{"id":"https://openalex.org/W4224932526","doi":"https://doi.org/10.1109/icassp43922.2022.9747157","title":"AuxFormer: Robust Approach to Audiovisual Emotion Recognition","display_name":"AuxFormer: Robust Approach to Audiovisual Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932526","doi":"https://doi.org/10.1109/icassp43922.2022.9747157"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747157","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/A5017966455","display_name":"Lucas Goncalves","orcid":"https://orcid.org/0000-0001-9613-1002"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lucas Goncalves","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017966455"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":4.7103,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95948617,"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":"7357","last_page":"7361"},"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":0.9991000294685364,"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":0.9948999881744385,"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":0.8244662284851074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966387271881104},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6601385474205017},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6006251573562622},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5770052075386047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5316641330718994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5305873155593872},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5121940970420837},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5071978569030762},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.498091459274292},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.48635298013687134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3996102809906006},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37990936636924744},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07984361052513123}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8244662284851074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966387271881104},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6601385474205017},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6006251573562622},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5770052075386047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5316641330718994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5305873155593872},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5121940970420837},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5071978569030762},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.498091459274292},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.48635298013687134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3996102809906006},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37990936636924744},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07984361052513123},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747157","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1976725440","https://openalex.org/W2012237712","https://openalex.org/W2030931454","https://openalex.org/W2080830759","https://openalex.org/W2096391593","https://openalex.org/W2097117768","https://openalex.org/W2144005487","https://openalex.org/W2145295623","https://openalex.org/W2155765376","https://openalex.org/W2163026698","https://openalex.org/W2193145675","https://openalex.org/W2325939864","https://openalex.org/W2342475039","https://openalex.org/W2525412388","https://openalex.org/W2790326622","https://openalex.org/W2897067191","https://openalex.org/W2963702064","https://openalex.org/W2964051877","https://openalex.org/W2964266095","https://openalex.org/W2972602947","https://openalex.org/W3007589762","https://openalex.org/W3034266838","https://openalex.org/W3035118106","https://openalex.org/W3106250896","https://openalex.org/W3114214226","https://openalex.org/W4385245566","https://openalex.org/W6641446668","https://openalex.org/W6739901393","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W2154469718","https://openalex.org/W4308080854","https://openalex.org/W4383993410","https://openalex.org/W4200381230","https://openalex.org/W3171735296","https://openalex.org/W4287204696","https://openalex.org/W3153347230","https://openalex.org/W4293518096","https://openalex.org/W3211951101","https://openalex.org/W4310877696"],"abstract_inverted_index":{"A":[0,55],"challenging":[1],"task":[2],"in":[3,83],"audiovisual":[4,116],"emotion":[5,52],"recognition":[6,53],"is":[7,62,200],"to":[8,42,47,58,63,68,102,119,202],"implement":[9],"neural":[10],"network":[11,122],"architectures":[12],"that":[13,108,125,135,181,191],"can":[14],"leverage":[15],"and":[16,27,46,71,141,146,161,166,208],"fuse":[17,70],"multimodal":[18,60],"information":[19,29,35,104,117,124],"while":[20],"temporally":[21],"aligning":[22],"modalities,":[23,26],"handling":[24],"missing":[25,196],"capturing":[28],"from":[30,105,185,212],"all":[31],"modalities":[32],"without":[33],"losing":[34],"during":[36,130],"training.":[37,131],"These":[38],"requirements":[39],"are":[40,109,174],"important":[41],"achieve":[43],"model":[44],"robustness":[45],"increase":[48],"accuracy":[49],"on":[50,149],"the":[51,65,73,78,87,92,136,150,154],"task.":[54],"recent":[56],"approach":[57],"perform":[59],"fusion":[61],"use":[64],"transformer":[66,93],"architecture":[67,138,199],"properly":[69],"align":[72],"modalities.":[74],"This":[75],"study":[76],"proposes":[77],"AuxFormer":[79,90,137,157],"framework,":[80],"which":[81],"addresses":[82],"a":[84,159,213],"principled":[85],"way":[86],"aforementioned":[88],"challenges.":[89],"combines":[91],"framework":[94,183],"with":[95],"auxiliary":[96,186],"networks.":[97,187],"It":[98],"uses":[99],"shared":[100],"losses":[101],"infuse":[103],"single-modality":[106],"networks":[107],"separately":[110],"embedded.":[111],"The":[112,132,169],"extra":[113],"layer":[114],"of":[115,144,164],"added":[118],"our":[120,182,198],"main":[121],"retains":[123],"would":[126],"otherwise":[127],"be":[128],"lost":[129],"results":[133,170],"show":[134,190],"achieves":[139,158],"macro":[140,160],"micro":[142,162],"F1Scores":[143],"71.3%":[145],"71.7%,":[147],"respectively,":[148],"CREMA-D":[151],"corpus.":[152],"For":[153],"MSP-IMPROV":[155],"corpus,":[156],"F1-Scores":[163],"70.4%":[165],"76.5%,":[167],"respectively.":[168],"for":[171],"both":[172],"corpora":[173],"significantly":[175],"better":[176],"than":[177],"strong":[178,204],"baselines,":[179],"indicating":[180],"benefits":[184],"We":[188],"also":[189],"under":[192,206],"non-ideal":[193],"conditions":[194],"(e.g.,":[195],"modalities)":[197],"able":[201],"sustain":[203],"performance":[205],"audio-only":[207],"video-only":[209],"scenarios,":[210],"benefiting":[211],"optimized":[214],"training":[215],"strategy.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}