{"id":"https://openalex.org/W2167023131","doi":"https://doi.org/10.1109/tsp.2009.2030861","title":"Audio-Visual Group Recognition Using Diffusion Maps","display_name":"Audio-Visual Group Recognition Using Diffusion Maps","publication_year":2009,"publication_date":"2009-08-25","ids":{"openalex":"https://openalex.org/W2167023131","doi":"https://doi.org/10.1109/tsp.2009.2030861","mag":"2167023131"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2009.2030861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2009.2030861","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-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/A5031057283","display_name":"Yosi Keller","orcid":"https://orcid.org/0000-0002-2876-2790"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yosi Keller","raw_affiliation_strings":["Department of Mathematics, Bar-llan University, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Bar-llan University, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110436903","display_name":"Ronald R. Coifman","orcid":"https://orcid.org/0000-0001-7336-7784"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronald R. Coifman","raw_affiliation_strings":["Department of Mathematics, Yale University, New Heaven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Yale University, New Heaven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083775994","display_name":"St\u00e9phane Lafon","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"St\u00c9phane Lafon","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012924253","display_name":"Steven W. Zucker","orcid":"https://orcid.org/0000-0002-2205-6895"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven W. Zucker","raw_affiliation_strings":["Department of Computer Science, Yale University, New Heaven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yale University, New Heaven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031057283"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":2.8544,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.91285894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"58","issue":"1","first_page":"403","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9968000054359436,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9968000054359436,"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":0.9916999936103821,"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/T10860","display_name":"Speech and Audio Processing","score":0.991100013256073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665158271789551},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6195717453956604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761595964431763},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5091342329978943},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.49374255537986755},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.46148696541786194},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42788293957710266},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33851200342178345},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3289593756198883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3241760730743408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19440320134162903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665158271789551},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6195717453956604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761595964431763},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5091342329978943},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.49374255537986755},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.46148696541786194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42788293957710266},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33851200342178345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3289593756198883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3241760730743408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19440320134162903},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsp.2009.2030861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2009.2030861","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.472.2817","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.2817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://yosi-keller.narod.ru/publications/pdf/AudioVisual.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W99428290","https://openalex.org/W194200989","https://openalex.org/W1554944419","https://openalex.org/W1646506067","https://openalex.org/W1874027545","https://openalex.org/W1984032850","https://openalex.org/W1986404249","https://openalex.org/W2006554089","https://openalex.org/W2013502943","https://openalex.org/W2031823405","https://openalex.org/W2042608483","https://openalex.org/W2065428732","https://openalex.org/W2079746361","https://openalex.org/W2082457734","https://openalex.org/W2093402979","https://openalex.org/W2097308346","https://openalex.org/W2097469960","https://openalex.org/W2098961769","https://openalex.org/W2099151709","https://openalex.org/W2103743127","https://openalex.org/W2108759471","https://openalex.org/W2116810533","https://openalex.org/W2117561657","https://openalex.org/W2119479037","https://openalex.org/W2124452080","https://openalex.org/W2128036349","https://openalex.org/W2140935196","https://openalex.org/W2142338953","https://openalex.org/W2160533343","https://openalex.org/W2161035581","https://openalex.org/W2161075870","https://openalex.org/W2171033594","https://openalex.org/W2294894133","https://openalex.org/W4213367101","https://openalex.org/W4285719527","https://openalex.org/W6603981764","https://openalex.org/W6607781037","https://openalex.org/W6636909375","https://openalex.org/W6653629126","https://openalex.org/W6678771169"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W3111677651","https://openalex.org/W2544283655","https://openalex.org/W2533072256","https://openalex.org/W2025991752","https://openalex.org/W2565829216"],"abstract_inverted_index":{"Data":[0],"fusion":[1],"is":[2,47,106],"a":[3,23,28,107,130],"natural":[4],"and":[5,50,113,128],"common":[6],"approach":[7,132],"to":[8,133],"recovering":[9],"the":[10,16,37,62,67,77,100,134],"state":[11],"of":[12,19,61,136],"physical":[13],"systems.":[14],"But":[15],"dissimilar":[17],"appearance":[18],"different":[20,89,95],"sensors":[21,90],"remains":[22],"fundamental":[24,108],"obstacle.":[25],"We":[26,119],"propose":[27],"unified":[29],"embedding":[30],"scheme":[31,46],"for":[32],"multisensory":[33],"data,":[34],"based":[35],"on":[36,123],"spectral":[38],"diffusion":[39,84,137],"framework,":[40],"which":[41],"addresses":[42],"this":[43],"issue.":[44],"Our":[45],"purely":[48],"data-driven":[49],"assumes":[51],"no":[52],"<i":[53,124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54,125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">a":[55],"priori</i>":[56],"statistical":[57],"or":[58],"deterministic":[59],"models":[60],"data":[63],"sources.":[64],"To":[65,139],"extract":[66],"underlying":[68],"structure,":[69],"we":[70,98,143],"first":[71],"embed":[72],"separately":[73],"each":[74],"input":[75],"channel;":[76],"resultant":[78],"structures":[79],"are":[80],"then":[81],"combined":[82],"in":[83,110,116,147],"coordinates.":[85,138],"In":[86],"particular,":[87],"as":[88],"sample":[91],"similar":[92],"phenomena":[93],"with":[94],"sampling":[96],"densities,":[97],"apply":[99],"density":[101],"invariant":[102],"Laplace-Beltrami":[103],"embedding.":[104],"This":[105],"issue":[109],"multisensor":[111],"acquisition":[112],"processing,":[114],"overlooked":[115],"prior":[117],"approaches.":[118],"extend":[120],"previous":[121],"work":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">group":[126],"recognition</i>":[127],"suggest":[129],"novel":[131],"selection":[135],"verify":[140],"our":[141],"approach,":[142],"demonstrate":[144],"performance":[145],"improvements":[146],"audio/visual":[148],"speech":[149],"recognition.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}