{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:23:44Z","timestamp":1772303024502,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"French Plan d\u2019Investissement d\u2019Avenir (PIA) SUBTIL Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2925806","type":"journal-article","created":{"date-parts":[[2019,7,11]],"date-time":"2019-07-11T19:04:36Z","timestamp":1562871876000},"page":"88150-88162","source":"Crossref","is-referenced-by-count":14,"title":["DEEP-HEAR: A Multimodal Subtitle Positioning System Dedicated to Deaf and Hearing-Impaired People"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-4150","authenticated-orcid":false,"given":"Ruxandra","family":"Tapu","sequence":"first","affiliation":[]},{"given":"Bogdan","family":"Mocanu","sequence":"additional","affiliation":[]},{"given":"Titus","family":"Zaharia","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Proc ACCV"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2632284"},{"key":"ref11","first-page":"108","article-title":"An intelligent captioning system for the optimization of image and caption visibility","author":"kinoshita","year":"2005","journal-title":"Proc 6th Int Symp Adv Intell Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IWSCA.2008.28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3210825.3213556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3134786"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Berlin.2011.6031875"},{"key":"ref16","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.82"},{"key":"ref18","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2745197.2745204"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025772"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2015.11.004"},{"key":"ref5","article-title":"Speaker-following video subtitles","volume":"11","author":"hu","year":"2014","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1145\/2932206.2933558","article-title":"Region-of-interest-based subtitle placementusing eye-tracking data of multiple viewers","author":"akahori","year":"2016","journal-title":"Proc ACM Int Conf Interact Exper TV Online Video"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578760"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5220\/0006262201020109"},{"key":"ref1","year":"2019","journal-title":"Deafness and Hearing Loss"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA.2017.8310091"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-65"},{"key":"ref23","first-page":"919","article-title":"A scale-space filtering-based shot detection algorithm","author":"zaharia","year":"2010","journal-title":"IEEE 26th Conv Elect Electron Eng"},{"key":"ref26","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref25","first-page":"2616","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"chung","year":"2018","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08751956.pdf?arnumber=8751956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:39:55Z","timestamp":1628624395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8751956\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2925806","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}