{"id":"https://openalex.org/W2169770604","doi":"https://doi.org/10.1145/1452392.1452438","title":"Detection and localization of 3d audio-visual objects using unsupervised clustering","display_name":"Detection and localization of 3d audio-visual objects using unsupervised clustering","publication_year":2008,"publication_date":"2008-10-20","ids":{"openalex":"https://openalex.org/W2169770604","doi":"https://doi.org/10.1145/1452392.1452438","mag":"2169770604"},"language":"en","primary_location":{"id":"doi:10.1145/1452392.1452438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1452392.1452438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on Multimodal interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00373148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015609539","display_name":"Vasil Khalidov","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","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":false,"raw_author_name":"Vasil Khalidov","raw_affiliation_strings":["INRIA Rh\u00f4ne-Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rh\u00f4ne-Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088691547","display_name":"Florence Forbes","orcid":"https://orcid.org/0000-0003-3639-0226"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","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":false,"raw_author_name":"Florence Forbes","raw_affiliation_strings":["INRIA Rh\u00f4ne-Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rh\u00f4ne-Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047677014","display_name":"Miles Hansard","orcid":"https://orcid.org/0000-0001-6764-786X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","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":false,"raw_author_name":"Miles Hansard","raw_affiliation_strings":["INRIA Rh\u00f4ne-Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rh\u00f4ne-Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113508987","display_name":"\u00c9lise Arnaud","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I177483745","display_name":"Universit\u00e9 Joseph Fourier","ror":"https://ror.org/02aj0kh94","country_code":"FR","type":"education","lineage":["https://openalex.org/I177483745"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Elise Arnaud","raw_affiliation_strings":["INRIA Rh\u00f4ne-Alpes, Montbonnot, and Universit\u00e9 Joseph Fourier, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rh\u00f4ne-Alpes, Montbonnot, and Universit\u00e9 Joseph Fourier, Grenoble, France","institution_ids":["https://openalex.org/I177483745","https://openalex.org/I1326498283"]}]},{"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/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","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":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Rh\u00f4ne-Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rh\u00f4ne-Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7524,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75254461,"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":"217","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9940999746322632,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9672999978065491,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701615691184998},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7290153503417969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6457122564315796},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5684249401092529},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5512675046920776},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.519096851348877},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5175768136978149},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5028936266899109},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49230921268463135},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4819888472557068},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47626611590385437},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4419942796230316},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4405268430709839},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4368768334388733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3840407729148865},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3549633026123047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701615691184998},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7290153503417969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6457122564315796},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5684249401092529},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5512675046920776},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.519096851348877},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5175768136978149},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5028936266899109},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49230921268463135},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4819888472557068},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47626611590385437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4419942796230316},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4405268430709839},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4368768334388733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3840407729148865},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3549633026123047},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1452392.1452438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1452392.1452438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on Multimodal interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.4801","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.4801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://perception.inrialpes.fr/Publications/2008/KFHAH08a/icmi08-khalidov.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00373148v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00373148","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICMI 2008 - ACM/IEEE International Conference on Multimodal Interfaces, Oct 2008, Chania, Greece. pp.217-224, &#x27E8;10.1145/1452392.1452438&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00373148v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00373148","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICMI 2008 - ACM/IEEE International Conference on Multimodal Interfaces, Oct 2008, Chania, Greece. pp.217-224, &#x27E8;10.1145/1452392.1452438&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1549965231","https://openalex.org/W1553557502","https://openalex.org/W1663973292","https://openalex.org/W1806536617","https://openalex.org/W1851133421","https://openalex.org/W1975350514","https://openalex.org/W2005705854","https://openalex.org/W2049633694","https://openalex.org/W2051091181","https://openalex.org/W2076364662","https://openalex.org/W2091377065","https://openalex.org/W2100152238","https://openalex.org/W2109124605","https://openalex.org/W2111308925","https://openalex.org/W2123993331","https://openalex.org/W2133115605","https://openalex.org/W2138232338","https://openalex.org/W2138414774","https://openalex.org/W2142511364","https://openalex.org/W2154496665","https://openalex.org/W2154897897","https://openalex.org/W2163141813","https://openalex.org/W2167709189","https://openalex.org/W2168175751","https://openalex.org/W2171819471","https://openalex.org/W4212863985","https://openalex.org/W4231869218","https://openalex.org/W6629510986"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"This":[0,76],"paper":[1],"addresses":[2],"the":[3,21,42,51,55,69,79,100,114,118,136],"issues":[4],"of":[5,23,27,53,90,99,112,121,138],"detecting":[6],"and":[7,17,30,35,44,73,107,117,130,133],"localizing":[8],"objects":[9],"in":[10,135],"a":[11,24,63,82,88,97],"scene":[12],"that":[13,41,67],"are":[14],"both":[15,113],"seen":[16],"heard.":[18],"We":[19,61,124],"explain":[20],"benefits":[22],"human-like":[25],"configuration":[26],"sensors":[28],"(binaural":[29],"binocular)":[31],"for":[32],"gathering":[33],"auditory":[34,115],"visual":[36,74],"observations.":[37,75],"It":[38],"is":[39,94,104],"shown":[40],"detection":[43,132],"localization":[45],"problem":[46],"can":[47],"be":[48],"recast":[49],"as":[50],"task":[52],"clustering":[54],"audio-visual":[56,84],"observations":[57],"into":[58,81],"coherent":[59],"groups.":[60],"propose":[62],"probabilistic":[64],"generative":[65],"model":[66,77],"captures":[68],"relations":[70],"between":[71],"audio":[72,140],"maps":[78],"data":[80],"common":[83],"3D":[85,119],"representation":[86],"via":[87],"pair":[89],"mixture":[91],"models.":[92],"Inference":[93],"performed":[95],"by":[96],"version":[98],"expectationmaximization":[101],"algorithm,":[102],"which":[103,108],"formally":[105],"derived,":[106],"provides":[109],"cooperative":[110],"estimates":[111],"activity":[116],"position":[120],"each":[122],"object.":[123],"describe":[125],"several":[126],"experiments":[127],"with":[128],"single-":[129],"multiple-speaker":[131],"localization,":[134],"presence":[137],"other":[139],"sources.":[141]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
