{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T05:21:48Z","timestamp":1773033708877,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Germany\/Hong Kong Joint Research Scheme funded by the Research Grants Council of Hong Kong and Germany Academic Exchange Service of Germany","award":["G-HKUST605\/24"],"award-info":[{"award-number":["G-HKUST605\/24"]}]},{"name":"Hong Kong Innovation and Technology Commission","award":["GHP\/006\/22GD"],"award-info":[{"award-number":["GHP\/006\/22GD"]}]},{"DOI":"10.13039\/501100004787","name":"Research Grants Council of Hong Kong","doi-asserted-by":"publisher","award":["T45-401\/22-N"],"award-info":[{"award-number":["T45-401\/22-N"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tmi.2025.3615967","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:39:07Z","timestamp":1759340347000},"page":"1013-1023","source":"Crossref","is-referenced-by-count":2,"title":["SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1761-9286","authenticated-orcid":false,"given":"Shu","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2374-6186","authenticated-orcid":false,"given":"Zhiyuan","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-4151","authenticated-orcid":false,"given":"Luyang","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"given":"Ning","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"given":"Shuchang","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Tongji Institute of Digestive Disease, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8400-3780","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-5004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref5","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref6","article-title":"AIM: Adapting image models for efficient video action recognition","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00219"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103366"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref15","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref16","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_55"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2787657"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069471"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.08.066"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3326665"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-024-03091-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102844"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref26","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref28","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00568"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref33","article-title":"STC-ViT: Spatio temporal continuous vision transformer for weather forecasting","author":"Saleem","year":"2024","journal-title":"arXiv:2402.17966"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02073-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_57"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561770"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.11.008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208137"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_37"},{"key":"ref44","article-title":"The TUM LapChole dataset for the M2CAI 2016 workflow challenge","author":"Stauder","year":"2016","journal-title":"arXiv:1610.09278"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11421252\/11185234.pdf?arnumber=11185234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:31:31Z","timestamp":1772692291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":46,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3615967","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}