{"id":"https://openalex.org/W2106488367","doi":null,"title":"Learning Joint Statistical Models for Audio-Visual Fusion and Segregation","display_name":"Learning Joint Statistical Models for Audio-Visual Fusion and Segregation","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2106488367","mag":"2106488367"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.26.2205","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.2205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.mit.edu/people/fisher/mypage/../papers/fishernips00.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5142873499","display_name":"John Sheridan Fisher","orcid":"https://orcid.org/0000-0003-4844-3495","observed_orcids":["https://orcid.org/0000-0003-4844-3495"]},"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":"John W. Fisher","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA,"],"raw_orcid":"https://orcid.org/0000-0003-4844-3495","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["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,"],"raw_orcid":"https://orcid.org/0000-0001-5453-8533","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074429265","display_name":"William T. Freeman","orcid":"https://orcid.org/0000-0002-2231-7995","observed_orcids":["https://orcid.org/0000-0002-2231-7995","https://orcid.org/0000-0002-3316-4007","https://orcid.org/0000-0001-9979-2500"]},"institutions":[{"id":"https://openalex.org/I4405253225","display_name":"Mitsubishi Electric Research Laboratories (United States)","ror":"https://ror.org/00e2e3n51","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4405253225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William T. Freeman","raw_affiliation_strings":["Mitsubishi Electric Research Laboratory, Cambridge, MA#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-2231-7995","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratory, Cambridge, MA#TAB#","institution_ids":["https://openalex.org/I4405253225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042310818","display_name":"Paul A. Viola","orcid":null,"observed_orcids":[]},"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":"Paul Viola","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.0052,"has_fulltext":false,"cited_by_count":176,"citation_normalized_percentile":{"value":0.98352516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"772","last_page":"778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9785000085830688,"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":0.9785000085830688,"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/T12032","display_name":"Multisensory perception and integration","score":0.014999999664723873,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audiovisual-integration","display_name":"audiovisual integration","score":0.9929999709129333},{"id":"https://openalex.org/keywords/nonparametric-density-estimation","display_name":"nonparametric density estimation","score":0.9229999780654907},{"id":"https://openalex.org/keywords/low-dimensional-subspace-projection","display_name":"low-dimensional subspace projection","score":0.7379999756813049},{"id":"https://openalex.org/keywords/audio-visual-correspondence","display_name":"audio-visual correspondence","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399442791938782},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6348267793655396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906150341033936},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5656530261039734},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5631860494613647},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5595895051956177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5411419868469238},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.5220908522605896},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5212417244911194},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5159245729446411},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.4802311062812805},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47969648241996765},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4457013010978699},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44289296865463257},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4420246183872223},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43306130170822144},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4320949912071228},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29765671491622925},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2222578525543213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1378360092639923},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12041831016540527},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.26.2205","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.2205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.mit.edu/people/fisher/mypage/../papers/fishernips00.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.900.8273","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.900.8273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/1898-learning-joint-statistical-models-for-audio-visual-fusion-and-segregation.pdf","raw_type":"text"},{"id":"mag:2106488367","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/1898-learning-joint-statistical-models-for-audio-visual-fusion-and-segregation.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2099111195","https://openalex.org/W2100561338","https://openalex.org/W2105857581","https://openalex.org/W2110413319","https://openalex.org/W2126678392","https://openalex.org/W2130657708","https://openalex.org/W2160621778","https://openalex.org/W2164899449"],"related_works":["https://openalex.org/W7095825300","https://openalex.org/W7099503650","https://openalex.org/W2167709189","https://openalex.org/W2056961398","https://openalex.org/W2137398355","https://openalex.org/W7099346643","https://openalex.org/W2128653983","https://openalex.org/W3185822061","https://openalex.org/W75825362","https://openalex.org/W2894050827"],"abstract_inverted_index":{"People":[0],"can":[1],"understand":[2],"complex":[3,58],"auditory":[4,70],"and":[5,34,37,69,118],"visual":[6,68],"information,":[7],"often":[8],"using":[9,72,101],"one":[10],"to":[11],"disambiguate":[12],"the":[13,25,32,49,57,63,67,79,94,99,125],"other.":[14],"Automated":[15],"analysis,":[16],"even":[17],"at":[18],"a":[19,73,82,102],"lowlevel,":[20],"faces":[21],"severe":[22],"challenges,":[23],"including":[24],"lack":[26],"of":[27,66,124],"accurate":[28],"statistical":[29],"models":[30,47],"for":[31,48,88],"signals,":[33,120],"their":[35],"high-dimensionality":[36],"varied":[38],"sampling":[39],"rates.":[40],"Previous":[41],"approaches":[42],"[6]":[43],"assumed":[44],"simple":[45],"parametric":[46],"joint":[50,64],"distribution":[51,65],"which,":[52],"while":[53],"tractable,":[54],"cannot":[55],"capture":[56],"signal":[59,112],"relationships.":[60],"We":[61,91,114],"learn":[62],"signals":[71,100],"non-parametric":[74],"approach.":[75],"First,":[76],"we":[77],"project":[78],"data":[80],"into":[81],"maximally":[83],"informative,":[84],"low-dimensional":[85],"subspace,":[86],"suitable":[87],"density":[89,104],"estimation.":[90],"then":[92],"model":[93],"complicated":[95],"stochastic":[96],"relationships":[97],"between":[98],"nonparametric":[103],"estimator.":[105],"These":[106],"learned":[107],"densities":[108],"allow":[109],"processing":[110],"across":[111],"modalities.":[113],"demonstrate,":[115],"on":[116],"synthetic":[117],"real":[119],"localization":[121],"in":[122,130],"video":[123],"face":[126],"that":[127],"is":[128],"speaking":[129],"audio,":[131],"and,":[132],"conversely,":[133],"audio":[134],"enhan...":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}