{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T17:22:54Z","timestamp":1780075374834,"version":"3.54.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation, Singapore under its Medium Sized Center for Advanced Robotics Technology Innovation"},{"name":"NTU Presidential Postdoctoral Fellowship, \u201cAdaptive Multimodal Learning for Robust Sensing and Recognition in Smart Cities\u201d Project Fund, Nanyang Technological University, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcyb.2023.3265393","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T21:12:54Z","timestamp":1682025174000},"page":"3810-3822","source":"Crossref","is-referenced-by-count":3,"title":["Self-Supervised Video Representation Learning by Video Incoherence Detection"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7703-3490","authenticated-orcid":false,"given":"Haozhi","family":"Cao","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4292-7379","authenticated-orcid":false,"given":"Yuecong","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9191-8604","authenticated-orcid":false,"given":"Kezhi","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7137-4136","authenticated-orcid":false,"given":"Lihua","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4686-2768","authenticated-orcid":false,"given":"Jianxiong","family":"Yin","sequence":"additional","affiliation":[{"name":"NVIDIA AI Tech Center, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4958-9237","authenticated-orcid":false,"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Tech Center, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2793-9048","authenticated-orcid":false,"given":"Qianwen","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electric Power and Energy Systems, KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Vondrick"},{"key":"ref2","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","volume":"37","author":"Srivastava"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2273174"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2399172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3079311"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3110813"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00171"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2973300"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2535122"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3227044"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3105637"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_9"},{"key":"ref26","article-title":"Video unsupervised domain adaptation with deep learning: A comprehensive survey","author":"Xu","year":"2022","journal-title":"arXiv:2211.10412"},{"key":"ref27","article-title":"Promoting poor features to supervisors: Some inputs work better as outputs","volume-title":"Advances in Neural Information Processing Systems","volume":"9","author":"Caruana","year":"1997"},{"issue":"11","key":"ref28","first-page":"1817","article-title":"A framework for learning predictive structures from multiple tasks and unlabeled data","volume":"6","author":"Ando","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref30","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Hjelm"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref32","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref33","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv:1909.11942"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref35","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref37","article-title":"Learning video representations using contrastive bidirectional transformer","author":"Sun","year":"2019","journal-title":"arXiv:1906.05743"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.751"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00259"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057833"},{"key":"ref41","first-page":"8545","article-title":"Self-supervised video representation learning with space-time cubic puzzles","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"33","author":"Kim"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02440-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"ref44","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Bachman","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093278"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref51","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":"ref52","first-page":"1","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Akbari"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126543"},{"key":"ref56","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref61","article-title":"Self-supervised learning by cross-modal audio-video clustering","author":"Alwassel","year":"2019","journal-title":"arXiv:1911.12667"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/104"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475394"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10542154\/10106103.pdf?arnumber=10106103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T18:55:52Z","timestamp":1732906552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10106103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2023.3265393","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}