"key":"2403_CR3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00766-2","volume":"6","author":"D Kiyasseh","year":"2023","unstructured":"Kiyasseh, D. et al. Human visual explanations mitigate bias in AI-based assessment of surgeon skills. NPJ Digit. Med. 6, 54 (2023).","journal-title":"NPJ Digit. Med."},{"key":"2403_CR4","doi-asserted-by":"publisher","first-page":"5405","DOI":"10.1109\/JBHI.2023.3311628","volume":"27","author":"KC Demir","year":"2023","unstructured":"Demir, K. C. et al. Deep learning in surgical workflow analysis: a review of phase and step recognition. IEEE J. Biomed. Health Inform. 27, 5405\u20135417 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2403_CR5","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/s41551-017-0132-7","volume":"1","author":"L Maier-Hein","year":"2017","unstructured":"Maier-Hein, L. et al. Surgical data science for next-generation interventions. Nat. Biomed. Eng. 1, 691\u2013696 (2017).","journal-title":"Nat. Biomed. Eng."},{"key":"2403_CR6","unstructured":"Surgical Data Science Initiative. Surgical data science. http:\/\/www.surgical-data-science.org\/ (2025)."},{"key":"2403_CR7","doi-asserted-by":"publisher","first-page":"102306","DOI":"10.1016\/j.media.2021.102306","volume":"76","author":"L Maier-Hein","year":"2022","unstructured":"Maier-Hein, L. et al. Surgical data science\u2013from concepts toward clinical translation. Med. image Anal. 76, 102306 (2022).","journal-title":"Med. image Anal."},{"key":"2403_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M. et al. Emerging properties in self-supervised vision transformers. in Proc. IEEE\/CVF International Conference on Computer Vision, 9650\u20139660 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2403_CR9","doi-asserted-by":"crossref","unstructured":"He, K. et al. Masked autoencoders are scalable vision learners. in Proc. IEEE\/CVF Conference On Computer Vision And Pattern Recognition, 16000\u201316009 (IEEE, 2022).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2403_CR10","unstructured":"Oquab, M. et al. Dinov2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024)."},{"key":"2403_CR11","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1038\/s41551-023-01049-7","volume":"7","author":"S Azizi","year":"2023","unstructured":"Azizi, S. et al. Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging. Nat. Biomed. Eng. 7, 756\u2013779 (2023).","journal-title":"Nat. Biomed. Eng."},{"key":"2403_CR12","doi-asserted-by":"publisher","unstructured":"Ma, J. et al. A generalizable pathology foundation model using a unified knowledge distillation pretraining framework. Nat. Biomed. Eng. https:\/\/doi.org\/10.1038\/s41551-025-01488-4 (2025).","DOI":"10.1038\/s41551-025-01488-4"},{"key":"2403_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00811-0","volume":"6","author":"S-C Huang","year":"2023","unstructured":"Huang, S.-C. et al. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digit. Med. 6, 74 (2023).","journal-title":"NPJ Digit. Med."},{"key":"2403_CR14","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1038\/s41551-022-00914-1","volume":"6","author":"R Krishnan","year":"2022","unstructured":"Krishnan, R., Rajpurkar, P. & Topol, E. J. Self-supervised learning in medicine and healthcare. Nat. Biomed. Eng. 6, 1346\u20131352 (2022).","journal-title":"Nat. Biomed. Eng."},{"key":"2403_CR15","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","volume":"30","author":"RJ Chen","year":"2024","unstructured":"Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850\u2013862 (2024).","journal-title":"Nat. Med."},{"key":"2403_CR16","doi-asserted-by":"publisher","first-page":"102844","DOI":"10.1016\/j.media.2023.102844","volume":"88","author":"S Ramesh","year":"2023","unstructured":"Ramesh, S. et al. Dissecting self-supervised learning methods for surgical computer vision. Med. Image Anal. 88, 102844 (2023).","journal-title":"Med. Image Anal."},{"key":"2403_CR17","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1007\/s11548-024-03091-5","volume":"19","author":"D Bati\u0107","year":"2024","unstructured":"Bati\u0107, D., Holm, F., \u00d6zsoy, E., Czempiel, T. & Navab, N. Endovit: pretraining vision transformers on a large collection of endoscopic images. Int. J. Comput. Assist. Radiol. Surg. 19, 1085\u20131091 (2024).