{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:09:02Z","timestamp":1778256542611,"version":"3.51.4"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:00:00Z","timestamp":1663718400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:00:00Z","timestamp":1663718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"DOI":"10.1007\/s11548-022-02743-8","type":"journal-article","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T10:05:57Z","timestamp":1663754757000},"page":"2193-2202","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Trans-SVNet: hybrid embedding aggregation Transformer for surgical workflow analysis"],"prefix":"10.1007","volume":"17","author":[{"given":"Yueming","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghao","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,21]]},"reference":[{"key":"2743_CR1","doi-asserted-by":"crossref","unstructured":"Maier-Hein L, Vedula SS, Speidel S, Navab N, Kikinis R, Park A, Eisenmann M, Feussner H, Forestier G, Giannarou S (2017) Surgical data science for next-generation interventions. Nature Biomedical Engineering","DOI":"10.1038\/s41551-017-0132-7"},{"issue":"2","key":"2743_CR2","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1080\/13645706.2019.1584116","volume":"28","author":"N Padoy","year":"2019","unstructured":"Padoy N (2019) Machine and deep learning for workflow recognition during surgery. Minimally Invasive Therapy & Allied Technol 28(2):82\u201390","journal-title":"Minimally Invasive Therapy & Allied Technol"},{"key":"2743_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102306","volume":"76","author":"L Maier-Hein","year":"2022","unstructured":"Maier-Hein L, Eisenmann M, Sarikaya D, M\u00e4rz K, Collins T, Malpani A, Fallert J, Feussner H, Giannarou S, Mascagni P (2022) Surgical data science-from concepts toward clinical translation. Med image anal 76:102306","journal-title":"Med image anal"},{"key":"2743_CR4","doi-asserted-by":"crossref","unstructured":"Rivoir D, Bodenstedt S, Funke I, Bechtolsheim Fv, Distler M, Weitz J, Speidel S (2020) Rethinking anticipation tasks: Uncertainty-aware anticipation of sparse surgical instrument usage for context-aware assistance. In: MICCAI, pp 752\u2013762. Springer","DOI":"10.1007\/978-3-030-59716-0_72"},{"key":"2743_CR5","doi-asserted-by":"crossref","unstructured":"Yuan K, Holden M, Gao S, Lee W-S (2021) Surgical workflow anticipation using instrument interaction. In: MICCAI, pp 615\u2013625. Springer","DOI":"10.1007\/978-3-030-87202-1_59"},{"issue":"6","key":"2743_CR6","first-page":"833","volume":"10","author":"G Forestier","year":"2015","unstructured":"Forestier G, Riffaud L, Jannin P (2015) Automatic phase prediction from low-level surgical activities. IJCARS 10(6):833\u2013841","journal-title":"IJCARS"},{"issue":"1","key":"2743_CR7","first-page":"86","volume":"36","author":"AP Twinanda","year":"2017","unstructured":"Twinanda AP, Shehata S, Mutter D, Marescaux J, De Mathelin M, Padoy N (2017) Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE TMI 36(1):86\u201397","journal-title":"IEEE TMI"},{"issue":"1","key":"2743_CR8","first-page":"39","volume":"8","author":"F Lalys","year":"2013","unstructured":"Lalys F, Bouget D, Riffaud L, Jannin P (2013) Automatic knowledge-based recognition of low-level tasks in ophthalmological procedures. IJCARS 8(1):39\u201349","journal-title":"IJCARS"},{"issue":"5","key":"2743_CR9","first-page":"1114","volume":"37","author":"Y Jin","year":"2018","unstructured":"Jin Y, Dou Q, Chen H, Yu L, Qin J, Fu C-W, Heng P-A (2018) SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network. IEEE TMI 37(5):1114\u20131126","journal-title":"IEEE TMI"},{"key":"2743_CR10","doi-asserted-by":"crossref","unstructured":"Yi F, Jiang T (2019) Hard frame detection and online mapping for surgical phase recognition. In: MICCAI","DOI":"10.1007\/978-3-030-32254-0_50"},{"issue":"4","key":"2743_CR11","first-page":"1069","volume":"38","author":"AP Twinanda","year":"2018","unstructured":"Twinanda AP, Yengera G, Mutter D, Marescaux J, Padoy N (2018) Rsdnet: Learning to predict remaining surgery duration from laparoscopic videos without manual annotations. IEEE