{"id":"https://openalex.org/W2153869101","doi":"https://doi.org/10.1109/icassp.2011.5946942","title":"Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter","display_name":"Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2153869101","doi":"https://doi.org/10.1109/icassp.2011.5946942","mag":"2153869101"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Bayesian_Integration_of_Audio_and_Visual_Information_for_Multi-Target_tracking_Using_a_CB-MeMBer_Filter/27378150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050176259","display_name":"Reza Hoseinnezhad","orcid":"https://orcid.org/0000-0001-9525-1467"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Reza Hoseinnezhad","raw_affiliation_strings":["RMIT University, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, VIC, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072792589","display_name":"Ba\u2010Ngu Vo","orcid":"https://orcid.org/0000-0003-4202-7722"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ba-Ngu Vo","raw_affiliation_strings":["University of Western Australia, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070960013","display_name":"Ba-Tuong Vo","orcid":"https://orcid.org/0000-0002-3954-238X"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ba-Tuong Vo","raw_affiliation_strings":["University of Western Australia, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031492664","display_name":"David Suter","orcid":"https://orcid.org/0000-0001-6306-3023"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Suter","raw_affiliation_strings":["University of Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2300","last_page":"2303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11220","display_name":"Water Systems and Optimization","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.7095054388046265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6988447308540344},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6595916748046875},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6451993584632874},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.572247326374054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5443463325500488},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5390024185180664},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5387182831764221},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.5374569892883301},{"id":"https://openalex.org/keywords/bayes-estimator","display_name":"Bayes estimator","score":0.5216039419174194},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5090115070343018},{"id":"https://openalex.org/keywords/recursive-bayesian-estimation","display_name":"Recursive Bayesian estimation","score":0.49363720417022705},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4865064024925232},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4523584842681885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37310904264450073}],"concepts":[{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.7095054388046265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988447308540344},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6595916748046875},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6451993584632874},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.572247326374054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443463325500488},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5390024185180664},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5387182831764221},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5374569892883301},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.5216039419174194},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5090115070343018},{"id":"https://openalex.org/C40343088","wikidata":"https://www.wikidata.org/wiki/Q3059012","display_name":"Recursive Bayesian estimation","level":3,"score":0.49363720417022705},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4865064024925232},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4523584842681885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37310904264450073},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp.2011.5946942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/8f44a507-7587-4ada-a455-23b7573a2e0a","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/8f44a507-7587-4ada-a455-23b7573a2e0a","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hoseinnezhad, R, Vo, B-N, Vo, B T & Suter, D 2011, Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 2300-2303, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2011, Prague, Czech Republic, 22/05/11.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:14102","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:14102","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:alma.61RMIT_INST:11246654800001341","is_oa":false,"landing_page_url":"http://doi.org/10.1109/ICASSP.2011.5946942","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/70434","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/70434","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1109/icassp.2011.5946942","raw_type":"Conference paper"},{"id":"pmh:oai:espace.curtin.edu.au:20.500.11937/55473","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11937/55473","pdf_url":null,"source":{"id":"https://openalex.org/S4306401790","display_name":"eSpace (Curtin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205640436","host_organization_name":"Curtin University","host_organization_lineage":["https://openalex.org/I205640436"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/27378150","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Bayesian_Integration_of_Audio_and_Visual_Information_for_Multi-Target_tracking_Using_a_CB-MeMBer_Filter/27378150","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27378150","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Bayesian_Integration_of_Audio_and_Visual_Information_for_Multi-Target_tracking_Using_a_CB-MeMBer_Filter/27378150","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W34992941","https://openalex.org/W2031664991","https://openalex.org/W2044931169","https://openalex.org/W2107457079","https://openalex.org/W2110354007","https://openalex.org/W2118143383","https://openalex.org/W2123378338","https://openalex.org/W2161435744","https://openalex.org/W2164865661","https://openalex.org/W2545944991","https://openalex.org/W6683781877","https://openalex.org/W6684302384","https://openalex.org/W6728767478"],"related_works":["https://openalex.org/W2152348771","https://openalex.org/W1976194731","https://openalex.org/W1654445201","https://openalex.org/W2532459328","https://openalex.org/W617750611","https://openalex.org/W2013439927","https://openalex.org/W2910650093","https://openalex.org/W2368707535","https://openalex.org/W2012949382","https://openalex.org/W2361761948"],"abstract_inverted_index":{"A":[0],"new":[1],"method":[2,69],"is":[3,38],"presented":[4,34],"for":[5,59],"integration":[6],"of":[7,83],"audio":[8,57],"and":[9,25],"visual":[10],"information":[11],"in":[12,35],"multiple":[13],"target":[14],"tracking":[15,82],"applications.":[16],"The":[17,32,77],"proposed":[18],"approach":[19,44],"uses":[20],"a":[21,60],"Bayesian":[22,42],"filtering":[23],"formulation":[24],"exploits":[26],"multi-Bernoulli":[27],"random":[28],"finite":[29],"set":[30],"approximations.":[31],"work":[33],"this":[36],"paper":[37],"the":[39,47,74,99],"first":[40],"principled":[41],"estimation":[43],"to":[45,98],"solve":[46],"sensor":[48],"fusion":[49],"problems":[50],"that":[51],"involve":[52],"intermittent":[53],"sensory":[54],"data":[55,58],"(e.g.":[56],"person":[61],"who":[62],"occasionally":[63],"speaks.)":[64],"We":[65],"have":[66],"examined":[67],"our":[68],"with":[70],"case":[71],"studies":[72],"from":[73],"SPEVI":[75],"database.":[76],"results":[78],"show":[79],"nearly":[80],"perfect":[81],"people":[84],"not":[85,96],"only":[86],"when":[87,93],"they":[88,94],"are":[89,95],"silent":[90],"but":[91],"also":[92],"visible":[97],"camera":[100],"(but":[101],"speaking).":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}