{"id":"https://openalex.org/W4225959162","doi":"https://doi.org/10.1109/icassp43922.2022.9747278","title":"A Pre-Trained Audio-Visual Transformer for Emotion Recognition","display_name":"A Pre-Trained Audio-Visual Transformer for Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225959162","doi":"https://doi.org/10.1109/icassp43922.2022.9747278"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747278","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5101612317","display_name":"Minh Tr\u1ea7n","orcid":"https://orcid.org/0000-0003-4637-6081"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minh Tran","raw_affiliation_strings":["Institute for Creative Technologies University of Southern California,Los Angeles,USA","Institute for Creative Technologies University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Institute for Creative Technologies University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024169758","display_name":"Mohammad Soleymani","orcid":"https://orcid.org/0000-0002-5873-1434"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymani","raw_affiliation_strings":["Institute for Creative Technologies University of Southern California,Los Angeles,USA","Institute for Creative Technologies University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Institute for Creative Technologies University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101612317"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"],"apc_list":null,"apc_paid":null,"fwci":5.5718,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96767875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4698","last_page":"4702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7697708606719971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6339982151985168},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5896282196044922},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5613726377487183},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5510630011558533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.518999457359314},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45815005898475647},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4186314642429352},{"id":"https://openalex.org/keywords/concordance-correlation-coefficient","display_name":"Concordance correlation coefficient","score":0.41331204771995544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3942064344882965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34201183915138245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07663935422897339},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07274088263511658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697708606719971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6339982151985168},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5896282196044922},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5613726377487183},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5510630011558533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.518999457359314},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45815005898475647},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4186314642429352},{"id":"https://openalex.org/C2781059462","wikidata":"https://www.wikidata.org/wiki/Q5158906","display_name":"Concordance correlation coefficient","level":2,"score":0.41331204771995544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3942064344882965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34201183915138245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07663935422897339},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07274088263511658},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747278","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2030931454","https://openalex.org/W2096733369","https://openalex.org/W2194775991","https://openalex.org/W2342475039","https://openalex.org/W2593116425","https://openalex.org/W2747172199","https://openalex.org/W2807126412","https://openalex.org/W2808631503","https://openalex.org/W2896457183","https://openalex.org/W2961193895","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W2973217570","https://openalex.org/W2982223350","https://openalex.org/W2995479270","https://openalex.org/W2997591391","https://openalex.org/W3006926732","https://openalex.org/W3014919073","https://openalex.org/W3016092640","https://openalex.org/W3035265375","https://openalex.org/W3041561163","https://openalex.org/W3049737225","https://openalex.org/W3090471441","https://openalex.org/W3113320078","https://openalex.org/W3148040514","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6704656359","https://openalex.org/W6734260513","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6765307894","https://openalex.org/W6766632297","https://openalex.org/W6766904570","https://openalex.org/W6774092362","https://openalex.org/W6776231833","https://openalex.org/W6787473416"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4286692883","https://openalex.org/W4221161909"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"a":[5,112,139],"pretrained":[6],"audio-visual":[7],"Transformer":[8],"trained":[9,98],"on":[10,55],"more":[11],"than":[12],"500k":[13],"utterances":[14],"from":[15,19,36,99],"nearly":[16],"4000":[17],"celebrities":[18],"the":[20,37,52,72,95,104,108,119,125],"VoxCeleb2":[21],"dataset":[22],"for":[23,147],"human":[24,40],"behavior":[25],"understanding.":[26],"The":[27],"model":[28,53,74,97,110,127],"aims":[29],"to":[30,94,130],"capture":[31],"and":[32,42,62,82,138],"extract":[33],"useful":[34],"information":[35],"interactions":[38],"between":[39],"facial":[41],"auditory":[43],"behaviors,":[44],"with":[45],"application":[46],"in":[47,87,111],"emotion":[48,65,77,89,135,149],"recognition.":[49,150],"We":[50,101],"evaluate":[51],"performance":[54],"two":[56],"datasets,":[57],"namely":[58],"CREMAD-D":[59],"(emotion":[60],"classification)":[61],"MSP-IMPROV":[63],"(continuous":[64],"regression).":[66],"Experimental":[67],"results":[68],"show":[69],"that":[70],"fine-tuning":[71],"pre-trained":[73,109,126],"helps":[75],"improving":[76],"classification":[78],"accuracy":[79,137],"by":[80,91,143],"5-7%":[81],"Concordance":[83],"Correlation":[84],"Coefficients":[85],"(CCC)":[86],"continuous":[88,148],"recognition":[90,136],"0.03-0.09":[92],"compared":[93],"same":[96],"scratch.":[100],"also":[102],"demonstrate":[103],"robustness":[105],"of":[106,118],"finetuning":[107,124],"low-resource":[113],"setting.":[114],"With":[115],"only":[116],"10%":[117,133],"original":[120],"training":[121],"set":[122],"provided,":[123],"can":[128],"lead":[129],"at":[131,144],"least":[132,145],"better":[134],"CCC":[140],"score":[141],"improvement":[142],"0.1":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}