{"id":"https://openalex.org/W2051000081","doi":"https://doi.org/10.1145/1027933.1027993","title":"Real-time audio-visual tracking for meeting analysis","display_name":"Real-time audio-visual tracking for meeting analysis","publication_year":2004,"publication_date":"2004-10-13","ids":{"openalex":"https://openalex.org/W2051000081","doi":"https://doi.org/10.1145/1027933.1027993","mag":"2051000081"},"language":"en","primary_location":{"id":"doi:10.1145/1027933.1027993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027933.1027993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international conference on Multimodal interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111581293","display_name":"David Demirdjian","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Demirdjian","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA","Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA","Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069218584","display_name":"Michael R. Siracusa","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Siracusa","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA","Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA","Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111581293"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.2733,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59507029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11439","display_name":"Video Analysis and Summarization","score":0.9871000051498413,"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/computer-science","display_name":"Computer science","score":0.7754333019256592},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6752438545227051},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6687955260276794},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6352078318595886},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6324954032897949},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.6007150411605835},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5446029305458069},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4747921824455261},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.4655047059059143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46216249465942383},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4139939248561859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40442246198654175},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3408549129962921},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2240292727947235},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2203611433506012},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10430634021759033},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08316335082054138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754333019256592},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6752438545227051},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6687955260276794},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6352078318595886},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6324954032897949},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6007150411605835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5446029305458069},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4747921824455261},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.4655047059059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46216249465942383},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4139939248561859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40442246198654175},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3408549129962921},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2240292727947235},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2203611433506012},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10430634021759033},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08316335082054138},{"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1027933.1027993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027933.1027993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international conference on Multimodal interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W187535091","https://openalex.org/W1506558619","https://openalex.org/W2104871070","https://openalex.org/W2108461717","https://openalex.org/W2111918405","https://openalex.org/W2163141813"],"related_works":["https://openalex.org/W4402262758","https://openalex.org/W2098934641","https://openalex.org/W3096250625","https://openalex.org/W3011716530","https://openalex.org/W3135871143","https://openalex.org/W4308222513","https://openalex.org/W4382560817","https://openalex.org/W2743050194","https://openalex.org/W2347715673","https://openalex.org/W2405875744"],"abstract_inverted_index":{"We":[0],"demonstrate":[1],"an":[2],"audio-visual":[3],"tracking":[4],"system":[5,29],"for":[6],"meeting":[7],"analysis.":[8],"A":[9],"stereo":[10],"camera":[11],"and":[12,22,41],"a":[13,43,50],"microphone":[14],"array":[15],"are":[16],"used":[17],"to":[18],"track":[19],"multiple":[20,35],"people":[21,48],"their":[23],"speech":[24],"activity":[25],"in":[26,49],"real-time.":[27],"Our":[28],"can":[30],"estimate":[31],"the":[32,38],"location":[33],"of":[34,45],"people,":[36],"detect":[37],"current":[39],"speaker":[40],"build":[42],"model":[44],"interaction":[46],"between":[47],"meeting.":[51]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
