{"id":"https://openalex.org/W4372260110","doi":"https://doi.org/10.1109/icassp49357.2023.10095855","title":"MGAT: Multi-Granularity Attention Based Transformers for Multi-Modal Emotion Recognition","display_name":"MGAT: Multi-Granularity Attention Based Transformers for Multi-Modal Emotion Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260110","doi":"https://doi.org/10.1109/icassp49357.2023.10095855"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5026460226","display_name":"Weiquan Fan","orcid":"https://orcid.org/0000-0002-8006-7947"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiquan Fan","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China","School of Electronic and Information Engineering, South China University of Technology, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036301580","display_name":"Xiaofen Xing","orcid":"https://orcid.org/0000-0002-0016-9055"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofen Xing","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China","School of Electronic and Information Engineering, South China University of Technology, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063210263","display_name":"Bolun Cai","orcid":"https://orcid.org/0000-0002-9394-7820"},"institutions":[{"id":"https://openalex.org/I106994412","display_name":"Sinopec (China)","ror":"https://ror.org/0161q6d74","country_code":"CN","type":"company","lineage":["https://openalex.org/I106994412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolun Cai","raw_affiliation_strings":["Shopee Video Intelligence,China","Shopee Video Intelligence, China"],"affiliations":[{"raw_affiliation_string":"Shopee Video Intelligence,China","institution_ids":["https://openalex.org/I106994412"]},{"raw_affiliation_string":"Shopee Video Intelligence, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033271721","display_name":"Xiangmin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["South China University of Technology,School of Future Technology,China","School of Future Technology, South China University of Technology, China","Pazhou Lab, Guangzhou, PR, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Future Technology,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Future Technology, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Pazhou Lab, Guangzhou, PR, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026460226"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":2.6081,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8897335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":1.0,"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":1.0,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9926000237464905,"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"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.8217242360115051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242693901062012},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7038966417312622},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.63770592212677},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.48308470845222473},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4664705693721771},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4337219297885895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3598668575286865},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13319486379623413},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11557364463806152},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09288877248764038}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8217242360115051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242693901062012},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7038966417312622},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.63770592212677},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.48308470845222473},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4664705693721771},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4337219297885895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3598668575286865},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13319486379623413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11557364463806152},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09288877248764038},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2896457183","https://openalex.org/W2963270767","https://openalex.org/W2964300796","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3015240477","https://openalex.org/W3036601975","https://openalex.org/W3096039514","https://openalex.org/W3096963953","https://openalex.org/W3117020206","https://openalex.org/W3128376221","https://openalex.org/W3128513378","https://openalex.org/W3132302778","https://openalex.org/W3161659450","https://openalex.org/W3162475537","https://openalex.org/W3173751215","https://openalex.org/W3198791972","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4212774754","https://openalex.org/W4214825215","https://openalex.org/W4221162874","https://openalex.org/W4224917001","https://openalex.org/W4226025958","https://openalex.org/W4285106979","https://openalex.org/W4297841880","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6803680838"],"related_works":["https://openalex.org/W4386721968","https://openalex.org/W2952745240","https://openalex.org/W2949074159","https://openalex.org/W4301143707","https://openalex.org/W4298715519","https://openalex.org/W3198037411","https://openalex.org/W2474574787","https://openalex.org/W4306353150","https://openalex.org/W3142456083","https://openalex.org/W4226120250"],"abstract_inverted_index":{"Multi-modal":[0],"emotion":[1],"recognition":[2],"is":[3,72,124],"crucial":[4],"for":[5],"human-computer":[6],"interaction.":[7],"Many":[8],"existing":[9],"algorithms":[10],"attempt":[11],"to":[12,21,54,74],"achieve":[13],"multi-modal":[14,62],"interactions":[15],"through":[16,107],"a":[17,39,87,108],"cross-attention":[18],"mechanism.":[19,111],"Due":[20],"the":[22,31,92,100,115,121],"problems":[23],"of":[24,117],"noise":[25],"introduction":[26],"and":[27,90,103,120],"heavy":[28],"computation":[29],"in":[30],"original":[32],"attention":[33,36,94,110],"mechanism,":[34],"window":[35,70],"has":[37],"become":[38],"new":[40],"trend.":[41],"However,":[42],"emotions":[43],"are":[44,64],"presented":[45],"asynchronously":[46],"between":[47,59],"different":[48],"modalities,":[49],"which":[50],"makes":[51],"it":[52],"difficult":[53],"interact":[55],"with":[56],"emotional":[57,101],"information":[58],"windows.":[60],"Furthermore,":[61],"data":[63],"temporally":[65],"misaligned,":[66],"so":[67],"single":[68],"fixed":[69],"size":[71],"hard":[73],"describe":[75],"cross-modal":[76],"information.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81],"put":[82],"these":[83],"two":[84],"issues":[85,106],"into":[86],"unified":[88],"framework":[89],"propose":[91],"multi-granularity":[93,109],"based":[95],"Transformers":[96],"(MGAT).":[97],"It":[98],"addresses":[99],"asynchrony":[102],"modality":[104],"misalignment":[105],"Experimental":[112],"results":[113],"confirm":[114],"effectiveness":[116],"our":[118],"method":[119],"state-of-the-art":[122],"performance":[123],"achieved":[125],"on":[126],"IEMOCAP.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}