{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T14:56:30Z","timestamp":1773413790280,"version":"3.50.1"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2023.3243812","type":"journal-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T19:50:49Z","timestamp":1676058649000},"page":"1-16","source":"Crossref","is-referenced-by-count":4,"title":["Self-supervised Video-centralised Transformer for Video Face Clustering"],"prefix":"10.1109","author":[{"given":"Yujiang","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8897-5931","authenticated-orcid":false,"given":"Mingzhi","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6722-2754","authenticated-orcid":false,"given":"Jie","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3096-4583","authenticated-orcid":false,"given":"Yiming","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6249-9909","authenticated-orcid":false,"given":"Yiming","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"899","article-title":"Hello! my name is... buffy","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Everingham"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103557"},{"key":"ref5","article-title":"Multi-face: Self-supervised multiview adaptation for robust face clustering in videos","author":"Somandepalli","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756609"},{"key":"ref7","article-title":"Constrained video face clustering using 1NN relations","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Kalogeiton"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.534"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.355"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.450"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11526346_26"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2463223"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CIISP.2007.369189"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.564"},{"key":"ref17","article-title":"A simple and effective technique for face clustering in TV series","volume-title":"Proc. Comput. Vis. Pattern Recognit. Workshop: Brave New Motion","author":"Sharma"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00914"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref25","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01362"},{"key":"ref33","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref34","first-page":"3861","article-title":"Towards K-means-friendly spaces: Simultaneous deep learning and clustering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.399"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247820"},{"key":"ref38","article-title":"EasyCom: An augmented reality dataset to support algorithms for easy communication in noisy environments","author":"Donley","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref40","first-page":"418","article-title":"TVD: A reproducible and multiply aligned TV series dataset","volume-title":"Proc. Int. Conf. Lang. Resour. Eval.","author":"Roy"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00513"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211332"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12327"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995680"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2679100"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2796999"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00121"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00240"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.134"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48890-5_49"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00101"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_46"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref57","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"Akbari","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref59","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref61","article-title":"Self-supervised co-training for video representation learning","author":"Han","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70096-0_39"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref69","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247986"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/2683483.2683490"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_15"},{"key":"ref77","volume-title":"Introduction to Information Retrieval","volume":"39","author":"Sch\u00fctze","year":"2008"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2001.989517"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.35"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref82","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3007"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10042051.pdf?arnumber=10042051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T19:22:47Z","timestamp":1709407367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10042051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3243812","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}