{"id":"https://openalex.org/W4372259790","doi":"https://doi.org/10.1109/icassp49357.2023.10095234","title":"Recursive Joint Attention for Audio-Visual Fusion in Regression Based Emotion Recognition","display_name":"Recursive Joint Attention for Audio-Visual Fusion in Regression Based Emotion Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259790","doi":"https://doi.org/10.1109/icassp49357.2023.10095234"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021177750","display_name":"R. Gnana Praveen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Gnana Praveen","raw_affiliation_strings":["&#x00C9;cole de Technologie sup&#x00E9;rieure,Laboratoire d&#x2019;Imagerie, de Vision et d&#x2019;Intelligence Artificielle (LIVIA),Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"&#x00C9;cole de Technologie sup&#x00E9;rieure,Laboratoire d&#x2019;Imagerie, de Vision et d&#x2019;Intelligence Artificielle (LIVIA),Montreal,Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006937759","display_name":"\u00c9ric Granger","orcid":"https://orcid.org/0000-0001-6116-7945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Granger","raw_affiliation_strings":["&#x00C9;cole de Technologie sup&#x00E9;rieure,Laboratoire d&#x2019;Imagerie, de Vision et d&#x2019;Intelligence Artificielle (LIVIA),Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"&#x00C9;cole de Technologie sup&#x00E9;rieure,Laboratoire d&#x2019;Imagerie, de Vision et d&#x2019;Intelligence Artificielle (LIVIA),Montreal,Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051056084","display_name":"Patrick Cardinal","orcid":"https://orcid.org/0009-0000-9439-9910"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Cardinal","raw_affiliation_strings":["&#x00C9;cole de Technologie sup&#x00E9;rieure,Laboratoire d&#x2019;Imagerie, de Vision et d&#x2019;Intelligence Artificielle (LIVIA),Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"&#x00C9;cole de Technologie sup&#x00E9;rieure,Laboratoire d&#x2019;Imagerie, de Vision et d&#x2019;Intelligence Artificielle (LIVIA),Montreal,Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.8644400835037231},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8420506715774536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7143169641494751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5399913787841797},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5216175317764282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.518254280090332},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4133395552635193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3666747808456421},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35965466499328613},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09345951676368713}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8644400835037231},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8420506715774536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143169641494751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5399913787841797},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5216175317764282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.518254280090332},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4133395552635193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3666747808456421},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35965466499328613},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09345951676368713},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:espace2.etsmtl.ca:28572","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/28572/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Compte rendu de conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2523856713","https://openalex.org/W2546875627","https://openalex.org/W2610961739","https://openalex.org/W2798536775","https://openalex.org/W2886300652","https://openalex.org/W2899366898","https://openalex.org/W2963155035","https://openalex.org/W3005450949","https://openalex.org/W3008736792","https://openalex.org/W3094524767","https://openalex.org/W3100513545","https://openalex.org/W3118366136","https://openalex.org/W3121375749","https://openalex.org/W3126750668","https://openalex.org/W3137028092","https://openalex.org/W3144366453","https://openalex.org/W3209279902","https://openalex.org/W3209397829","https://openalex.org/W3211666705","https://openalex.org/W4221139382","https://openalex.org/W4292794079","https://openalex.org/W4292829055","https://openalex.org/W4313591463","https://openalex.org/W6729233594","https://openalex.org/W6756086341","https://openalex.org/W6773393266"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2185469136","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519"],"abstract_inverted_index":{"In":[0,29],"video-based":[1],"emotion":[2],"recognition":[3],"(ER),":[4],"it":[5],"is":[6,37],"important":[7],"to":[8,83],"effectively":[9],"leverage":[10,112],"the":[11,23,47,60,64,85,90,97,119,136,145],"complementary":[12,65],"relationship":[13],"among":[14,96],"audio":[15],"(A)":[16],"and":[17,51,69,115,123,139],"visual":[18],"(V)":[19],"modalities,":[20],"while":[21],"retaining":[22],"intramodal":[24,86],"characteristics":[25],"of":[26,49,62,67,121,128],"individual":[27],"modalities.":[28,125],"this":[30],"paper,":[31],"a":[32,73,78],"recursive":[33,79,105],"joint":[34,74,106],"attention":[35],"model":[36,76,109,149],"proposed":[38,146],"along":[39],"with":[40,81,104],"long":[41],"short-term":[42],"memory":[43],"(LSTM)":[44],"modules":[45],"for":[46,118],"fusion":[48,120,148],"vocal":[50],"facial":[52],"expressions":[53],"in":[54,77],"regression-based":[55],"ER.":[56],"Specifically,":[57],"we":[58],"investigated":[59],"possibility":[61],"exploiting":[63],"nature":[66],"A":[68,122],"V":[70,124],"modalities":[71,92],"using":[72],"cross-attention":[75],"fashion":[80],"LSTMs":[82,103],"capture":[84],"temporal":[87],"dependencies":[88],"within":[89],"same":[91],"as":[93,95],"well":[94],"A-V":[98,147],"feature":[99],"representations.":[100],"By":[101],"integrating":[102],"cross-attention,":[107],"our":[108],"can":[110,150],"efficiently":[111],"both":[113],"intra-":[114],"inter-modal":[116],"relationships":[117],"The":[126],"results":[127],"extensive":[129],"experiments":[130],"<sup":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[133],"performed":[134],"on":[135],"challenging":[137],"Affwild2":[138],"Fatigue":[140],"(private)":[141],"datasets":[142],"indicate":[143],"that":[144],"significantly":[151],"outperform":[152],"state-of-art-methods.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}