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"2403_CR18","doi-asserted-by":"crossref","unstructured":"Hirsch, R. et al. Self-supervised learning for endoscopic video analysis. in Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention, 569\u2013578 (Springer, 2023).","DOI":"10.1007\/978-3-031-43904-9_55"},{"key":"2403_CR19","unstructured":"Schmidgall, S., Kim, J. W., Jopling, J. & Krieger, A. General surgery vision transformer: a video pre-trained foundation model for general surgery. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/2403.05949 (2024)."},{"key":"2403_CR20","doi-asserted-by":"crossref","unstructured":"Czempiel, T. et al. Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In Proc. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23, 343\u2013352 (Springer, 2020).","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"2403_CR21","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A. P. et al. Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. imaging 36, 86\u201397 (2016).","journal-title":"IEEE Trans. Med. imaging"},{"key":"2403_CR22","unstructured":"Stauder, R. et al. The tum lapchole dataset for the M2CAI 2016 workflow challenge. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/1610.09278 (2016)."},{"key":"2403_CR23","doi-asserted-by":"publisher","first-page":"102770","DOI":"10.1016\/j.media.2023.102770","volume":"86","author":"M Wagner","year":"2023","unstructured":"Wagner, M. et al. Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the heichole benchmark. Med. Image Anal. 86, 102770 (2023).","journal-title":"Med. Image Anal."},{"key":"2403_CR24","doi-asserted-by":"publisher","first-page":"103716","DOI":"10.1016\/j.media.2025.103716","volume":"106","author":"A Das","year":"2025","unstructured":"Das, A. et al. Pitvis-2023 challenge: workflow recognition in videos of endoscopic pituitary surgery. Med. Image Anal. 106, 103716 (2025).","journal-title":"Med. Image Anal."},{"key":"2403_CR25","doi-asserted-by":"crossref","unstructured":"Valderrama, N. et al. Towards holistic surgical scene understanding. in International Conference on Medical Image Computing and Computer-assisted Intervention, 442\u2013452 (Springer, 2022).","DOI":"10.1007\/978-3-031-16449-1_42"},{"key":"2403_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z. et al. Autolaparo: A new dataset of integrated multi-tasks for image-guided surgical automation in laparoscopic hysterectomy. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 486\u2013496 (Springer, 2022).","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"2403_CR27","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1007\/s11548-024-03166-3","volume":"19","author":"JL Lavanchy","year":"2024","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. 19, 2249\u20132257 (2024).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"2403_CR28","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. In Proc. International Conference on Learning Representations (2021)."},{"key":"2403_CR29","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J. & Wang, L. Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural Inf. Process. Syst. 35, 10078\u201310093 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2403_CR30","unstructured":"Wang, Y. et al. Internvideo: general video foundation models via generative and discriminative learning. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/2212.03191 (2022)."},{"key":"2403_CR31","doi-asserted-by":"crossref","unstructured":"Wang, R. et al. Masked video distillation: rethinking masked feature modeling for self-supervised video representation learning. in Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6312\u20136322 (IEEE, 2023).","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"2403_CR32","doi-asserted-by":"crossref","unstructured":"Li, K. et al. Unmasked teacher: towards training-efficient video foundation models. in Proc. IEEE\/CVF International Conference on Computer Vision, 19948\u201319960 (IEEE, 2023).","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"2403_CR33","unstructured":"White, C. et al. Livebench: a challenging, contamination-free llm benchmark. In Proc. International Conference on Learning Representations (2025)."},{"key":"2403_CR34","doi-asserted-by":"crossref","unstructured":"Wang, L. et al. Videomae v2: Scaling video masked autoencoders with dual masking. in Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14549\u201314560 (IEEE, 2023).","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"2403_CR35","unstructured":"Bertasius, G., Wang, H. & Torresani, L. Is space-time attention all you need for video understanding? In Proc. International Conference on Machine Learning, 813\u2013824 (Proceedings of Machine Learning Research, 2021)."