{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:10:12Z","timestamp":1771953012840,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093490","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"330-339","source":"Crossref","is-referenced-by-count":8,"title":["End to End Lip Synchronization with a Temporal AutoEncoder"],"prefix":"10.1109","author":[{"given":"Yoav","family":"Shalev","sequence":"first","affiliation":[]},{"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"2286","article-title":"Canonical time warping for alignment of human behavior","author":"zhou","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247812"},{"key":"ref31","article-title":"Convolutional Experts Constrained Local Model for Facial Landmark Detection","author":"zadeh","year":"2016"},{"key":"ref30","article-title":"CIDEr: Consensus-based Image Description Evaluation","author":"vedantam","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521684"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref10","article-title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","author":"chung","year":"2018"},{"key":"ref11","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref12","article-title":"Dynamic Temporal Alignment of Speech to Lips","author":"halperin","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284627"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref16","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/1025045"},{"key":"ref18","article-title":"ObamaNet: Photo-realistic lip-sync from text","author":"kumar","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/vis.4340020404"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"95:1","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing obama: Learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-008-0121-2"},{"key":"ref27","article-title":"You said that?","author":"son chung","year":"2017"},{"key":"ref3","article-title":"Audio-to-text alignment for speech recognition with very limited resources","author":"anguera","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.552"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref8","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"ACCV"},{"key":"ref7","article-title":"Monotonic Chunkwise Attention","author":"chiu and","year":"2017"},{"key":"ref2","article-title":"Deep Audio-Visual Speech Recognition","author":"afouras","year":"2018"},{"key":"ref9","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"ACCV Workshops"},{"key":"ref1","first-page":"69","year":"2007","journal-title":"Dynamic Time Warping"},{"key":"ref20","article-title":"Monotonic Multihead Attention","author":"ma","year":"2019"},{"key":"ref22","first-page":"ii?2117-ii","article-title":"Audiovisual speech translation with automatic lip syncqronization and face tracking based on 3-d head model","volume":"2","author":"morishima","year":"2002","journal-title":"2002 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref21","article-title":"Detecting audio-visual synchrony using deep neural networks","author":"marcheret","year":"2015","journal-title":"InterSpeech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906583"},{"key":"ref23","article-title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","author":"raffel","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126545"},{"key":"ref25","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"saxe","year":"2013"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093490.pdf?arnumber=9093490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:13:47Z","timestamp":1656602027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093490","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}