{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:50:41Z","timestamp":1781016641780,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"14","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"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":["62106158"],"award-info":[{"award-number":["62106158"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","award":["SKLSDE-2020KF-08"],"award-info":[{"award-number":["SKLSDE-2020KF-08"]}],"id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002888","name":"Research and Development Program of Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KM202210028007"],"award-info":[{"award-number":["KM202210028007"]}],"id":[{"id":"10.13039\/501100002888","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,7,15]]},"DOI":"10.1109\/jiot.2023.3257992","type":"journal-article","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T17:54:15Z","timestamp":1678989255000},"page":"12999-13011","source":"Crossref","is-referenced-by-count":10,"title":["Temporal Transformer Networks With Self-Supervision for Action Recognition"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0976-5934","authenticated-orcid":false,"given":"Yongkang","family":"Zhang","sequence":"first","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5009-6536","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Jiang","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoming","family":"Wu","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-8602","authenticated-orcid":false,"given":"Zhiping","family":"Shi","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxun","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2169-8271","authenticated-orcid":false,"given":"Zizhang","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Vision Perception Department, ZongMu Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-4195","authenticated-orcid":false,"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98355-0_10"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00209"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89029-2_20"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_41"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156634"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107037"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.619"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref51","first-page":"678","article-title":"Unsupervised visual representation learning by graph-based consistent constraints","author":"dong","year":"2016","journal-title":"Proc ECCV"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00815"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref47","first-page":"649","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3190307"},{"key":"ref41","article-title":"Transfusion: Cross-view fusion with transformer for 3D human pose estimation","author":"ma","year":"2021","journal-title":"arXiv 2110 09554"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169469"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_45"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025665"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2953814"},{"key":"ref9","article-title":"Self-supervised temporal discriminative learning for video representation learning","author":"wang","year":"2020","journal-title":"arXiv 2008 02129"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3163406"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref5","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"arXiv 1406 2199"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172971"},{"key":"ref34","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref36","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169842"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3195736"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072412"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3182313"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref39","article-title":"OCNet: Object context network for scene parsing","author":"yuan","year":"2018","journal-title":"arXiv 1809 00916"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref72","first-page":"1","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume":"32","author":"fan","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_22"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref25","article-title":"Interlaced sparse self-attention for semantic segmentation","author":"huang","year":"2019","journal-title":"arXiv 1907 12273"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref64","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"du","year":"2018","journal-title":"Proc CVPR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506453"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2771462"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2962304"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3162016"},{"key":"ref62","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":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10175002\/10073948.pdf?arnumber=10073948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:40:14Z","timestamp":1690825214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10073948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":76,"journal-issue":{"issue":"14"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3257992","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,15]]}}}