{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:13:15Z","timestamp":1788873195700,"version":"build-2803163510"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"3IA Cote d\u2019Azur Investments","award":["ANR-23-IACL-0001"],"award-info":[{"award-number":["ANR-23-IACL-0001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"DOI":"10.1007\/s11548-026-03709-w","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:27:07Z","timestamp":1787923627000},"page":"1649-1656","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TBDM: Temporal boundary distillation module for surgical gesture segmentation"],"prefix":"10.1007","volume":"21","author":[{"given":"Ezem Sura","family":"Ekmekci","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastien","family":"Frey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Snehashis","family":"Majhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khodor","family":"Hamadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Herv\u00e9","family":"Delingette","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthieu","family":"Durand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Berthet-Rayne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francois","family":"Bremond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Ayache","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"3709_CR1","unstructured":"Baby B, Suri A (2024) Videocutmix: temporal segmentation of surgical videos in scarce data scenarios. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. Springer, Cham"},{"issue":"1","key":"3709_CR2","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1109\/TMI.2023.3299518","volume":"43","author":"Y Ban","year":"2024","unstructured":"Ban Y, Eckhoff JA, Ward TM, Hashimoto DA, Meireles OR, Rus D, Rosman G (2024) Concept graph neural networks for surgical video understanding. IEEE Trans Med Imaging 43(1):264\u2013274. https:\/\/doi.org\/10.1109\/TMI.2023.3299518","journal-title":"IEEE Trans Med Imaging"},{"key":"3709_CR3","doi-asserted-by":"publisher","unstructured":"Behrmann N, Golestaneh SA, Kolter Z, Gall J, Noroozi M (2022) Unified fully and timestamp supervised temporal action segmentation via sequence to sequence translation. In: European Conference on Computer Vision, pp. 52\u201368. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-19833-5_4","DOI":"10.1007\/978-3-031-19833-5_4"},{"key":"3709_CR4","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"3709_CR5","doi-asserted-by":"crossref","unstructured":"Csurka G, Larlus D, Perronnin F (2013) What is a good evaluation measure for semantic segmentation? In: British Machine Vision Conference","DOI":"10.5244\/C.27.32"},{"key":"3709_CR6","doi-asserted-by":"crossref","unstructured":"Ishikawa Y, Kasai S, Aoki Y, Kataoka H (2021) Alleviating over-segmentation errors by detecting action boundaries. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 2322\u20132331","DOI":"10.1109\/WACV48630.2021.00237"},{"issue":"8","key":"3709_CR7","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein VI (1966) Binary codes capable of correcting deletions, insertions, and reversals. Sov Phys Doklady 10(8):707\u2013710","journal-title":"Sov Phys Doklady"},{"issue":"6","key":"3709_CR8","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.1109\/TPAMI.2020.3021756","volume":"45","author":"S Li","year":"2023","unstructured":"Li S, Abu Farha Y, Liu Y, Cheng M-M, Gall J (2023) Ms-tcn++: multi-stage temporal convolutional network for action segmentation. IEEE Trans Pattern Anal Mach Intell 45(6):6647\u20136658. https:\/\/doi.org\/10.1109\/TPAMI.2020.3021756","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3709_CR9","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Su H, Wang C, Yang M (2018) Bsn: boundary sensitive network for temporal action proposal generation. In: European Conference on Computer Vision, pp 3\u201319. Springer, Cham","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"3709_CR10","doi-asserted-by":"crossref","unstructured":"Lin T, Liu X, Li X, Ding E, Wen S (2019) Bmn: boundary-matching network for temporal action proposal generation. In: IEEE International Conference on Computer Vision, pp 3889\u20133898","DOI":"10.1109\/ICCV.2019.00399"},{"key":"3709_CR11","doi-asserted-by":"crossref","unstructured":"Lu Z, Elhamifar E (2024) Fact: frame-action cross-attention temporal modeling for efficient action segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18175\u201318185","DOI":"10.1109\/CVPR52733.2024.01721"},{"key":"3709_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102803","volume":"86","author":"CI Nwoye","year":"2023","unstructured":"Nwoye CI, Alapatt D, Yu T, Vardazaryan A, Xia F, Zhao Z, Xia T, Jia F, Yang Y, Wang H et al (2023) Cholectriplet 2021: a benchmark challenge for surgical action triplet recognition. Med Image Anal 86:102803. https:\/\/doi.org\/10.1016\/j.media.2023.102803","journal-title":"Med Image Anal"},{"key":"3709_CR13","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","journal-title":"Med Image Anal"},{"key":"3709_CR14","doi-asserted-by":"publisher","unstructured":"Psychogyios D, Colleoni E, Amsterdam B, Li C-Y, Huang S-Y, Li Y, et al (2024) SAR-RARP50: Segmentation of surgical instrumentation and action recognition on robot-assisted radical prostatectomy challenge. arXiv preprint arXiv:2401.00496. Dataset (train): Dataset (test): https:\/\/doi.org\/10.5522\/04\/24932499","DOI":"10.5522\/04\/24932499"},{"key":"3709_CR15","doi-asserted-by":"crossref","unstructured":"Shen Y, Elhamifar E (2024) Progress-aware online action segmentation for egocentric procedural task videos. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18186\u201318197","DOI":"10.1109\/CVPR52733.2024.01722"},{"issue":"7","key":"3709_CR16","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1109\/TMI.2022.3147640","volume":"41","author":"B Amsterdam","year":"2022","unstructured":"Amsterdam B, Funke I, Edwards E, Speidel S, Collins J, Sridhar A, Kelly J, Clarkson MJ, Stoyanov D (2022) Gesture recognition in robotic surgery with multimodal attention. IEEE Trans Med Imaging 41(7):1677\u20131687. https:\/\/doi.org\/10.1109\/TMI.2022.3147640","journal-title":"IEEE Trans Med Imaging"},{"key":"3709_CR17","doi-asserted-by":"crossref","unstructured":"Amsterdam B, Kadkhodamohammadi A, Luengo I, Stoyanov D (2023) Aspnet: action segmentation with shared-private representation of multiple data sources. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2384\u20132393","DOI":"10.1109\/CVPR52729.2023.00236"},{"key":"3709_CR18","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30:5998\u20136008","journal-title":"Adv Neural Inf Process Syst"},{"key":"3709_CR19","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van\u00a0Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: European Conference on Computer Vision. Springer, Cham","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"3709_CR20","doi-asserted-by":"crossref","unstructured":"Wang L, Huang B, Zhao Z, Tong Z, He Y, Wang Y, Wang Y, Qiao Y (2023) Videomae v2: scaling video masked autoencoders with dual masking. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 14549\u201314560","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"3709_CR21","doi-asserted-by":"crossref","unstructured":"Yi F, Wen H, Jiang T (2021) Asformer: transformer for action segmentation. In: British Machine Vision Conference","DOI":"10.5244\/C.35.49"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03709-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03709-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03709-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:03:40Z","timestamp":1788872620000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03709-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":21,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["3709"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03709-w","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"assertion":[{"value":"26 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest to declare that is relevant to the content of this article.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This study used only publicly available de-identified datasets.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":4,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}]}}