{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T21:54:26Z","timestamp":1780350866894,"version":"3.54.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council of the U.K.","doi-asserted-by":"publisher","award":["EP\/K014307\/1"],"award-info":[{"award-number":["EP\/K014307\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council of the U.K.","doi-asserted-by":"publisher","award":["EP\/L000539\/1"],"award-info":[{"award-number":["EP\/L000539\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/tmm.2016.2599150","type":"journal-article","created":{"date-parts":[[2016,8,10]],"date-time":"2016-08-10T20:10:51Z","timestamp":1470859851000},"page":"2417-2431","source":"Crossref","is-referenced-by-count":34,"title":["Mean-Shift and Sparse Sampling-Based SMC-PHD Filtering for Audio Informed Visual Speaker Tracking"],"prefix":"10.1109","volume":"18","author":[{"given":"Volkan","family":"Kilic","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Barnard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2009.2021482"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415381"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2005.1561884"},{"key":"ref32","author":"mahler","year":"2007","journal-title":"Statistical Multisource-Multitarget Information Fusion"},{"key":"ref31","first-page":"357","article-title":"Tracking multiple speakers using random sets","volume":"2","author":"vo","year":"2004","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1088463.1088477"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334577"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref35","first-page":"1","article-title":"Adaptive particle filtering approach to audio-visual tracking","author":"kilic","year":"2013","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638334"},{"key":"ref60","author":"bluman","year":"2013","journal-title":"Elementary Statistics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008078328650"},{"key":"ref27","author":"bar-shalom","year":"1998","journal-title":"Tracking and Data Association"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.922063"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/365024.365310"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.836152"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937536"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.884624"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1195991"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2009722"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1247172"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.012"},{"key":"ref51","article-title":"Audio-visual tracking of multiple moving speakers","author":"kilic","year":"2015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2004.824848"},{"key":"ref58","first-page":"1","article-title":"On performance evaluation of multi-object filters","author":"schuhmacher","year":"2008","journal-title":"2008 11th International Conference on Information Fusion FUSION"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2140111"},{"key":"ref56","article-title":"Surveillance performance evaluation initiative (spevi) audiovisual people dataset","author":"taj","year":"2007"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30568-2_16"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1177\/0278364903022012001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.842254"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2266634"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2189853"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2131639"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284949"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2178402"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.893340"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301977"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1109\/AFGR.2004.1301611","article-title":"Real time hand tracking by combining particle filtering and mean shift","author":"shan","year":"2004","journal-title":"Proc Int Conf Autom Face Gesture Recog"},{"key":"ref4","first-page":"95","article-title":"Joint audio-visual speech processing for recognition and enhancement","author":"potamianos","year":"2003","journal-title":"Proc Int Conf Audio-Visual Speech Process"},{"key":"ref3","first-page":"3149","article-title":"Combining multi-source far distance speech recognition strategies: Beamforming, blind channel and confusion network combination","author":"w\u00f6lfel","year":"2005","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057890"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1998.999041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1406476"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415380"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0075-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.877658"},{"key":"ref45","first-page":"1","article-title":"Audio-visual tracking of a variable number of speakers with a random finite set approach","author":"kilic","year":"2014","journal-title":"Proc Int Conf Inf Fusion"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415697"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881190"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"2259","DOI":"10.1109\/TPAMI.2011.66","article-title":"Robust visual tracking and vehicle classification via sparse representation","volume":"33","author":"mei","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FCST.2008.9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177497"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2463221"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7744637\/07539615.pdf?arnumber=7539615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:13:29Z","timestamp":1642004009000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7539615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":60,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2016.2599150","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}