{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:27:05Z","timestamp":1776886025936,"version":"3.51.2"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.00720","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T15:55:59Z","timestamp":1705334159000},"page":"7799-7808","source":"Crossref","is-referenced-by-count":4,"title":["SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning"],"prefix":"10.1109","author":[{"given":"Urwa","family":"Muaz","sequence":"first","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wondong","family":"Jang","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohun","family":"Tripathi","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santhosh","family":"Mani","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi Teja","family":"Gadde","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baris","family":"Gecer","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Elizondo","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reza","family":"Madad","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naveen","family":"Nair","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Azulay","year":"2018","journal-title":"Why do deep convolutional networks generalize so poorly to small image transformations?"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1009-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00377"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref8","article-title":"Deep generative image models using a laplacian pyramid of adversarial networks","volume":"28","author":"Denton","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00518"},{"key":"ref12","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01366"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref17","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"ref19","author":"Kumar","year":"2017","journal-title":"Obamanet: Photo-realistic lip-sync from text"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref21","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"International conference on machine learning","author":"Larsen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/info13020071"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_47"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref29","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref37","article-title":"Large-scale multilingual audio visual dubbing","author":"Yang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00158"},{"key":"ref39","first-page":"7324","article-title":"Making convolutional networks shift-invariant again","volume-title":"International conference on machine learning","author":"Zhang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01672-y"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10377730.pdf?arnumber=10377730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T20:18:02Z","timestamp":1705522682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10377730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.00720","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}