{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:35Z","timestamp":1740100895481,"version":"3.37.3"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":["62172101,61976057"],"award-info":[{"award-number":["62172101,61976057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["20511100800,21511100500"],"award-info":[{"award-number":["20511100800,21511100500"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859802","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Self-Supervised Video Representation Learning with Motion-Contrastive Perception"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Cheng","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui-Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Self-supervised spatiotemporal feature learning via video rotation prediction","author":"jing","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_47"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01367"},{"key":"ref14","article-title":"Self-supervised co-training for video representation learning","author":"han","year":"0","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413694"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00799"},{"key":"ref17","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref27","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref8","article-title":"Self-supervised video representation learning by pace prediction","author":"sauder","year":"0","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref2","article-title":"RSPNet: Relative speed perception for unsupervised video representation learning","author":"chen","year":"0","journal-title":"AAAI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"ref1","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"joao","year":"0","journal-title":"CVPR"},{"key":"ref20","article-title":"Learning representations for automatic colorization","author":"gustav","year":"0","journal-title":"ECCV"},{"key":"ref22","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"noroozi","year":"0","journal-title":"ECCV"},{"key":"ref24","article-title":"Rethinking motion representation: Residual frames with 3d convnets for better action recognition","author":"tao","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref26","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"0","journal-title":"AIS-TATS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859802.pdf?arnumber=9859802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:01Z","timestamp":1663619041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859802","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}