{"id":"https://openalex.org/W4224916778","doi":"https://doi.org/10.1109/icassp43922.2022.9746924","title":"Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?","display_name":"Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916778","doi":"https://doi.org/10.1109/icassp43922.2022.9746924"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746924","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/A5071287333","display_name":"Vandana Rajan","orcid":"https://orcid.org/0000-0002-2250-1688"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vandana Rajan","raw_affiliation_strings":["Queen Mary University of London,Centre for Intelligent Sensing,UK","Centre for Intelligent Sensing, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Intelligent Sensing,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Intelligent Sensing, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066363315","display_name":"Alessio Brutti","orcid":"https://orcid.org/0000-0003-4146-3071"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Brutti","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy","Fondazione Bruno Kessler, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004087827","display_name":"Andrea Cavallaro","orcid":"https://orcid.org/0000-0001-5086-7858"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Cavallaro","raw_affiliation_strings":["Queen Mary University of London,Centre for Intelligent Sensing,UK","Centre for Intelligent Sensing, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Intelligent Sensing,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Intelligent Sensing, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071287333"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":5.3788,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96470588,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4693","last_page":"4697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10057","display_name":"Face and Expression Recognition","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8017711639404297},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7068490982055664},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6534947752952576},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5850719809532166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565029382705688},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5045405626296997},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4923485517501831},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47205716371536255},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.445857971906662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42064422369003296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3837254047393799},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3413146734237671}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017711639404297},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7068490982055664},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6534947752952576},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5850719809532166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565029382705688},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5045405626296997},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4923485517501831},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47205716371536255},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.445857971906662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42064422369003296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3837254047393799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3413146734237671},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746924","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":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1606749791","https://openalex.org/W1614298861","https://openalex.org/W2033773055","https://openalex.org/W2133564696","https://openalex.org/W2146334809","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2399733683","https://openalex.org/W2610961739","https://openalex.org/W2619383789","https://openalex.org/W2885005742","https://openalex.org/W2899771611","https://openalex.org/W2937584914","https://openalex.org/W2962770129","https://openalex.org/W2964051877","https://openalex.org/W2976196855","https://openalex.org/W3015906487","https://openalex.org/W3016138882","https://openalex.org/W3160183718","https://openalex.org/W4287029753","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6756040250","https://openalex.org/W6799510764"],"related_works":["https://openalex.org/W2613123485","https://openalex.org/W4205137593","https://openalex.org/W2952745240","https://openalex.org/W4236838349","https://openalex.org/W2949074159","https://openalex.org/W4301143707","https://openalex.org/W4298715519","https://openalex.org/W2012466265","https://openalex.org/W2546942002","https://openalex.org/W2921079524"],"abstract_inverted_index":{"Humans":[0],"express":[1],"their":[2,48,173],"emotions":[3],"via":[4],"facial":[5],"expressions,":[6],"voice":[7],"intonation":[8],"and":[9,31,104,108,125,165,170],"word":[10],"choices.":[11],"To":[12,99],"infer":[13],"the":[14,17,86,95,134,147,159,183],"nature":[15],"of":[16,36,163],"underlying":[18],"emotion,":[19],"recognition":[20],"models":[21,39,135,156],"may":[22],"use":[23],"a":[24,34,52,90,106,109,141],"single":[25],"modality,":[26],"such":[27,89],"as":[28,74],"vision,":[29],"audio,":[30],"text,":[32],"or":[33],"combination":[35],"modalities.":[37],"Generally,":[38],"that":[40,55,60,88,153],"fuse":[41],"complementary":[42],"information":[43,65],"from":[44,66],"multiple":[45],"modalities":[46,57],"outperform":[47],"uni-modal":[49],"counterparts.":[50],"However,":[51],"successful":[53],"model":[54,117],"fuses":[56],"requires":[58],"components":[59],"can":[61],"effectively":[62],"aggregate":[63],"task-relevant":[64],"each":[67,116],"modality.":[68],"As":[69],"cross-modal":[70],"attention":[71],"is":[72,175,185],"seen":[73],"an":[75],"effective":[76],"mechanism":[77,91],"for":[78,121,128,140,168],"multi-modal":[79],"fusion,":[80],"in":[81,161],"this":[82,100],"paper":[83],"we":[84,102],"quantify":[85],"gain":[87],"brings":[92],"compared":[93],"to":[94,114,181],"corresponding":[96],"self-attention":[97,110],"mechanism.":[98],"end,":[101],"implement":[103],"compare":[105,133],"cross-attention":[107],"model.":[111],"In":[112],"addition":[113],"attention,":[115],"uses":[118],"convolutional":[119],"layers":[120,127],"local":[122],"feature":[123],"extraction":[124],"recurrent":[126],"global":[129],"sequential":[130],"modelling.":[131],"We":[132],"using":[136,146],"different":[137],"modality":[138],"combinations":[139],"7-class":[142],"emotion":[143],"classification":[144],"task":[145],"IEMOCAP":[148],"dataset.":[149],"Experimental":[150],"results":[151],"indicate":[152],"albeit":[154],"both":[155],"improve":[157],"upon":[158],"state-of-the-art":[160],"terms":[162],"weighted":[164],"unweighted":[166],"accuracy":[167],"tri-":[169],"bi-modal":[171],"configurations,":[172],"performance":[174],"generally":[176],"statistically":[177],"comparable.":[178],"The":[179],"code":[180],"replicate":[182],"experiments":[184],"available":[186],"at":[187],"https://github.com/smartcameras/SelfCrossAttn":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}