{"id":"https://openalex.org/W2141823335","doi":"https://doi.org/10.1109/icip.2003.1247172","title":"Audio-visual speaker tracking with importance particle filters","display_name":"Audio-visual speaker tracking with importance particle filters","publication_year":2004,"publication_date":"2004-06-03","ids":{"openalex":"https://openalex.org/W2141823335","doi":"https://doi.org/10.1109/icip.2003.1247172","mag":"2141823335"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2003.1247172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1247172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/82738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012965551","display_name":"Daniel G\u00e1tica-P\u00e9rez","orcid":"https://orcid.org/0000-0001-5488-2182"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"D. Gatica-Perez","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007555019","display_name":"Guillaume Lathoud","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"G. Lathoud","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"I. McCowan","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J.-M. Odobez","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101490729","display_name":"David Moore","orcid":"https://orcid.org/0009-0000-8340-3013"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"D. Moore","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, IDIAP, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012965551"],"corresponding_institution_ids":["https://openalex.org/I2614128279"],"apc_list":null,"apc_paid":null,"fwci":4.8568,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95529559,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"III","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.799510657787323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7880032062530518},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.655052900314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6034403443336487},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.5850846767425537},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49024778604507446},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.46771329641342163},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.46702030301094055},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.45375868678092957},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44754448533058167},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44655999541282654},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41410428285598755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40680861473083496},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.40552347898483276},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38832011818885803},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.26226091384887695},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09272441267967224},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.08599302172660828}],"concepts":[{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.799510657787323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880032062530518},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.655052900314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6034403443336487},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5850846767425537},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49024778604507446},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.46771329641342163},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.46702030301094055},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.45375868678092957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44754448533058167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44655999541282654},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41410428285598755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40680861473083496},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.40552347898483276},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38832011818885803},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.26226091384887695},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09272441267967224},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.08599302172660828},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icip.2003.1247172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1247172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.3434","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.3434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~gatica/publications/GaticaLathoudMcCowanOdobezMoore-icip03.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82738","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:infoscience.epfl.ch:82888","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82888","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:infoscience.tind.io:82888","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/gatica02d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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 proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:82738","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1483307070","https://openalex.org/W1869980952","https://openalex.org/W1910898529","https://openalex.org/W2045656233","https://openalex.org/W2046317813","https://openalex.org/W2108248087","https://openalex.org/W2114863372","https://openalex.org/W2133447020","https://openalex.org/W2142511364","https://openalex.org/W4247690662","https://openalex.org/W4255333169","https://openalex.org/W6639402332","https://openalex.org/W6662135573","https://openalex.org/W6677383040"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W2333771223","https://openalex.org/W2120056845","https://openalex.org/W1981531423","https://openalex.org/W1679012645","https://openalex.org/W2070318884","https://openalex.org/W2011939812","https://openalex.org/W1994458110","https://openalex.org/W2100525497"],"abstract_inverted_index":{"We":[0,107],"present":[1],"a":[2,16,43,73,124,144],"probabilistic":[3],"method":[4],"for":[5,35],"audio-visual":[6],"(AV)":[7],"speaker":[8],"tracking,":[9],"using":[10],"an":[11,61,117],"uncalibrated":[12],"wide-angle":[13],"camera":[14],"and":[15,26,95,122,133],"micro-":[17],"phone":[18],"array.":[19],"The":[20,90],"algorithm":[21,118],"fuses":[22],"2-D":[23],"object":[24,138],"shape":[25],"audio":[27,96],"information":[28,41,56],"via":[29],"importance":[30,62],"particle":[31,74],"filters":[32],"(I-PFs),":[33],"allowing":[34],"the":[36,48,68,79,85,141],"asymmetrical":[37],"integration":[38],"of":[39,51,72,78,143],"AV":[40,137],"in":[42,100,104,140],"way":[44],"that":[45,109,119],"efficiently":[46],"exploits":[47],"complementary":[49],"features":[50],"each":[52],"modality.":[53],"Audio":[54],"localization":[55],"is":[57],"used":[58],"to":[59,83],"generate":[60],"sampling":[63],"(IS)":[64],"function,":[65],"which":[66,98],"guides":[67],"random":[69],"search":[70],"process":[71,92],"filter":[75],"towards":[76],"regions":[77],"configuration":[80,87],"space":[81],"likely":[82],"contain":[84],"true":[86],"(a":[88],"speaker).":[89],"measurement":[91],"integrates":[93],"contour-based":[94],"observations,":[97],"results":[99],"reliable":[101],"head":[102],"tracking":[103],"realistic":[105],"scenarios.":[106],"show":[108],"imperfect":[110],"single":[111],"modalities":[112],"can":[113],"be":[114],"combined":[115],"into":[116],"automatically":[120],"initializes":[121],"tracks":[123],"speaker,":[125],"switches":[126],"between":[127],"multiple":[128],"speakers,":[129],"tolerates":[130],"visual":[131],"clutter,":[132],"recovers":[134],"from":[135],"total":[136],"occlusion,":[139],"context":[142],"multimodal":[145],"meeting":[146],"room.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"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":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
