{"id":"https://openalex.org/W2048447221","doi":"https://doi.org/10.1145/1631272.1631387","title":"Investigating the use of visual focus of attention for audio-visual speaker diarisation","display_name":"Investigating the use of visual focus of attention for audio-visual speaker diarisation","publication_year":2009,"publication_date":"2009-10-19","ids":{"openalex":"https://openalex.org/W2048447221","doi":"https://doi.org/10.1145/1631272.1631387","mag":"2048447221"},"language":"en","primary_location":{"id":"doi:10.1145/1631272.1631387","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146015","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089965540","display_name":"Giulia Garau","orcid":null},"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":false,"raw_author_name":"Giulia Garau","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037326211","display_name":"Sil\u00e8ye Ba","orcid":"https://orcid.org/0000-0003-4581-9880"},"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":false,"raw_author_name":"Sileye Ba","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"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":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"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":false,"raw_author_name":"Jean-Marc Odobez","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.911033570766449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024891972541809},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6603691577911377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5671721696853638},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5469399690628052},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26810240745544434},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06067204475402832}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.911033570766449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024891972541809},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6603691577911377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5671721696853638},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5469399690628052},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26810240745544434},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06067204475402832},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1631272.1631387","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.1346","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.1346","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/~odobez/publications/GarauBaBourlardOdobez-ACM-MM.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.1304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.1304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2009/Garau_ACMMULTIMEDIA_2009.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146015","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146015","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"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146015","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146015","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W94101771","https://openalex.org/W198212340","https://openalex.org/W1991048564","https://openalex.org/W2081841744","https://openalex.org/W2106015547","https://openalex.org/W2114528521","https://openalex.org/W2115175902","https://openalex.org/W2124022904","https://openalex.org/W2125336414","https://openalex.org/W2159591770","https://openalex.org/W2170584777","https://openalex.org/W2171757151","https://openalex.org/W2338994564"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519"],"abstract_inverted_index":{"Audio-visual":[0],"speaker":[1],"diarisation":[2],"is":[3],"the":[4],"task":[5],"of":[6],"estimating":[7],"``who":[8],"spoke":[9],"when''":[10],"using":[11],"audio":[12],"and":[13],"visual":[14],"cues.":[15]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
