{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:12:24Z","timestamp":1730247144836,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897657","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T17:27:24Z","timestamp":1667496444000},"page":"1716-1720","source":"Crossref","is-referenced-by-count":0,"title":["Ventriloquist-Net: Leveraging Speech Cues for Emotive Talking Head Generation"],"prefix":"10.1109","author":[{"given":"Deepan","family":"Das","sequence":"first","affiliation":[{"name":"Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany"}]},{"given":"Qadeer","family":"Khan","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany"}]},{"given":"Daniel","family":"Cremers","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Computer Vision and Artificial Intelligence,Department of Informatics,Garching,Germany"}]}],"member":"263","reference":[{"article-title":"What comprises a good talking-head video generation?: A survey and benchmark","year":"2020","author":"Chen","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3449063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"article-title":"You said that?","year":"2017","author":"Chung","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref14","first-page":"37","article-title":"End-to-end speech-driven realistic facial animation with temporal gans","volume-title":"CVPR Workshops","author":"Vougioukas"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2015.7404961"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1511\/2001.4.344"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref26","first-page":"398","volume-title":"Machine Audition: Principles, Algorithms and Systems, chapter Multimodal Emotion Recognition","author":"Haq","year":"2010"},{"issue":"3","key":"ref27","first-page":"182","article-title":"Recognition of emotional speech for younger and older talkers: behavioural findings from the toronto emotional speech set","volume":"39","author":"Dupuis","year":"2011","journal-title":"Canadian Acoustics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897657.pdf?arnumber=9897657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T16:39:49Z","timestamp":1705941589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897657","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}