{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T02:51:37Z","timestamp":1772247097925,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Wellcome\/Engineering and Physical Sciences Research Council (EPSRC) Centre for Interventional and Surgical Sciences","doi-asserted-by":"publisher","award":["203145\/Z\/16\/Z"],"award-info":[{"award-number":["203145\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/P027938\/1"],"award-info":[{"award-number":["EP\/P027938\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/R004080\/1"],"award-info":[{"award-number":["EP\/R004080\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/P012841\/1"],"award-info":[{"award-number":["EP\/P012841\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering Chair in Emerging Technologies Scheme, and Horizon 2020 Future and Emerging Technologies (FET) Open","doi-asserted-by":"publisher","award":["863146"],"award-info":[{"award-number":["863146"]}],"id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key-Area Research and Development Programof Guangdong Province, China","award":["2020B010165004"],"award-info":[{"award-number":["2020B010165004"]}]},{"name":"Hong Kong Research Grants Council (RGC) Theme-based Research Scheme","award":["T42-409\/18-R"],"award-info":[{"award-number":["T42-409\/18-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tmi.2022.3177077","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T20:50:15Z","timestamp":1653339015000},"page":"2991-3002","source":"Crossref","is-referenced-by-count":37,"title":["Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-3877","authenticated-orcid":false,"given":"Yueming","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Computer Science, Wellcome\/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London WC1E 6BT, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3024-9371","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6040-6833","authenticated-orcid":false,"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9399-3475","authenticated-orcid":false,"given":"Zixu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3055-5034","authenticated-orcid":false,"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0980-3227","authenticated-orcid":false,"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Wellcome\/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London WC1E 6BT, U.K"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-017-0132-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2019.4917"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102306"},{"key":"ref4","article-title":"2018 robotic scene segmentation challenge","author":"Allan","year":"2020","journal-title":"arXiv:2001.11190"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2020.1004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00940"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02369-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.07.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.12700\/aph.16.8.2019.8.5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3003735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067928"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00681"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref16","article-title":"Contrastive learning for label-efficient semantic segmentation","author":"Zhao","year":"2020","journal-title":"arXiv:2012.06985"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206462"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6850"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_47"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2021.3121138"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1117\/12.2512518"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32254-0_49"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_65"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_33"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_49"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3154925"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref29","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref31","article-title":"TrackFormer: Multi-object tracking with transformers","author":"Meinhardt","year":"2021","journal-title":"arXiv:2101.02702"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/21681163.2020.1835550"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_58"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433"},{"key":"ref37","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2018","journal-title":"arXiv:1808.06670"},{"key":"ref38","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. NeurIPS","volume":"27","author":"Dosovitskiy"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref40","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"arXiv:2006.07733"},{"key":"ref41","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Han"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref43","article-title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","author":"Chaitanya","year":"2020","journal-title":"arXiv:2006.10511"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref45","article-title":"Prototypical contrastive learning of unsupervised representations","author":"Li","year":"2020","journal-title":"arXiv:2005.04966"},{"key":"ref46","article-title":"What should not be contrastive in contrastive learning","author":"Xiao","year":"2020","journal-title":"arXiv:2008.05659"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/00224065.1986.11979014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"ref53","article-title":"2017 robotic instrument segmentation challenge","author":"Allan","year":"2019","journal-title":"arXiv:1902.06426"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref56","article-title":"Video swin transformer","author":"Liu","year":"2021","journal-title":"arXiv:2106.13230"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/42\/9931396\/09779714.pdf?arnumber=9779714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T02:23:07Z","timestamp":1706062987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9779714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":56,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2022.3177077","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}