{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:38:07Z","timestamp":1768340287989,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"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":["62072076"],"award-info":[{"award-number":["62072076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan, China","doi-asserted-by":"publisher","award":["2022NSFSC0500"],"award-info":[{"award-number":["2022NSFSC0500"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tcsvt.2023.3267178","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T17:33:26Z","timestamp":1681493606000},"page":"6679-6692","source":"Crossref","is-referenced-by-count":11,"title":["Actor-Aware Self-Supervised Learning for Semi-Supervised Video Representation Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2815-7993","authenticated-orcid":false,"given":"Maregu","family":"Assefa","sequence":"first","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6181-3900","authenticated-orcid":false,"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-1882","authenticated-orcid":false,"given":"Kumie Gedamu","family":"Alemu","sequence":"additional","affiliation":[{"name":"Sichuan Artificial Intelligence Research Institute, University of Electronic Science and Technology of China, Yibin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-3201","authenticated-orcid":false,"given":"Getinet","family":"Yilma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Adama Science and Technology University, Adama, Ethiopia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepak","family":"Adhikari","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6398-6060","authenticated-orcid":false,"given":"Melese","family":"Ayalew","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3672-6132","authenticated-orcid":false,"given":"Abegaz Mohammed","family":"Seid","sequence":"additional","affiliation":[{"name":"Division of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7565-5253","authenticated-orcid":false,"given":"Aiman","family":"Erbad","sequence":"additional","affiliation":[{"name":"Division of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"A dataset of 101 human action classes from videos in the wild","volume":"2","author":"soomro","year":"2012","journal-title":"Computer and Vision Research Center"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref52","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00373"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"ref16","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"sohn","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","author":"lee","year":"2013","journal-title":"Proc Workshop Challenges Represent Learn (ICML)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01407"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref50","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref46","first-page":"1","article-title":"When does label smoothing help?","volume":"32","author":"m\u00fcller","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref48","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"Proc ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref41","first-page":"1","article-title":"Why can’t I dance in the mall? Learning to mitigate scene bias in action recognition","volume":"32","author":"choi","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref44","article-title":"Online object representations with contrastive learning","author":"pirk","year":"2019","journal-title":"arXiv 1906 04312"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00980"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210271"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3114209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910208"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00115"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3193559"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00325"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"ref31","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108043"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169469"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980944"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00712"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00297"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP53232.2021.9674096"},{"key":"ref23","first-page":"9","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126622501596"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00022"},{"key":"ref22","first-page":"660","article-title":"Actor-aware contrastive learning for semi-supervised action recognition","author":"maregu","year":"2022","journal-title":"Proc IEEE 34th Int Conf Tools With Artif Intell (ICTAI)"},{"key":"ref21","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109455"},{"key":"ref27","first-page":"213","article-title":"Spatio-temporal dual-attention network for view-invariant human action recognition","volume":"12342","author":"gedamu","year":"2022","journal-title":"Proc SPIE"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10297951\/10102464.pdf?arnumber=10102464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:41:55Z","timestamp":1699904515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10102464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3267178","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}