{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:53:53Z","timestamp":1747756433885},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412071","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"8914-8921","source":"Crossref","is-referenced-by-count":21,"title":["Temporally Coherent Embeddings for Self-Supervised Video Representation Learning"],"prefix":"10.1109","author":[{"given":"Joshua","family":"Knights","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Harwood","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Ward","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony","family":"Vanderkop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivia","family":"Mackenzie-Ross","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peyman","family":"Moghadam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref32","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"0","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/CVPR.2016.90"},{"year":"2017","author":"kay","journal-title":"The kinetics human action video dataset","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/CVPR.2018.00840"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/CVPR.2019.00413"},{"year":"2018","author":"jing","journal-title":"Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction","key":"ref34"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1609\/aaai.v33i01.33018545"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref12","first-page":"527","article-title":"Shuffle and learn: unsupervised learning using temporal order verification","author":"misra","year":"2016","journal-title":"European Conference on Computer Vision"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref14","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"Advances in neural information processing systems"},{"year":"2020","author":"chen","journal-title":"A simple framework for contrastive learning of visual representations","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICRA.2018.8462891"},{"year":"2019","author":"tian","journal-title":"Contrastive multiview coding","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2017.76"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR.2018.00586"},{"year":"2012","author":"soomro","journal-title":"Ucf10l A dataset of 101 human actions classes from videos in the wild","key":"ref28"},{"key":"ref4","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref3","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"0","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR.2016.18"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICCV.2011.6126543"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICCVW.2019.00186"},{"year":"2019","author":"el-nouby","journal-title":"Skip-clip Self-supervised spatiotemporal representation learning by future clip order ranking","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref2","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref1","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"0","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2016.418"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV.2017.471"},{"key":"ref21","article-title":"On mutual information maximization for representation learning","author":"tschannen","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref24","first-page":"2265","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","author":"mnih","year":"2013","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICCV.2015.320"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref25","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"0","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412071.pdf?arnumber=9412071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:55Z","timestamp":1652197255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412071\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412071","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}