{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:24:48Z","timestamp":1772907888824,"version":"3.50.1"},"reference-count":84,"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":"am","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 Science Foundation Artificial Intelligence (AI) Institute for Foundations of Machine Learning","award":["2019844"],"award-info":[{"award-number":["2019844"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3310344","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:48:01Z","timestamp":1694108881000},"page":"5138-5152","source":"Crossref","is-referenced-by-count":24,"title":["CONVIQT: Contrastive Video Quality Estimator"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-7097","authenticated-orcid":false,"given":"Pavan C.","family":"Madhusudana","sequence":"first","affiliation":[{"name":"Samsung Research America, Plano, TX, USA"}]},{"given":"Neil","family":"Birkbeck","sequence":"additional","affiliation":[{"name":"Google Inc., Mountain View, CA, USA"}]},{"given":"Yilin","family":"Wang","sequence":"additional","affiliation":[{"name":"Google Inc., Mountain View, CA, USA"}]},{"given":"Balu","family":"Adsumilli","sequence":"additional","affiliation":[{"name":"Google Inc., Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6067-710X","authenticated-orcid":false,"given":"Alan C.","family":"Bovik","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3100462"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2880603"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413694"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref52","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137658"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISM46123.2019.00012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181496"},{"key":"ref18","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref51","first-page":"1","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","first-page":"1","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01408-w"},{"key":"ref44","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref43","first-page":"2864","article-title":"Continual learning for blind image quality assessment","volume":"45","author":"zhang","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref49","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","author":"dosovitskiy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5496296"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.23.1.013016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.02.012"},{"key":"ref82","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref84","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"komodakis","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref83","year":"2000","journal-title":"Final Report from the Video Quality Experts Group on the Validation of Objective Quality Metrics for Video Quality Assessment"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2683504"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946613"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502725"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/18.119732"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025098"},{"key":"ref77","year":"2021","journal-title":"Stock Video Footage in 4 K"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984879"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988437"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2042111"},{"key":"ref1","year":"2019","journal-title":"Cisco Visual Networking Index Forecast and Trends 2017–2022 White Paper"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240643"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2868063"},{"key":"ref71","first-page":"5128","article-title":"MUSIQ: Multiscale image quality transformer","author":"ke","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis (ICCV)"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2147325"},{"key":"ref73","article-title":"FAVER: Blind quality prediction of variable frame rate videos","author":"zheng","year":"2022","journal-title":"arXiv 2201 01492"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/PCS50896.2021.9477462"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366046"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2562513"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3162159"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2389431"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191169"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2707479"},{"key":"ref20","author":"li","year":"2019","journal-title":"Toward A Practical Perceptual Video Quality Metric"},{"key":"ref64","year":"2021","journal-title":"Encoding for Streaming Sites"},{"key":"ref63","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"khosla","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106801"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2011.2121650"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2868262"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2568752"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130536"},{"key":"ref61","first-page":"3298","article-title":"A largescale study on unsupervised spatiotemporal representation learning","author":"feichtenhofer","year":"2021","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/83\/9991910\/10243566-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10243566.pdf?arnumber=10243566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:15:22Z","timestamp":1695060922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3310344","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}