{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:01:16Z","timestamp":1783530076495,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"General Program of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82102189"],"award-info":[{"award-number":["82102189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"General Program of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82272086"],"award-info":[{"award-number":["82272086"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcsvt.2024.3502755","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T19:13:25Z","timestamp":1732130005000},"page":"3134-3145","source":"Crossref","is-referenced-by-count":10,"title":["Hierarchical Context Transformer for Multi-Level Semantic Scene Understanding"],"prefix":"10.1109","volume":"35","author":[{"given":"Luoying","family":"Hao","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7663-3096","authenticated-orcid":false,"given":"Yan","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8505-3057","authenticated-orcid":false,"given":"Yang","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wu","sequence":"additional","affiliation":[{"name":"MGI Tech Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9702-5524","authenticated-orcid":false,"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5108-2128","authenticated-orcid":false,"given":"Jinming","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6281-6505","authenticated-orcid":false,"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2946993"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0940-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_19"},{"key":"ref4","article-title":"MIcro-surgical anastomose workflow recognition challenge report","volume-title":"Comput. Methods Programs Biomed.","volume":"212","author":"Huaulm\u00e9","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101837"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02811-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000004351"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/13645706.2019.1584116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00940"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281413"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396692"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3260212"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069471"},{"key":"ref17","first-page":"343","article-title":"TeCNO: Surgical phase recognition with multi-stage temporal convolutional networks","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Czempiel"},{"key":"ref18","first-page":"2613","article-title":"Not end-to-end: Explore multi-stage architecture for online surgical phase recognition","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Yi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02785-y"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref21","first-page":"604","article-title":"OperA: Attention-regularized transformers for surgical phase recognition","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Czempiel"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3182995"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3265354"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102433","article-title":"Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos","volume":"78","author":"Nwoye","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref25","first-page":"399","article-title":"Instrument-tissue interaction quintuple detection in surgery videos","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Lin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3191838"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277462"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3405998"},{"key":"ref29","first-page":"442","article-title":"Towards holistic surgical scene understanding","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Valderrama"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3266137"},{"key":"ref32","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Pan"},{"key":"ref33","first-page":"1","article-title":"AIM: Adapting image models for efficient video action recognition","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref34","article-title":"The SARAS endoscopic surgeon action detection (ESAD) dataset","author":"Bawa","year":"2021","journal-title":"arXiv:2104.03178"},{"key":"ref35","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1007\/s11548-021-02388-z","article-title":"Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures","volume":"16","author":"Ramesh","year":"2021","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref37","first-page":"364","article-title":"Recognition of instrument-tissue interactions in endoscopic videos via action triplets","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Nwoye"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3381209"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref41","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref42","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref43","first-page":"6202","article-title":"SlowFast networks for video recognition","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Feichtenhofer"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref45","article-title":"2017 robotic instrument segmentation challenge","author":"Allan","year":"2019","journal-title":"arXiv:1902.06426"},{"key":"ref46","article-title":"2018 robotic scene segmentation challenge","author":"Allan","year":"2020","journal-title":"arXiv:2001.11190"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10949577\/10758661.pdf?arnumber=10758661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T07:20:51Z","timestamp":1743837651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10758661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":46,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3502755","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}