{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T18:55:59Z","timestamp":1770490559763,"version":"3.49.0"},"reference-count":31,"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\/wacv45572.2020.9093345","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"3298-3306","source":"Crossref","is-referenced-by-count":33,"title":["AlignNet: A Unifying Approach to Audio-Visual Alignment"],"prefix":"10.1109","author":[{"given":"Jianren","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhaoyuan","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Hang","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","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":"ref30","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2945078.2945097"},{"key":"ref12","first-page":"324","article-title":"2.5 d visual sound","author":"gao","year":"2019","journal-title":"Proceedings ofthe IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682863"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288293"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/vis.4340020404"},{"key":"ref17","first-page":"674","article-title":"An iterative image registratio technique with an application to stereo vision","author":"lucas","year":"1981","journal-title":"Proceedings of 7th International Joint Conference on Artificial Intelligence 1981"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248083"},{"key":"ref4","first-page":"1423","article-title":"Action-agnostic human pose forecasting","author":"chiu","year":"2018","journal-title":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"ref27","article-title":"Nfi-frits: A forensic speaker recognition database and some first experiments","author":"vloed","year":"2014","journal-title":"[Sl] ISCA Speaker and Language Characterization special interest group"},{"key":"ref3","article-title":"OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields","author":"cao","year":"2018"},{"key":"ref6","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201371"},{"key":"ref7","first-page":"3965","article-title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","author":"chung","year":"2018","journal-title":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref2","first-page":"179","article-title":"Audiovisual speech synchrony measure: application to biometrics","author":"bredin","year":"2007","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.184"},{"key":"ref1","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref20","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref22","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906583"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.552"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2710047"}],"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\/09093345.pdf?arnumber=9093345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:18:24Z","timestamp":1656602304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093345","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}