{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:47:46Z","timestamp":1773272866616,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428338","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Self-Supervised Mutual Learning for Video Representation Learning"],"prefix":"10.1109","author":[{"given":"Jinpeng","family":"Wang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}]},{"given":"Yutong","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}]},{"given":"Jianguo","family":"Hu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}]},{"given":"Xuebin","family":"Yang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}]},{"given":"Yanyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Development Research Institute of Guangzhou Smart City"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref11","article-title":"Enhancing unsupervised video representation learning by decoupling the scene and the motion","author":"wang","year":"2021","journal-title":"AAAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00666"},{"key":"ref14","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref17","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","author":"chollet","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref19","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"8545","DOI":"10.1609\/aaai.v33i01.33018545","article-title":"Self-supervised video representation learning with space-time cubic puzzles","volume":"33","author":"kim","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref6","first-page":"6210","article-title":"Un-supervised embedding learning via invariant and spreading instance feature","author":"ye","year":"2019","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.149"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref2","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"ICLRE"},{"key":"ref20","first-page":"2556","article-title":"Hmdb51: A large video database for human motion recognition","author":"kuehne","year":"2011","journal-title":"IEEE International Conference on Computer Vision"},{"key":"ref22","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref21","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref26","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"NeurlPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,5]]},"end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428338.pdf?arnumber=9428338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:24:12Z","timestamp":1659486252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428338","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}