},{"key":"2403_CR36","first-page":"35946","volume":"35","author":"C Feichtenhofer","year":"2022","unstructured":"Feichtenhofer, C., Li, Y., He, K. et al. Masked autoencoders as spatiotemporal learners. Adv. neural Inf. Process. Syst. 35, 35946\u201335958 (2022).","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"2403_CR37","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, L., Wang, Q. & Chen, H. Surgformer: surgical transformer with hierarchical temporal attention for surgical phase recognition. in Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention, 606\u2013616 (Springer, 2024).","DOI":"10.1007\/978-3-031-72089-5_57"},{"key":"2403_CR38","doi-asserted-by":"crossref","unstructured":"Guo, D., Si, W., Li, Z., Pei, J. & Heng, P.-A. Surgical workflow recognition and blocking effectiveness detection in laparoscopic liver resections with pringle maneuver. In Proc. 39th AAAI Conference on Artificial Intelligence, 3220-3228 (AAAI Press, 2025).","DOI":"10.1609\/aaai.v39i3.32332"},{"key":"2403_CR39","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.media.2018.11.008","volume":"52","author":"H Al Hajj","year":"2019","unstructured":"Al Hajj, H. et al. Cataracts: Challenge on automatic tool annotation for cataract surgery. Med. image Anal. 52, 24\u201341 (2019).","journal-title":"Med. image Anal."},{"key":"2403_CR40","doi-asserted-by":"crossref","unstructured":"Schoeffmann, K. et al. Cataract-101: video dataset of 101 cataract surgeries. in Proc. 9th ACM Multimedia Systems Conference, 421\u2013425 (ACM, 2018).","DOI":"10.1145\/3204949.3208137"},{"key":"2403_CR41","doi-asserted-by":"crossref","unstructured":"Primus, M. J. et al. Frame-based classification of operation phases in cataract surgery videos. in MultiMedia Modeling: 24th International Conference, MMM 2018, Bangkok, Thailand, February 5-7, 2018, Proceedings, Part I 24, 241\u2013253 (Springer, 2018).","DOI":"10.1007\/978-3-319-73603-7_20"},{"key":"2403_CR42","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.1109\/TMI.2021.3069471","volume":"40","author":"Y Jin","year":"2021","unstructured":"Jin, Y. et al. Temporal memory relation network for workflow recognition from surgical video. IEEE Trans. Med. Imaging 40, 1911\u20131923 (2021).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2403_CR43","doi-asserted-by":"crossref","unstructured":"Yang, S. et al. Surgpetl: Parameter-efficient image-to-surgical-video transfer learning for surgical phase recognition. IEEE Trans. Med. Imaging (2025).","DOI":"10.1109\/TMI.2025.3615967"},{"key":"2403_CR44","doi-asserted-by":"publisher","first-page":"16813","DOI":"10.1007\/s11042-017-5252-2","volume":"77","author":"K Schoeffmann","year":"2018","unstructured":"Schoeffmann, K. et al. Video retrieval in laparoscopic video recordings with dynamic content descriptors. Multim. Tools Appl. 77, 16813\u201316832 (2018).","journal-title":"Multim. Tools Appl."},{"key":"2403_CR45","doi-asserted-by":"publisher","first-page":"102433","DOI":"10.1016\/j.media.2022.102433","volume":"78","author":"CI Nwoye","year":"2022","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).","journal-title":"Med. Image Anal."},{"key":"2403_CR46","doi-asserted-by":"crossref","unstructured":"Nwoye, C. I. et al. Recognition of instrument-tissue interactions in endoscopic videos via action triplets. In Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23, 364\u2013374 (Springer, 2020).","DOI":"10.1007\/978-3-030-59716-0_35"},{"key":"2403_CR47","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02073-7","volume":"10","author":"MS R\u00edos","year":"2023","unstructured":"R\u00edos, M. S. et al. Cholec80-cvs: An open dataset with an evaluation of strasberg\u2019s critical view of safety for AI. Sci. Data 10, 194 (2023).","journal-title":"Sci. Data"},{"key":"2403_CR48","unstructured":"Murali, A. et al. Latent graph representations for critical view of safety assessment. in Proc. IEEE Transactions on Medical Imaging (IEEE, 2023)."},{"key":"2403_CR49","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: A large-scale hierarchical image database. in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2403_CR50","doi-asserted-by":"crossref","unstructured":"Carreira, J. & Zisserman, A. Quo Vadis, action recognition? A new model and the Kinetics dataset. