{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:35:11Z","timestamp":1776882911835,"version":"3.51.2"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016909","name":"Microsoft Research Asia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016909","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DSAIR@NTU"},{"name":"BSEWWT project"},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BSEWWT program office","award":["BSEWWT2017_2_06"],"award-info":[{"award-number":["BSEWWT2017_2_06"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971457"],"award-info":[{"award-number":["61971457"]}],"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":[[2020,12]]},"DOI":"10.1109\/tmm.2020.2973828","type":"journal-article","created":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T21:09:06Z","timestamp":1581714546000},"page":"3210-3223","source":"Crossref","is-referenced-by-count":70,"title":["DeepQoE: A Multimodal Learning Framework for Video Quality of Experience (QoE) Prediction"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0153-6400","authenticated-orcid":false,"given":"Huaizheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0315-1125","authenticated-orcid":false,"given":"Linsen","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8584-0532","authenticated-orcid":false,"given":"Guanyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7532-0496","authenticated-orcid":false,"given":"Han","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2751-5114","authenticated-orcid":false,"given":"Yonggang","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787486"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2018602.2018611"},{"key":"ref33","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref32","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chap Assoc Computat Linguist Human Lang Technol"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.04.009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2729891"},{"key":"ref35","article-title":"Learning to predict streaming video QoE: Distortions, rebuffering and memory","author":"bampis","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2247583"},{"key":"ref60","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Neural Inf Process Syst Deep Learn Workshop"},{"key":"ref61","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0"},{"key":"ref63","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"0","journal-title":"Proc USENIX Symp on Operating System Design and Implementation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref29","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2176324"},{"key":"ref1","article-title":"Cisco visual networking index: Global mobile data traffic forecast update, 2017–2022","author":"cisco","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2831639"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref26","article-title":"C3D: generic features for video analysis","volume":"2","author":"tran","year":"2014","journal-title":"Comput Vision Pattern Recognit"},{"key":"ref25","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":"ref50","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041760"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2013.2291681"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref54","first-page":"18","article-title":"Classification and regression by randomforest","volume":"2","author":"liaw","year":"2002","journal-title":"R News"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1109\/JPROC.2013.2257632","article-title":"Automatic prediction of perceptual image and video quality","volume":"101","author":"bovik","year":"0","journal-title":"Proc IEEE"},{"key":"ref52","article-title":"Toward a practical perceptual video quality metric","volume":"6","author":"li","year":"2016","journal-title":"The Netflix Tech Blog"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2363139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2619982"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2043164.2018478"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2014.6965834"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2012.107"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2013.6603207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520090"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2014.11.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2619901"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2298217"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924575"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2757761"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2315596"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2008.2001246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2838330"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2652064"},{"key":"ref7","first-page":"494","article-title":"Quantification of youtube QoE via crowdsourcing","author":"ho\u00dffeld","year":"0","journal-title":"Proc Int Symp Multimedia (ISM)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/EUVIP.2014.7018407"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206048"},{"key":"ref45","article-title":"WHU-MVQoE2016: A quality of experience dataset for mobile video research","author":"zhang","year":"2016"},{"key":"ref48","article-title":"Subjective video quality assessment methods for multimedia applications","year":"1999","journal-title":"Int Telecommun Union"},{"key":"ref47","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996604"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486523"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2815842"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9263048\/08999528.pdf?arnumber=8999528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T17:19:48Z","timestamp":1722446388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8999528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":63,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2973828","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]}}}