{"id":"https://openalex.org/W2587662404","doi":"https://doi.org/10.1109/hscma.2017.7895564","title":"Audio-visual tracking by density approximation in a sequential Bayesian filtering framework","display_name":"Audio-visual tracking by density approximation in a sequential Bayesian filtering framework","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2587662404","doi":"https://doi.org/10.1109/hscma.2017.7895564","mag":"2587662404"},"language":"en","primary_location":{"id":"doi:10.1109/hscma.2017.7895564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2017.7895564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Hands-free Speech Communications and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://inria.hal.science/hal-01452167","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072548521","display_name":"Israel D. Gebru","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Israel D. Gebru","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France","PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061813792","display_name":"Christine Evers","orcid":"https://orcid.org/0000-0003-0757-5504"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christine Evers","raw_affiliation_strings":["Imperial College London, Department of Electrical and Electronic Engineering, UK","DEEE - Department of Electrical and Electronic Engineering [London] (Imperial College London, South Kensington Campus, London SW7 2AZ - United Kingdom)"],"affiliations":[{"raw_affiliation_string":"Imperial College London, Department of Electrical and Electronic Engineering, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"DEEE - Department of Electrical and Electronic Engineering [London] (Imperial College London, South Kensington Campus, London SW7 2AZ - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College London, Department of Electrical and Electronic Engineering, UK","DEEE - Department of Electrical and Electronic Engineering [London] (Imperial College London, South Kensington Campus, London SW7 2AZ - United Kingdom)"],"affiliations":[{"raw_affiliation_string":"Imperial College London, Department of Electrical and Electronic Engineering, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"DEEE - Department of Electrical and Electronic Engineering [London] (Imperial College London, South Kensington Campus, London SW7 2AZ - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France","PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072548521"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"],"apc_list":null,"apc_paid":null,"fwci":1.01176064,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73904039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/mixture-model","display_name":"Mixture model","score":0.7842816114425659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6614181995391846},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.6115432977676392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5647692680358887},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4864461421966553},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47512727975845337},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47249141335487366},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4693017303943634},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.45722049474716187},{"id":"https://openalex.org/keywords/density-estimation","display_name":"Density estimation","score":0.44857606291770935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4096324145793915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2456359565258026},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.12798890471458435}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7842816114425659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614181995391846},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.6115432977676392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5647692680358887},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4864461421966553},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47512727975845337},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47249141335487366},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4693017303943634},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.45722049474716187},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.44857606291770935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4096324145793915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2456359565258026},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.12798890471458435},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hscma.2017.7895564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2017.7895564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Hands-free Speech Communications and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01452167v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01452167","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hscma2017.org/","raw_type":"Conference papers"},{"id":"pmh:oai:eprints.soton.ac.uk:445098","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/445098/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"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 or Workshop Item"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/44900","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/44900","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HSCMA 2017","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01452167v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01452167","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hscma2017.org/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1489950266","https://openalex.org/W1548502347","https://openalex.org/W1557595030","https://openalex.org/W1581808154","https://openalex.org/W1603544686","https://openalex.org/W1873027057","https://openalex.org/W1982687260","https://openalex.org/W2004909598","https://openalex.org/W2020934227","https://openalex.org/W2085157346","https://openalex.org/W2088725063","https://openalex.org/W2096301647","https://openalex.org/W2124156864","https://openalex.org/W2124781496","https://openalex.org/W2126885789","https://openalex.org/W2138414774","https://openalex.org/W2155325587","https://openalex.org/W2167868656","https://openalex.org/W2222512263","https://openalex.org/W2316138215","https://openalex.org/W3097096317","https://openalex.org/W6632875940","https://openalex.org/W6633511732","https://openalex.org/W6636127146","https://openalex.org/W6655473528","https://openalex.org/W6696741278"],"related_works":["https://openalex.org/W1952261593","https://openalex.org/W2017090935","https://openalex.org/W2032094637","https://openalex.org/W2040227828","https://openalex.org/W4244110343","https://openalex.org/W2060045818","https://openalex.org/W2131935101","https://openalex.org/W856257623","https://openalex.org/W2892315154","https://openalex.org/W2889431959"],"abstract_inverted_index":{"<p>This":[0],"paper":[1],"proposes":[2],"a":[3,24,34,50,58,73,80,88,98,112,126,136],"novel":[4],"audio-visual":[5,157],"tracking":[6,29,152],"approach":[7,158],"that":[8,57],"exploits":[9],"constructively":[10],"audio":[11],"and":[12,138],"visual":[13,163],"modalities":[14],"in":[15,23,125,151],"order":[16],"to":[17,44,86,101,143,160],"estimate":[18],"trajectories":[19],"of":[20,91,105,130,154],"multiple":[21],"people":[22],"joint":[25],"state":[26],"space.":[27],"The":[28],"problem":[30],"is":[31,70,84,96,122],"modeled":[32],"using":[33,75,135],"sequential":[35],"Bayesian":[36],"filtering":[37],"framework.":[38],"Within":[39],"this":[40],"framework,":[41],"we":[42],"propose":[43],"represent":[45],"the":[46,67,76,92,103,117,131,145,155],"posterior":[47,132],"density":[48,69,81,113],"with":[49],"Gaussian":[51],"Mixture":[52],"Model":[53],"(GMM).":[54],"To":[55],"ensure":[56],"GMM":[59,74,128],"representation":[60,90,129],"can":[61],"be":[62],"retained":[63],"sequentially":[64],"over":[65,110],"time,":[66,111],"predictive":[68],"approximated":[71],"by":[72],"Unscented":[77],"Transform.":[78],"While":[79],"interpolation":[82],"technique":[83],"introduced":[85],"obtain":[87],"continuous":[89],"observation":[93],"likelihood,":[94],"which":[95],"also":[97],"GMM.":[99],"Furthermore,":[100],"prevent":[102],"number":[104],"mixtures":[106],"from":[107],"growing":[108],"exponentially":[109],"approximation":[114],"based":[115],"on":[116],"Expectation":[118],"Maximization":[119],"(EM)":[120],"algorithm":[121],"applied,":[123],"resulting":[124],"compact":[127],"density.":[133],"Recordings":[134],"camcorder":[137],"microphone":[139],"array":[140],"are":[141],"used":[142],"evaluate":[144],"proposed":[146,156],"approach,":[147],"demonstrating":[148],"significant":[149],"improvements":[150],"performance":[153],"compared":[159],"two":[161],"benchmark":[162],"trackers.</p>":[164]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}