{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:35:59Z","timestamp":1767987359175,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100004963","name":"European Union Seventh Framework Program","doi-asserted-by":"publisher","award":["FP7\/2007\u20132013"],"award-info":[{"award-number":["FP7\/2007\u20132013"]}],"id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004963","name":"European Union Seventh Framework Program","doi-asserted-by":"publisher","award":["287674"],"award-info":[{"award-number":["287674"]}],"id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1109\/tmm.2016.2535357","type":"journal-article","created":{"date-parts":[[2016,2,26]],"date-time":"2016-02-26T14:18:03Z","timestamp":1456496283000},"page":"967-977","source":"Crossref","is-referenced-by-count":31,"title":["Visual Voice Activity Detection in the Wild"],"prefix":"10.1109","volume":"18","author":[{"given":"Foteini","family":"Patrona","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Iosifidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Nikolaidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Pitas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"3056","DOI":"10.1016\/j.neucom.2007.02.009","article-title":"Convex incremental extreme learning machine","volume":"70","author":"huang","year":"2008","journal-title":"Neurocomputing"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.875977"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2237379"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref31","first-page":"1","article-title":"Using audio-visual features for robust voice activity detection in clean and noisy speech","volume":"86","author":"almajai","year":"2008","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2009.0042"},{"key":"ref37","author":"theodoridis","year":"2008","journal-title":"Pattern Recognition"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.2.23"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2269774"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854640"},{"key":"ref11","first-page":"1996","article-title":"Recognizing realistic actions from videos ‘in the wild’","author":"liu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF02910057"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2226527"},{"key":"ref14","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.07.011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2330763"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1380068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2011.29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.906583"},{"key":"ref27","article-title":"Dynamic visual features for visual-speech activity detection","author":"navarathna","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2247391"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305632"},{"key":"ref29","first-page":"1","article-title":"A visual voice activity detection method with adaboosting","author":"liu","year":"0","journal-title":"Proc Sensor Signal Process Defence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2322824"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2101586"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2007344"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.12.003"},{"key":"ref22","first-page":"151","article-title":"Voice activity detection based on fusion of audio and visual information","author":"takeuchi","year":"0","journal-title":"Proc Auditory Vis Speech Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745028"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.3050257"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2168604"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660092"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.251"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9794-4"},{"key":"ref25","article-title":"Visual speech detection using mouth region intensities","author":"siatras","year":"0"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7469905\/07420734.pdf?arnumber=7420734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:43:38Z","timestamp":1641987818000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7420734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":43,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2016.2535357","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,6]]}}}