{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T09:19:47Z","timestamp":1768727987286,"version":"3.49.0"},"reference-count":63,"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":[{"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"}]},{"name":"Natural Science Foundation of Sichuan, China","award":["2022NSFSC0500"],"award-info":[{"award-number":["2022NSFSC0500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3193559","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T19:52:33Z","timestamp":1658778753000},"page":"5500-5515","source":"Crossref","is-referenced-by-count":15,"title":["Self-Supervised Scene-Debiasing for Video Representation Learning via Background Patching"],"prefix":"10.1109","volume":"25","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","family":"Gedamu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 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":"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\/0000-0002-8462-7518","authenticated-orcid":false,"given":"Bulbula","family":"Kumeda","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"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","author":"komodakis","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref56","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Self-supervised spatiotemporal feature learning via video rotation prediction","author":"jing","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00944"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref54","first-page":"2579","article-title":"Visualizing data using t-SNE.","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref19","first-page":"21271","article-title":"Bootstrap your own latent - A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref50","article-title":"UCF101: A dataset of 101 human action classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref46","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","author":"sohn","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"0","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2935128"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref44","first-page":"2216","article-title":"Un-mix: Rethinking image mixtures for unsupervised visual representation learning","author":"shen","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref43","first-page":"4694","article-title":"When Does Label Smoothing Help?","author":"m\u00fcller","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref9","first-page":"3791","article-title":"Self-supervised video representation learning by uncovering spatio-temporal statistics","volume":"44","author":"wang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127040"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3066775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980944"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00980"},{"key":"ref35","article-title":"Video representation learning with visual tempo consistency","author":"yang","year":"2020"},{"key":"ref34","first-page":"1","article-title":"Inter-intra variant dual representations for self-supervised video recognition","author":"zhang","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00358"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025661"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"ref24","first-page":"853","article-title":"Why can't I dance in the mall? learning to mitigate scene bias in action recognition","author":"choi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00373"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00153"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126622501596"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01367"},{"key":"ref61","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09839482.pdf?arnumber=9839482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:04:07Z","timestamp":1701115447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9839482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3193559","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}