{"id":"https://openalex.org/W4313591463","doi":"https://doi.org/10.1109/tbiom.2022.3233083","title":"Audio\u2013Visual Fusion for Emotion Recognition in the Valence\u2013Arousal Space Using Joint Cross-Attention","display_name":"Audio\u2013Visual Fusion for Emotion Recognition in the Valence\u2013Arousal Space Using Joint Cross-Attention","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313591463","doi":"https://doi.org/10.1109/tbiom.2022.3233083"},"language":"en","primary_location":{"id":"doi:10.1109/tbiom.2022.3233083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbiom.2022.3233083","pdf_url":null,"source":{"id":"https://openalex.org/S4210209367","display_name":"IEEE Transactions on Biometrics Behavior and Identity Science","issn_l":"2637-6407","issn":["2637-6407"],"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 Biometrics, Behavior, and Identity Science","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/A5021177750","display_name":"R. Gnana Praveen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Gnana Praveen","raw_affiliation_strings":["Department of Systems Engineering, Laboratoire d&#x2019;imagerie, de vision et d&#x2019;intelligence artificielle, &#x00C9;cole de technologie sup&#x00E9;rieure, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4698-9198","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, Laboratoire d&#x2019;imagerie, de vision et d&#x2019;intelligence artificielle, &#x00C9;cole de technologie sup&#x00E9;rieure, Montreal, Canada","institution_ids":[]}]},{"author_position":"middle","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":["Department of Systems Engineering, Laboratoire d&#x2019;imagerie, de vision et d&#x2019;intelligence artificielle, &#x00C9;cole de technologie sup&#x00E9;rieure, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, Laboratoire d&#x2019;imagerie, de vision et d&#x2019;intelligence artificielle, &#x00C9;cole de technologie sup&#x00E9;rieure, Montreal, Canada","institution_ids":[]}]},{"author_position":"last","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":["Department of Systems Engineering, Laboratoire d&#x2019;imagerie, de vision et d&#x2019;intelligence artificielle, &#x00C9;cole de technologie sup&#x00E9;rieure, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6116-7945","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, Laboratoire d&#x2019;imagerie, de vision et d&#x2019;intelligence artificielle, &#x00C9;cole de technologie sup&#x00E9;rieure, 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":9.7336,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98849245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"5","issue":"3","first_page":"360","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/modalities","display_name":"Modalities","score":0.7898773550987244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7025372385978699},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6828083992004395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5340731739997864},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5280723571777344},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4473874568939209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4423297047615051},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4291410446166992},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4083433449268341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34753191471099854},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12090682983398438}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7898773550987244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025372385978699},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6828083992004395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340731739997864},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5280723571777344},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4473874568939209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4423297047615051},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4291410446166992},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4083433449268341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34753191471099854},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12090682983398438},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tbiom.2022.3233083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbiom.2022.3233083","pdf_url":null,"source":{"id":"https://openalex.org/S4210209367","display_name":"IEEE Transactions on Biometrics Behavior and Identity Science","issn_l":"2637-6407","issn":["2637-6407"],"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 Biometrics, Behavior, and Identity Science","raw_type":"journal-article"},{"id":"pmh:oai:espace2.etsmtl.ca:26260","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/26260/","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":"Article publi\u00e9 dans une revue, r\u00e9vis\u00e9 par les pairs"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334841","display_name":"Fonds de recherche du Qu\u00e9bec \u2013 Nature et