{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T19:54:35Z","timestamp":1774727675618,"version":"3.50.1"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/cvpr42600.2020.00144","type":"proceedings-article","created":{"date-parts":[[2020,8,5]],"date-time":"2020-08-05T17:20:05Z","timestamp":1596648005000},"page":"1361-1371","source":"Crossref","is-referenced-by-count":23,"title":["Learning to Have an Ear for Face Super-Resolution"],"prefix":"10.1109","author":[{"given":"Givi","family":"Meishvili","sequence":"first","affiliation":[]},{"given":"Simon","family":"Jenni","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Favaro","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref33","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31726-3_23"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01077"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00280"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00428"},{"key":"ref35","article-title":"Deep face recognition","author":"parkhi","year":"0","journal-title":"British Machine Vision Conference"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_27"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00262"},{"key":"ref62","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00817"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00252"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref64","author":"zhu","year":"2018","journal-title":"High-resolution talking face generation via mutual information approximation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.618"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_32"},{"key":"ref2","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref1","article-title":"Fast, accurate, and lightweight super-resolution with cascading residual network","author":"ahn","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00183"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.187"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00167"},{"key":"ref24","author":"karras","year":"2018","journal-title":"A style-based generator architecture for generative adversarial networks"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00082"},{"key":"ref26","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00321"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00320"},{"key":"ref51","article-title":"Face super-resolution guided by facial component heatmaps","author":"yu","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref59","article-title":"Image super-resolution using very deep residual channel attention networks","author":"zhang","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00388"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00319"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00344"},{"key":"ref55","article-title":"Super-identity convolutional neural network for face hallucination","author":"zhang","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00889"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.570"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00831"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00317"},{"key":"ref13","author":"ephrat","year":"2018","journal-title":"Looking to listen at the cocktail party A speaker-independent audio-visual model for speech separation"},{"key":"ref14","article-title":"Learning to separate object sounds by watching unlabeled video","author":"gao","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref15","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00170"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00178"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00402"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00318"},{"key":"ref5","article-title":"To learn image super-resolution, use a gan to learn how to do image degradation first","author":"bulat","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00264"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00175"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.36"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00039"},{"key":"ref46","article-title":"What makes training multi-modal networks hard?","volume":"abs 1905 12681","author":"wang","year":"2019","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01253"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00182"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_34"},{"key":"ref41","author":"song","year":"2018","journal-title":"Talking face generation by conditional recurrent adversarial network"},{"key":"ref44","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.298"}],"event":{"name":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Seattle, WA, USA","start":{"date-parts":[[2020,6,13]]},"end":{"date-parts":[[2020,6,19]]}},"container-title":["2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9142308\/9156271\/09156840.pdf?arnumber=9156840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T11:55:58Z","timestamp":1656330958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9156840\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/cvpr42600.2020.00144","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}