{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:32:37Z","timestamp":1740180757130,"version":"3.37.3"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"German Research Foundation (DFG) funded PLUMCOT Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/tbiom.2019.2947264","type":"journal-article","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T19:51:51Z","timestamp":1571341911000},"page":"145-157","source":"Crossref","is-referenced-by-count":6,"title":["Video Face Clustering With Self-Supervised Representation Learning"],"prefix":"10.1109","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3909-7279","authenticated-orcid":false,"given":"Vivek","family":"Sharma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8800-9015","authenticated-orcid":false,"given":"Makarand","family":"Tapaswi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Saquib","family":"Sarfraz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref70","first-page":"1012","article-title":"Robust multi-pose face tracking by multi-stage tracklet association","author":"roth","year":"2012","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref39","first-page":"5925","article-title":"Learning disentangled representations with semi-supervised deep generative models","author":"narayanaswamy","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.131"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref32","first-page":"1","article-title":"Selfsupervised learning of face representations for video face clustering","author":"sharma","year":"2019","journal-title":"Proc Int Conf Autom Face Gesture Recognit"},{"key":"ref31","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_47"},{"journal-title":"Morphing Faces","year":"2018","key":"ref36"},{"key":"ref35","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref34","first-page":"2264","article-title":"Robust Boltzmann machines for recognition and denoising","author":"tang","year":"2012","journal-title":"Proc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref60","first-page":"527","article-title":"Shuffle and learn: Unsupervised learning using temporal order verification","author":"misra","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00424"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"ref64","article-title":"A simple and effective technique for face clustering in TV series","author":"sharma","year":"2017","journal-title":"CVPR Brave New Motion Representations Workshop"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/957052.957087"},{"key":"ref29","first-page":"420","article-title":"A posesensitive embedding for person re-identification with expanded cross neighborhood re-ranking","author":"sarfraz","year":"2018","journal-title":"Proc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1007\/3-540-45113-7_24","article-title":"Multimedia search with pseudorelevance feedback","author":"yan","year":"2003","journal-title":"Proc Int Conf Image Video Retrieval"},{"key":"ref67","article-title":"Tutorial on variational autoencoders","author":"doersch","year":"2016","journal-title":"arXiv preprint arXiv 1606 05908"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749296"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref69","first-page":"87","article-title":"MS-Celeb-1M: A dataset and benchmark for large-scale face recognition","author":"guo","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00029"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref26","first-page":"1","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","author":"huang","year":"2008","journal-title":"Proc Faces in Real-Life Images Workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref50","first-page":"2658","article-title":"‘Knock! Knock! Who is it?’ Probabilistic person identification in TV-series","author":"tapaswi","year":"2012","journal-title":"Proc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref51","first-page":"116","article-title":"A conditional random field approach for audio-visual people diarization","author":"gay","year":"2014","journal-title":"Proc Int Conf Audio Speech Signal Process"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref58","first-page":"6902","article-title":"Merge or not? Learning to group faces via imitation learning","author":"he","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref57","first-page":"8934","article-title":"Efficient parameter-free clustering using first neighbor relations","author":"sarfraz","year":"2019","journal-title":"Proc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351071"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.562"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477560"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806290"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2461466.2461469"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00513"},{"key":"ref40","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.92"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206513"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.462"},{"key":"ref14","first-page":"95","article-title":"Linking people in videos with ‘their’ names using coreference resolution","author":"ramanathan","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref15","first-page":"1","article-title":"From Benedict Cumberbatch to Sherlock Holmes: Character identification in TV series without a script","author":"nagrani","year":"2017","journal-title":"Proc Brit Mach Vis Conf (BMVC)"},{"key":"ref16","first-page":"467","article-title":"Who’s that actor? Automatic labelling of actors in TV series starting from IMDB images","author":"aljundi","year":"2016","journal-title":"Proc Asian Conf Comput Vis (ACCV)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.355"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.450"},{"key":"ref19","first-page":"497","article-title":"Deep metric learning with improved triplet loss for face clustering in videos","author":"zhang","year":"2016","journal-title":"Proc Pacific Rim Conf Multimedia"},{"key":"ref4","first-page":"7425","article-title":"Now you shake me: Towards automatic 4D cinema","author":"zhou","year":"2018","journal-title":"Proc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126415"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.447"},{"key":"ref8","first-page":"5286","article-title":"End-to-end face detection and cast grouping in movies using Erd?s–Rényi clustering","author":"jin","year":"2017","journal-title":"Proc Int Conf Comput Vis (ICCV)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.219"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459197"},{"key":"ref9","first-page":"236","article-title":"Joint face representation adaptation and clustering in videos","author":"zhang","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref46","article-title":"TVAE: Deep metric learning approach for variational autoencoder","author":"ishfaq","year":"2018","journal-title":"Proc ICLR Workshop"},{"key":"ref45","article-title":"Deep unsupervised clustering with Gaussian mixture variational autoencoders","author":"dilokthanakul","year":"2016","journal-title":"arXiv preprint arXiv 1611 02648"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2683483.2683490"},{"key":"ref47","first-page":"123","article-title":"Weighted block-sparse low rank representation for face clustering in videos","author":"xiao","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.637"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.346"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/273"},{"key":"ref43","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"xie","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8423754\/9050320\/08873682.pdf?arnumber=8873682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:13:34Z","timestamp":1651065214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8873682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":71,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2019.2947264","relation":{},"ISSN":["2637-6407"],"issn-type":[{"type":"electronic","value":"2637-6407"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}