{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:07:03Z","timestamp":1783530423707,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science, Technology, and Innovation (STI) 2030-Major Projects","award":["2021ZD0200300"],"award-info":[{"award-number":["2021ZD0200300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176241"],"award-info":[{"award-number":["62176241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC230B013"],"award-info":[{"award-number":["CUC230B013"]}],"id":[{"id":"10.13039\/501100012226","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":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3290938","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T17:31:54Z","timestamp":1688146314000},"page":"6634-6645","source":"Crossref","is-referenced-by-count":3,"title":["Self-Supervised Video Representation Learning via Capturing Semantic Changes Indicated by Saccades"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6872-5540","authenticated-orcid":false,"given":"Qiuxia","family":"Lai","sequence":"first","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication and the Neuroscience and Intelligent Media Institute, Communication University of China (CUC), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ailing","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Computer Vision and Robotics, International Digital Economy Academy (IDEA), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6073-4688","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication and the Neuroscience and Intelligent Media Institute, Communication University of China (CUC), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3866-2734","authenticated-orcid":false,"given":"Lihong","family":"Cao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication and the Neuroscience and Intelligent Media Institute, Communication University of China (CUC), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-126X","authenticated-orcid":false,"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.01.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321192121"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553469"},{"key":"ref4","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057833"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00301"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2008.09.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2762"},{"key":"ref12","first-page":"30365","article-title":"Local plasticity rules can learn deep representations using self-supervised contrastive predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Illing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/17470210902816461"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00548"},{"key":"ref15","first-page":"1","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00789"},{"key":"ref19","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Alayrac"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00944"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00840"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.638"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.751"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"ref32","first-page":"1","article-title":"Decomposing motion and content for natural video sequence prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Villegas"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00171"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref44","first-page":"1","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00813"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00799"},{"key":"ref51","first-page":"8089","article-title":"Cycle-contrast for self-supervised video representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00358"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00871"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00211"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2920636"},{"key":"ref57","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10168973.pdf?arnumber=10168973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:35:37Z","timestamp":1723527337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10168973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":66,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3290938","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}