{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T11:30:21Z","timestamp":1766748621111,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB1701600"],"award-info":[{"award-number":["2018YFB1701600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2069"],"award-info":[{"award-number":["U20B2069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3189253","type":"journal-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T19:24:43Z","timestamp":1657221883000},"page":"5192-5205","source":"Crossref","is-referenced-by-count":12,"title":["LgNet: A Local-Global Network for Action Recognition and Beyond"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7889-4601","authenticated-orcid":false,"given":"Jiaqi","family":"Zhou","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehua","family":"Fu","sequence":"additional","affiliation":[{"name":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyu","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5181-6451","authenticated-orcid":false,"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref12","first-page":"318","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"article-title":"Contrastive bidirectional transformer for temporal representation learning","year":"2019","author":"sun","key":"ref59"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018674"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"article-title":"Self-supervised spatiotemporal feature learning by video geometric transformations","year":"2018","author":"jing","key":"ref55"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref54","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref16","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_17"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"article-title":"Improving neural networks by preventing co-adaptation of feature detectors","year":"2012","author":"hinton","key":"ref46"},{"article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","year":"2017","author":"goyal","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00200"},{"key":"ref41","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref44","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01212"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928494"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971175"},{"article-title":"Improved baselines with momentum contrastive learning","year":"0","author":"chen","key":"ref40"},{"key":"ref35","first-page":"1","article-title":"Deep graph infomax","author":"velickovic","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_47"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"article-title":"Youtube-8 m: A large-scale video classification benchmark","year":"2016","author":"abu-el-haija","key":"ref64"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00629"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"kay","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"soomro","key":"ref29"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"ref62","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","author":"han","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09817623.pdf?arnumber=9817623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:02:33Z","timestamp":1701115353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9817623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3189253","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2023]]}}}