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4724\u20134733 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.502"},{"key":"2403_CR51","doi-asserted-by":"crossref","unstructured":"Li, K. et al. UniFormerV2: Unlocking the potential of image ViTs for video understanding. In Proc. IEEE\/CVF International Conference on Computer Vision, 1632\u20131643 (IEEE, 2023).","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"2403_CR52","doi-asserted-by":"crossref","unstructured":"Goyal, R. et al. The\" something something\" video database for learning and evaluating visual common sense. in Proc. IEEE International Conference on Computer Vision, 5842\u20135850 (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.622"},{"key":"2403_CR53","doi-asserted-by":"crossref","unstructured":"Gu, C. et al. Ava: a video dataset of spatio-temporally localized atomic visual actions. in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 6047\u20136056 (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00633"},{"key":"2403_CR54","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G. & Zisserman, A. Frozen in time: a joint video and image encoder for end-to-end retrieval. in Proc. IEEE\/CVF International Conference on Computer Vision, 1728\u20131738 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"2403_CR55","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C. & Zisserman, A. A short note about kinetics-600. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/1808.01340 (2018)."},{"key":"2403_CR56","unstructured":"Carreira, J., Noland, E., Hillier, C. & Zisserman, A. A short note on the kinetics-700 human action dataset. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/1907.06987 (2019)."},{"key":"2403_CR57","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. in Proc. International Conference on Machine Learning, 8748\u20138763 (PMLR, 2021)."},{"key":"2403_CR58","unstructured":"Chen, X., Fan, H., Girshick, R. & He, K. Improved baselines with momentum contrastive learning. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/2003.04297 (2020)."},{"key":"2403_CR59","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. in Proc. International Conference on Machine Learning, 1597\u20131607 (PMLR, 2020)."},{"key":"2403_CR60","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M. et al. Unsupervised learning of visual features by contrasting cluster assignments. Adv. neural Inf. Process. Syst. 33, 9912\u20139924 (2020).","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"2403_CR61","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2403_CR62","doi-asserted-by":"crossref","unstructured":"Assran, M. et al. Masked siamese networks for label-efficient learning. in European Conference on Computer Vision, 456\u2013473 (Springer, 2022).","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"2403_CR63","doi-asserted-by":"crossref","unstructured":"Liu, X. et al. Efficientvit: memory efficient vision transformer with cascaded group attention. in Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14420\u201314430 (IEEE, 2023).","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"2403_CR64","unstructured":"Nwoye, C. I. & Padoy, N. Data splits and metrics for method benchmarking on surgical action triplet datasets. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/2204.05235 (2022)."},{"key":"2403_CR65","unstructured":"Bawa, V. S. et al. The saras endoscopic surgeon action detection (ESAD) dataset: challenges and methods. arXiv preprint arXiv: https:\/\/arxiv.org\/abs\/2104.03178 (2021)."}],"updated-by":[{"DOI":"10.1038\/s41746-026-02864-3","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02403-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02403-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02403-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:41:28Z","timestamp":1781588488000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02403-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,4]]},"references-count":65,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2403"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02403-0","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,4]]},"assertion":[{"value":"21 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-026-02864-3","URL":"https:\/\/doi.org\/10.1038\/s41746-026-02864-3","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"S.Y. and H.C. are inventors on a patent application related to this work that is currently being prepared for filing via the Patent Cooperation Treaty (PCT) route, with The Hong Kong University of Science and Technology as the applicant. The application will cover the pre-training framework, model architecture, and pre-trained parameters presented in this manuscript. All other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"220"}}