{"id":"https://openalex.org/W2153801342","doi":"https://doi.org/10.1109/cvprw.2008.4563178","title":"Associating audio-visual activity cues in a dominance estimation framework","display_name":"Associating audio-visual activity cues in a dominance estimation framework","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2153801342","doi":"https://doi.org/10.1109/cvprw.2008.4563178","mag":"2153801342"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw.2008.4563178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2008.4563178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061353073","display_name":"Hayley Hung","orcid":"https://orcid.org/0000-0001-9574-5395"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Hayley Hung","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764456","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-0575-0156"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["International Computer Science Institute, Berkeley, USA","University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028054905","display_name":"Chuohao Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuohao Yeo","raw_affiliation_strings":["University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","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/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniel Gatica-Perez","raw_affiliation_strings":["Ecole Polytechnique Federale de Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Federale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061353073"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":3.7983,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.93687296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9911999702453613,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9825999736785889,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8229600191116333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409745454788208},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6256780028343201},{"id":"https://openalex.org/keywords/torso","display_name":"Torso","score":0.6111240983009338},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5804656147956848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5609745383262634},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.527321994304657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49457284808158875},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4864928126335144},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4680081903934479},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4374498426914215},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34603744745254517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3385201096534729},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26350945234298706},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10720247030258179}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8229600191116333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409745454788208},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6256780028343201},{"id":"https://openalex.org/C523889960","wikidata":"https://www.wikidata.org/wiki/Q160695","display_name":"Torso","level":2,"score":0.6111240983009338},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5804656147956848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5609745383262634},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.527321994304657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49457284808158875},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4864928126335144},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4680081903934479},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4374498426914215},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34603744745254517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3385201096534729},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26350945234298706},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10720247030258179},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/cvprw.2008.4563178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2008.4563178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.139.347","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.139.347","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/HungHuangYeoGatica-cvpr4hb08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.5063","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.5063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146428/files/Hung_CVPR2008_2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.5118","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.5118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146425/files/Hung_Idiap-RR-66-2008.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146425","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146425","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:146428","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146428","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:146428","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Hung_Idiap-RR-66-2008","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 paper"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146425","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146425","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W187535091","https://openalex.org/W1770895068","https://openalex.org/W1831185418","https://openalex.org/W1967880820","https://openalex.org/W1976811227","https://openalex.org/W2073452456","https://openalex.org/W2073711670","https://openalex.org/W2099403067","https://openalex.org/W2106488367","https://openalex.org/W2110783210","https://openalex.org/W2123921937","https://openalex.org/W2124332251","https://openalex.org/W2124673517","https://openalex.org/W2125336414","https://openalex.org/W2129421456","https://openalex.org/W2133457618","https://openalex.org/W2165061375","https://openalex.org/W2167709189","https://openalex.org/W2560308376","https://openalex.org/W4236711171","https://openalex.org/W6638953181","https://openalex.org/W6678386964","https://openalex.org/W6678809451","https://openalex.org/W6684225735","https://openalex.org/W6730845448"],"related_works":["https://openalex.org/W4381953457","https://openalex.org/W2037557144","https://openalex.org/W2285739514","https://openalex.org/W2058088690","https://openalex.org/W2086597735","https://openalex.org/W2052143774","https://openalex.org/W1984495143","https://openalex.org/W4308297792","https://openalex.org/W2158185825","https://openalex.org/W1606408717"],"abstract_inverted_index":{"We":[0,26],"address":[1],"the":[2,7,52,57,63,69,74,140,149,152],"problem":[3,70],"of":[4,62,68,92,129,151,159],"both":[5],"estimating":[6],"dominant":[8,154],"person":[9,59,155],"in":[10,22,60],"a":[11,14,23,28,43,136,157],"meeting":[12],"from":[13,101,132],"single":[15],"audio":[16],"source":[17],"and":[18,36,86,113,144],"identifying":[19],"them":[20],"visually":[21],"multi-camera":[24],"setting.":[25],"use":[27],"speaker":[29,34,53,75,142],"diarization":[30,76,143],"algorithm":[31],"to":[32,55,94],"perform":[33],"segmentation":[35],"clustering,":[37],"representing":[38],"when":[39],"they":[40],"spoke.":[41],"Using":[42],"greedy":[44],"ordered":[45],"audio-visual":[46,130],"association":[47],"algorithm,":[48],"we":[49],"investigate":[50],"using":[51,125],"clusters":[54,93],"find":[56],"corresponding":[58],"one":[61],"video":[64],"channels.":[65,161],"The":[66],"difficulty":[67],"is":[71,78,116],"that":[72],"firstly":[73],"output":[77],"noisy":[79],"(e.g.":[80],"for":[81],"participants":[82],"who":[83],"speak":[84],"little)":[85],"often":[87],"produces":[88],"an":[89],"unequal":[90],"number":[91],"true":[95],"participants.":[96],"Secondly,":[97],"personal":[98],"visual":[99,145],"activity":[100,146],"natural":[102],"upper":[103],"torso":[104],"motion,":[105],"which":[106],"can":[107],"include":[108],"highly":[109],"deformable":[110],"pose":[111],"changes":[112],"perspective":[114],"distortion,":[115],"computed":[117],"through":[118],"computationally":[119],"efficient":[120],"coarse":[121],"features.":[122],"Our":[123],"results":[124],"almost":[126],"2":[127],"hours":[128],"data":[131],"4-participant":[133],"meetings":[134],"show":[135],"strong":[137],"correlation":[138],"between":[139],"estimated":[141],"features,":[147],"enabling":[148],"identification":[150],"most":[153],"as":[156],"pair":[158],"audiovisual":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
