{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:47:48Z","timestamp":1783529268485,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002957","name":"Technische Universität Dresden","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002957","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Federal Ministry of Education and Research of Germany"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biomed. Eng."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tbme.2025.3535228","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:36:12Z","timestamp":1738089372000},"page":"2105-2119","source":"Crossref","is-referenced-by-count":10,"title":["TUNeS: A Temporal U-Net With Self-Attention for Video-Based Surgical Phase Recognition"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4566-3049","authenticated-orcid":false,"given":"Isabel","family":"Funke","sequence":"first","affiliation":[{"name":"Department of Translational Surgical Oncology, National Center for Tumor Diseases (NCT\/UCC) Dresden, Dresden, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominik","family":"Rivoir","sequence":"additional","affiliation":[{"name":"Department of Translational Surgical Oncology, National Center for Tumor Diseases (NCT\/UCC), Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanie","family":"Krell","sequence":"additional","affiliation":[{"name":"Department of Translational Surgical Oncology, National Center for Tumor Diseases (NCT\/UCC) Dresden, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4590-1908","authenticated-orcid":false,"given":"Stefanie","family":"Speidel","sequence":"additional","affiliation":[{"name":"Department of Translational Surgical Oncology, National Center for Tumor Diseases (NCT\/UCC) Dresden, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0940-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000004425"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2010.10.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051574-8.50089-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000004736"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2787657"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_32"},{"key":"ref17","first-page":"356","article-title":"An empirical study on activity recognition in long surgical videos","volume-title":"Proc. Mach. Learn. Health","volume":"193","author":"He","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02388-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02616-0"},{"key":"ref21","article-title":"Unsupervised temporal context learning using convolutional neural networks for laparoscopic workflow analysis","author":"Bodenstedt","year":"2017","journal-title":"arXiv:1702.03684"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01201-4_11"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102844"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103126"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_58"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3182995"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00178"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.49"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284080"},{"key":"ref35","article-title":"Vision-based approaches for surgical activity recognition using laparoscopic and RBGD videos","author":"Twinanda","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02600-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_47"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069471"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02811-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871004"},{"key":"ref44","first-page":"864","article-title":"PixelSNAIL: An improved autoregressive generative model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2018"},{"key":"ref45","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-022-02302-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref49","article-title":"Conditional positional encodings for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu","year":"2021"},{"key":"ref50","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref52","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref54","article-title":"Metrics matter in surgical phase recognition","author":"Funke","year":"2023","journal-title":"arXiv:2305.13961"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref56","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487305"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"ref59","article-title":"SAR-RARP50: Segmentation of surgical instrumentation and action recognition on robot-assisted radical prostatectomy challenge","author":"Psychogyios","year":"2023","journal-title":"arXiv:2401.00496"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"}],"container-title":["IEEE Transactions on Biomedical Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10\/11044973\/10856322.pdf?arnumber=10856322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:01:22Z","timestamp":1750744882000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":60,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tbme.2025.3535228","relation":{},"ISSN":["0018-9294","1558-2531"],"issn-type":[{"value":"0018-9294","type":"print"},{"value":"1558-2531","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}