{"id":"https://openalex.org/W4390905815","doi":"https://doi.org/10.1109/aciiw59127.2023.10388147","title":"Mutual Cross-Attention in Dyadic Fusion Networks for Audio-Video Emotion Recognition","display_name":"Mutual Cross-Attention in Dyadic Fusion Networks for Audio-Video Emotion Recognition","publication_year":2023,"publication_date":"2023-09-10","ids":{"openalex":"https://openalex.org/W4390905815","doi":"https://doi.org/10.1109/aciiw59127.2023.10388147"},"language":"en","primary_location":{"id":"doi:10.1109/aciiw59127.2023.10388147","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aciiw59127.2023.10388147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 11th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","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/A5056746787","display_name":"Jiachen Luo","orcid":null},"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":"Jiachen Luo","raw_affiliation_strings":["Centre for Digital Music Queen Mary U. of London,London,UK","Centre for Digital Music Queen Mary U. of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music Queen Mary U. of London,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music Queen Mary U. of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Amazon Alexa,Cambridge,MA,USA","Amazon Alexa, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403109","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0001-8095-9518"},"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":"Lin Wang","raw_affiliation_strings":["Centre for Digital Music Queen Mary U. of London,London,UK","Centre for Digital Music Queen Mary U. of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music Queen Mary U. of London,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music Queen Mary U. of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403298","display_name":"Joshua D. Reiss","orcid":null},"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":"Joshua Reiss","raw_affiliation_strings":["Centre for Digital Music Queen Mary U. of London,London,UK","Centre for Digital Music Queen Mary U. of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music Queen Mary U. of London,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music Queen Mary U. of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056746787"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24986415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8029952645301819},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6915105581283569},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5952752232551575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5641074180603027},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5440830588340759},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.482552707195282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44665098190307617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029952645301819},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6915105581283569},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5952752232551575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5641074180603027},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5440830588340759},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.482552707195282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44665098190307617},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aciiw59127.2023.10388147","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aciiw59127.2023.10388147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 11th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2546875627","https://openalex.org/W2548128734","https://openalex.org/W2703895418","https://openalex.org/W2740550900","https://openalex.org/W2767488767","https://openalex.org/W2796430037","https://openalex.org/W2804748097","https://openalex.org/W2950978907","https://openalex.org/W2954548939","https://openalex.org/W2963686995","https://openalex.org/W2969889150","https://openalex.org/W2973049979","https://openalex.org/W2997399314","https://openalex.org/W2998796500","https://openalex.org/W3137028092","https://openalex.org/W3160183718","https://openalex.org/W3161565210","https://openalex.org/W3188183700","https://openalex.org/W3193484423","https://openalex.org/W3201068280","https://openalex.org/W3205314427","https://openalex.org/W4206157917","https://openalex.org/W4220887861","https://openalex.org/W4221154966","https://openalex.org/W4281701185","https://openalex.org/W4310007381","https://openalex.org/W4360930863","https://openalex.org/W4376278471","https://openalex.org/W6751830489"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,36],"recognition":[2],"is":[3,29],"a":[4,21,90,135],"challenging":[5],"problem":[6,33],"in":[7,48,134],"the":[8,25,61,93,98,107,129,140,143,147,152,159],"research":[9],"fields":[10],"of":[11,63,128],"human-computer":[12],"interaction":[13,62],"and":[14,60,71,80,101,123,131,146],"pattern":[15],"recognition.":[16,37],"How":[17],"to":[18,53,76],"efficiently":[19],"find":[20],"common":[22],"subspace":[23],"among":[24,106],"heterogeneous":[26],"multimodal":[27],"data":[28],"still":[30],"an":[31,43,49],"open":[32],"for":[34],"audio-video":[35,45,64,108],"In":[38],"this":[39],"work,":[40],"we":[41],"propose":[42],"attentive":[44,55],"fusion":[46,87],"network":[47],"emotional":[50],"dialogue":[51],"system":[52],"learn":[54,124],"contextual":[56,118],"dependency,":[57],"speaker":[58,121],"information,":[59,119],"modalities.":[65],"We":[66,138],"employ":[67],"pre-trained":[68],"models,":[69],"wav2vec,":[70],"Distract":[72],"your":[73],"Attention":[74],"Network,":[75],"extract":[77],"high-level":[78],"audio":[79,130],"video":[81,132],"representations,":[82],"respectively.":[83],"By":[84],"using":[85],"weighted":[86],"based":[88],"on":[89,97,142,158],"cross-attention":[91],"module,":[92],"cross-modality":[94],"encoder":[95],"focuses":[96],"inter-modality":[99],"relations":[100],"selectively":[102],"captures":[103],"effective":[104],"information":[105],"modality.":[109],"Specifically,":[110],"bidirectional":[111],"gated":[112],"recurrent":[113],"unit":[114],"models":[115],"capture":[116],"long-term":[117],"explore":[120],"influence,":[122],"intra-and":[125],"inter-modal":[126],"interactions":[127],"modalities":[133],"dynamic":[136],"manner.":[137],"evaluate":[139],"approach":[141,154],"MELD":[144],"dataset,":[145],"experimental":[148],"results":[149],"show":[150],"that":[151],"proposed":[153],"achieves":[155],"state-of-the-art":[156],"performance":[157],"dataset.":[160]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}