{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T21:14:31Z","timestamp":1767993271107,"version":"3.49.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3007350","type":"journal-article","created":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T20:30:09Z","timestamp":1594067409000},"page":"2071-2085","source":"Crossref","is-referenced-by-count":23,"title":["RealVAD: A Real-World Dataset and A Method for Voice Activity Detection by Body Motion Analysis"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9583-0087","authenticated-orcid":false,"given":"Cigdem","family":"Beyan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4573-0379","authenticated-orcid":false,"given":"Muhammad","family":"Shahid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-2328","authenticated-orcid":false,"given":"Vittorio","family":"Murino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846321"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-017-1006-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-141"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960522"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2000.840663"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.07.003"},{"key":"ref36","article-title":"Putting a face to the voice: Fusing audio and visual signals across a video to determine speakers","author":"hoover","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993172"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2016.04.014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853855"},{"key":"ref27","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"heng","year":"0","journal-title":"Proc IEEE Int Conf Comput Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31479-7_14"},{"key":"ref20","article-title":"Working with very sparse data to detect speaker and listener participation in a meetings corpus","volume":"10","author":"campbell","year":"0","journal-title":"Proc Workshop Programme"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240685"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/cav.6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-446"},{"key":"ref23","article-title":"Privacy camp 2018: Round-table, government hacking in different national contexts and strategies","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2927941"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.10.032"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2012.031"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.368"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30642-7_5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.02.001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960522"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-10"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.784617"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0187-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2016.7906033"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820780"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494913"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0105036"},{"key":"ref18","author":"feyereisen","year":"1991","journal-title":"Gestures and Speech Psychological Investigations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.92.3.350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2848914"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461267"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2013.2244901"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2895505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638359"},{"key":"ref49","first-page":"1556","article-title":"ELAN: A professional framework for multimodality research","author":"wittenburg","year":"0","journal-title":"Proc Lang Resour Eval Conf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2632111"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005602"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2463722"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405475"},{"key":"ref48","article-title":"Ava-activespeaker: An audio-visual dataset for active speaker detection","author":"roth","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349466"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.96"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-012-0111-y"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09133504.pdf?arnumber=9133504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:20Z","timestamp":1652194280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9133504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3007350","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}