{"id":"https://openalex.org/W3211666705","doi":"https://doi.org/10.1109/fg52635.2021.9667055","title":"Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition","display_name":"Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W3211666705","doi":"https://doi.org/10.1109/fg52635.2021.9667055","mag":"3211666705"},"language":"en","primary_location":{"id":"doi:10.1109/fg52635.2021.9667055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg52635.2021.9667055","pdf_url":null,"source":{"id":"https://openalex.org/S4363608446","display_name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","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":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"R. Gnana Praveen","raw_affiliation_strings":["Laboratoire d'imagerie, de vision et d'intelligence artificielle (LIVIA), \u00c9cole de technologie sup\u00e9rieure, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'imagerie, de vision et d'intelligence artificielle (LIVIA), \u00c9cole de technologie sup\u00e9rieure, Montreal, Canada","institution_ids":["https://openalex.org/I9736820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006937759","display_name":"\u00c9ric Granger","orcid":"https://orcid.org/0000-0001-6116-7945"},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eric Granger","raw_affiliation_strings":["Laboratoire d'imagerie, de vision et d'intelligence artificielle (LIVIA), \u00c9cole de technologie sup\u00e9rieure, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'imagerie, de vision et d'intelligence artificielle (LIVIA), \u00c9cole de technologie sup\u00e9rieure, Montreal, Canada","institution_ids":["https://openalex.org/I9736820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051056084","display_name":"Patrick Cardinal","orcid":"https://orcid.org/0009-0000-9439-9910"},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Cardinal","raw_affiliation_strings":["Laboratoire d'imagerie, de vision et d'intelligence artificielle (LIVIA), \u00c9cole de technologie sup\u00e9rieure, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'imagerie, de vision et d'intelligence artificielle (LIVIA), \u00c9cole de technologie sup\u00e9rieure, Montreal, Canada","institution_ids":["https://openalex.org/I9736820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9736820"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9944000244140625,"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":0.8245960474014282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269258499145508},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6889179944992065},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5634720325469971},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5458604693412781},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.5326836705207825},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.528958797454834},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.5046521425247192},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4966753125190735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4900413751602173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48900043964385986},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4417804777622223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4393843710422516},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.415256142616272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3606317639350891},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33360499143600464},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0956522524356842}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8245960474014282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269258499145508},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6889179944992065},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5634720325469971},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5458604693412781},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.5326836705207825},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.528958797454834},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.5046521425247192},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4966753125190735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4900413751602173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48900043964385986},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4417804777622223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4393843710422516},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.415256142616272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3606317639350891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33360499143600464},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0956522524356842},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fg52635.2021.9667055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg52635.2021.9667055","pdf_url":null,"source":{"id":"https://openalex.org/S4363608446","display_name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:espace2.etsmtl.ca:24080","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/24080/","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":51,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1866370351","https://openalex.org/W1976235033","https://openalex.org/W2012237712","https://openalex.org/W2021913835","https://openalex.org/W2026243162","https://openalex.org/W2037441721","https://openalex.org/W2045528981","https://openalex.org/W2080576537","https://openalex.org/W2105020570","https://openalex.org/W2164186291","https://openalex.org/W2314395941","https://openalex.org/W2341528187","https://openalex.org/W2346454595","https://openalex.org/W2560025328","https://openalex.org/W2606933083","https://openalex.org/W2610961739","https://openalex.org/W2613677041","https://openalex.org/W2619383789","https://openalex.org/W2626778328","https://openalex.org/W2747664154","https://openalex.org/W2886300652","https://openalex.org/W2889544113","https://openalex.org/W2896323182","https://openalex.org/W2949296282","https://openalex.org/W2962781483","https://openalex.org/W2963524571","https://openalex.org/W2971035910","https://openalex.org/W2980347982","https://openalex.org/W2991485489","https://openalex.org/W2996799978","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/W3101998545","https://openalex.org/W3121375749","https://openalex.org/W3130662682","https://openalex.org/W3137028092","https://openalex.org/W3137646246","https://openalex.org/W3144366453","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6739901393","https://openalex.org/W6767471572","https://openalex.org/W6784766212","https://openalex.org/W6790875704"],"related_works":["https://openalex.org/W4362650935","https://openalex.org/W3080495370","https://openalex.org/W2904925713","https://openalex.org/W4285597148","https://openalex.org/W2901531394","https://openalex.org/W2083738729","https://openalex.org/W2964266095","https://openalex.org/W4310841718","https://openalex.org/W2798573901","https://openalex.org/W2978360381"],"abstract_inverted_index":{"Multimodal":[0],"analysis":[1],"has":[2],"recently":[3],"drawn":[4],"much":[5],"interest":[6],"in":[7],"affective":[8],"computing,":[9],"since":[10],"it":[11,148],"can":[12],"improve":[13],"the":[14,63,82,99,114,143,155,177,186,195],"overall":[15],"accuracy":[16],"of":[17,38,65,81,102,126,129,179,185],"emotion":[18,30,59],"recognition":[19,31,60],"over":[20],"isolated":[21],"uni-modal":[22],"approaches.":[23,219],"The":[24,183],"most":[25],"effective":[26],"techniques":[27,85],"for":[28,123,176],"multimodal":[29],"efficiently":[32,141],"leverage":[33,98],"diverse":[34],"and":[35,44,67,131,162,181,197],"complimentary":[36,100],"sources":[37],"information,":[39],"such":[40],"as":[41],"facial,":[42],"vocal,":[43],"physiological":[45],"modalities,":[46,121,161],"to":[47,112,152,172],"provide":[48],"comprehensive":[49],"feature":[50,166],"representations.":[51],"In":[52,146],"this":[53],"paper,":[54],"we":[55],"focus":[56,153],"on":[57,62,87,154,192],"dimensional":[58],"based":[61],"fusion":[64,84,110,139,209,218],"facial":[66],"vocal":[68],"modalities":[69],"extracted":[70],"from":[71,194],"videos,":[72],"where":[73],"complex":[74],"spatiotemporal":[75],"relationships":[76],"may":[77],"be":[78],"captured.":[79],"Most":[80],"existing":[83],"rely":[86],"recurrent":[88],"networks":[89],"or":[90],"conventional":[91],"attention":[92],"mechanisms":[93],"that":[94,203,215],"do":[95],"not":[96],"effectively":[97],"nature":[101],"audiovisual":[103],"(A-V)":[104],"modalities.":[105],"We":[106],"introduce":[107],"a":[108,212],"cross-attentional":[109,135,205],"approach":[111,188,214],"extract":[113],"salient":[115],"features":[116,158],"across":[117,159],"A":[118,136,206],"-":[119,137,207],"V":[120,138,208],"allowing":[122],"accurate":[124],"prediction":[125,178],"continuous":[127],"values":[128],"valence":[130,180],"arousal.":[132,182],"Our":[133],"new":[134],"model":[140,210],"leverages":[142],"inter-modal":[144],"relationships.":[145],"particular,":[147],"computes":[149],"cross-attention":[150],"weights":[151],"more":[156],"contributive":[157,165],"individual":[160],"thereby":[163],"combine":[164],"representations,":[167],"which":[168],"are":[169],"then":[170],"fed":[171],"fully":[173],"connected":[174],"layers":[175],"effectiveness":[184],"proposed":[187],"is":[189,211,221],"validated":[190],"experimentally":[191],"videos":[193],"RECOLA":[196],"Fatigue":[198],"(private)":[199],"data-sets.":[200],"Results":[201],"indicate":[202],"our":[204],"cost-effective":[213],"outperforms":[216],"state-of-the-art":[217],"Code":[220],"available:":[222],"https://github.com/praveena2j/Cross-Attentional-AV-Fusion.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}