technologies","ror":"https://ror.org/00b9f9778"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W6094958","https://openalex.org/W1533861849","https://openalex.org/W1866370351","https://openalex.org/W1965028342","https://openalex.org/W1966797434","https://openalex.org/W1976235033","https://openalex.org/W2021913835","https://openalex.org/W2026243162","https://openalex.org/W2037441721","https://openalex.org/W2045528981","https://openalex.org/W2055098062","https://openalex.org/W2078833921","https://openalex.org/W2080576537","https://openalex.org/W2112173139","https://openalex.org/W2164186291","https://openalex.org/W2194775991","https://openalex.org/W2314395941","https://openalex.org/W2341528187","https://openalex.org/W2346454595","https://openalex.org/W2414857070","https://openalex.org/W2560025328","https://openalex.org/W2606933083","https://openalex.org/W2610961739","https://openalex.org/W2619383789","https://openalex.org/W2619947201","https://openalex.org/W2747664154","https://openalex.org/W2798536775","https://openalex.org/W2886300652","https://openalex.org/W2888786729","https://openalex.org/W2889544113","https://openalex.org/W2895368507","https://openalex.org/W2896323182","https://openalex.org/W2902299888","https://openalex.org/W2962781483","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2980347982","https://openalex.org/W2991485489","https://openalex.org/W2996799978","https://openalex.org/W3005450949","https://openalex.org/W3035333188","https://openalex.org/W3035585099","https://openalex.org/W3035588244","https://openalex.org/W3088950396","https://openalex.org/W3090471441","https://openalex.org/W3094378983","https://openalex.org/W3094524767","https://openalex.org/W3095251683","https://openalex.org/W3096164988","https://openalex.org/W3100513545","https://openalex.org/W3101998545","https://openalex.org/W3118366136","https://openalex.org/W3121375749","https://openalex.org/W3126750668","https://openalex.org/W3128420506","https://openalex.org/W3128692355","https://openalex.org/W3130662682","https://openalex.org/W3137028092","https://openalex.org/W3137646246","https://openalex.org/W3144366453","https://openalex.org/W3155418628","https://openalex.org/W3174906557","https://openalex.org/W3208945181","https://openalex.org/W3209279902","https://openalex.org/W3209397829","https://openalex.org/W3209454485","https://openalex.org/W3211666705","https://openalex.org/W4292794079","https://openalex.org/W4292829055","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6739901393","https://openalex.org/W6767471572","https://openalex.org/W6790875704","https://openalex.org/W6797613833","https://openalex.org/W6955071965"],"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/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Automatic":[0],"emotion":[1],"recognition":[2],"(ER)":[3],"has":[4],"recently":[5],"gained":[6],"much":[7],"interest":[8],"due":[9],"to":[10,25,42,74,129,171],"its":[11],"potential":[12],"in":[13,80],"many":[14],"real-world":[15],"applications.":[16],"In":[17,47,140],"this":[18,48,108],"context,":[19],"multimodal":[20],"approaches":[21],"have":[22],"been":[23],"shown":[24],"improve":[26],"performance":[27,185],"(over":[28],"unimodal":[29],"approaches)":[30],"by":[31],"combining":[32],"diverse":[33],"and":[34,44,61,127,155,177,209],"complementary":[35,68,101],"sources":[36],"of":[37,59,103,157,186,196],"information,":[38],"providing":[39],"some":[40],"robustness":[41],"noisy":[43,235],"missing":[45],"modalities.":[46,105,159],"paper,":[49],"we":[50,110],"focus":[51],"on":[52,56,88,148,203],"dimensional":[53],"ER":[54],"based":[55,147],"the":[57,100,121,132,137,144,151,161,167,175,184,187,190,207,232],"fusion":[58,85,118,219],"facial":[60],"vocal":[62],"modalities":[63,233],"extracted":[64],"from":[65,206],"videos,":[66],"where":[67],"audio-visual":[69],"(A-V)":[70],"relationships":[71],"are":[72,234],"explored":[73],"predict":[75],"an":[76],"individual\u2019s":[77],"emotional":[78],"states":[79],"valence-arousal":[81],"space.":[82],"Most":[83],"state-of-the-art":[84,228],"techniques":[86],"rely":[87],"recurrent":[89],"networks":[90],"or":[91,236],"conventional":[92],"attention":[93],"mechanisms":[94],"that":[95,119,156,214,225],"do":[96],"not":[97],"effectively":[98,130],"leverage":[99,131,173],"nature":[102],"A-V":[104,117,125,163,218],"To":[106],"address":[107],"problem,":[109],"introduce":[111],"a":[112,222],"joint":[113,152,162,216],"cross-attentional":[114,217],"model":[115,220],"for":[116],"extracts":[120],"salient":[122],"features":[123],"across":[124],"modalities,":[126],"allows":[128],"inter-modal":[133],"relationships,":[134,180],"while":[135],"retaining":[136],"intra-modal":[138],"relationships.":[139],"particular,":[141],"it":[142],"computes":[143],"cross-attention":[145,168,192],"weights":[146],"correlation":[149],"between":[150],"feature":[153,164],"representation":[154,165],"individual":[158],"Deploying":[160],"into":[166],"module":[169],"helps":[170],"simultaneously":[172],"both":[174],"intra":[176],"inter":[178],"modal":[179],"thereby":[181],"significantly":[182],"improving":[183],"system":[188],"over":[189],"vanilla":[191],"module.":[193],"The":[194],"effectiveness":[195],"our":[197,215],"proposed":[198],"approach":[199],"is":[200,239],"validated":[201],"experimentally":[202],"challenging":[204],"videos":[205],"RECOLA":[208],"AffWild2":[210],"datasets.":[211],"Results":[212],"indicate":[213],"provides":[221],"cost-effective":[223],"solution":[224],"can":[226],"outperform":[227],"approaches,":[229],"even":[230],"when":[231],"absent.":[237],"Code":[238],"available":[240],"at":[241],"<uri":[242],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[243],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/praveena2j/Joint-Cross-Attention-for-Audio-Visual-Fusion</uri>":[244],".":[245]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}