TMI 38(4):1069\u20131078","journal-title":"IEEE TMI"},{"key":"2743_CR12","doi-asserted-by":"crossref","unstructured":"Funke I, Bodenstedt S, Oehme F, von Bechtolsheim F, Weitz J, Speidel S (2019) Using 3D convolutional neural networks to learn spatiotemporal features for automatic surgical gesture recognition in video. In: MICCAI","DOI":"10.1007\/978-3-030-32254-0_52"},{"key":"2743_CR13","doi-asserted-by":"crossref","unstructured":"Lea C, Flynn MD, Vidal R, Reiter A, Hager GD (2017) Temporal convolutional networks for action segmentation and detection. In: CVPR, pp 156\u2013165","DOI":"10.1109\/CVPR.2017.113"},{"key":"2743_CR14","doi-asserted-by":"crossref","unstructured":"Czempiel T, Paschali M, Keicher M, Simson W, Feussner H, Kim ST, Navab N (2020) Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In: MICCAI","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"2743_CR15","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in Neural Information Processing Systems, pp 5998\u20136008"},{"key":"2743_CR16","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A (2020) A survey on visual transformer. arXiv preprint arXiv:2012.12556"},{"key":"2743_CR17","doi-asserted-by":"crossref","unstructured":"Gabeur V, Sun C, Alahari K, Schmid C (2020) Multi-modal transformer for video retrieval. In: ECCV, pp 214\u2013229. Springer","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"2743_CR18","doi-asserted-by":"crossref","unstructured":"Wang Y, Solomon JM (2019) Deep closest point: Learning representations for point cloud registration. In: CVPR, pp 3523\u20133532","DOI":"10.1109\/ICCV.2019.00362"},{"key":"2743_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101572","volume":"59","author":"Y Jin","year":"2020","unstructured":"Jin Y, Li H, Dou Q, Chen H, Qin J, Fu C-W, Heng P-A (2020) Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med Image Anal 59:101572","journal-title":"Med Image Anal"},{"issue":"10","key":"2743_CR20","first-page":"1675","volume":"16","author":"J Zhang","year":"2021","unstructured":"Zhang J, Nie Y, Lyu Y, Yang X, Chang J, Zhang JJ (2021) Sd-net: joint surgical gesture recognition and skill assessment. IJCARS 16(10):1675\u20131682","journal-title":"IJCARS"},{"key":"2743_CR21","unstructured":"Franke S, Neumuth T (2015) Adaptive surgical process models for prediction of surgical work steps from surgical low-level activities. In: 6th Workshop on M2CAI at MICCAI"},{"key":"2743_CR22","doi-asserted-by":"crossref","unstructured":"Gao X, Jin Y, Long Y, Dou Q, Heng P-A (2021) Trans-svnet: accurate phase recognition from surgical videos via hybrid embedding aggregation transformer. In: MICCAI, pp 593\u2013603. Springer","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"2743_CR23","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2743_CR24","unstructured":"Twinanda AP, Shehata S, Mutter D, Marescaux J, De\u00a0Mathelin M, Padoy N MICCAI M2CAI Challenge. http:\/\/camma.u-strasbg.fr\/m2cai2016\/"},{"key":"2743_CR25","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, Lamard M, Conze P-H, Roychowdhury S, Hu X, Mar\u0161alkait\u0117 G, Zisimopoulos O (2019) Cataracts: Challenge on automatic tool annotation for cataract surgery. Med image anal 52:24\u201341","journal-title":"Med image anal"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02743-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-022-02743-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-022-02743-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T17:27:20Z","timestamp":1668446840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-022-02743-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,21]]},"references-count":25,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["2743"],"URL":"https:\/\/doi.org\/10.1007\/s11548-022-02743-8","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,21]]},"assertion":[{"value":"29 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2022","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 declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"This article does not contain patient data.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}