{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:55:14Z","timestamp":1780764914795,"version":"3.54.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125603"],"award-info":[{"award-number":["62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1813218"],"award-info":[{"award-number":["U1813218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/tcsvt.2022.3149329","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T21:05:59Z","timestamp":1644267959000},"page":"5438-5452","source":"Crossref","is-referenced-by-count":9,"title":["Order-Constrained Representation Learning for Instructional Video Prediction"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0619-5780","authenticated-orcid":false,"given":"Muheng","family":"Li","sequence":"first","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4279-3892","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4971-6707","authenticated-orcid":false,"given":"Jianjiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.116"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv:1212.0402"},{"key":"ref7","article-title":"Deep learning for vision-based prediction: A survey","author":"Rasouli","year":"2020","journal-title":"arXiv:2007.00095"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2882805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00367"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2976789"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00840"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01234"},{"key":"ref20","article-title":"Boundary-sensitive pre-training for temporal localization in videos","author":"Xu","year":"2020","journal-title":"arXiv:2011.10830"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_28"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2882061"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00910"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987141"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984783"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-994-9_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2940224"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.362"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.39"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_26"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01409-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428266"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.751"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00629"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref42","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref43","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref46","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. NeurIPS","author":"Han"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"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","first-page":"7763","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. NeurIPS","author":"Korbar"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"ref52","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. AISTATS","author":"Gutmann"},{"key":"ref53","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. NeurIPS","author":"Tian"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref57","first-page":"270","article-title":"Ut-interaction dataset, ICPR contest on semantic description of human activities (SDHA)","volume-title":"Proc. ICCVW","author":"Ryoo"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_22"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.343"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_39"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.365"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491928"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2975065"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.390"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2751145"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9849156\/09705536.pdf?arnumber=9705536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:25:30Z","timestamp":1705533930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9705536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3149329","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}