{"id":"https://openalex.org/W4408352120","doi":"https://doi.org/10.1109/icassp49660.2025.10889156","title":"Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment","display_name":"Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352120","doi":"https://doi.org/10.1109/icassp49660.2025.10889156"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101483730","display_name":"Xuechen Wang","orcid":"https://orcid.org/0000-0002-3584-7821"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuechen Wang","raw_affiliation_strings":["Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035524175","display_name":"Haoqin Sun","orcid":"https://orcid.org/0000-0002-8554-8969"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqin Sun","raw_affiliation_strings":["Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460850","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8814-1988"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086127472","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0000-0002-9298-4347"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102006082","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0001-9808-0456"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101483730"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":11.1655,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98233141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"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":0.9537000060081482,"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":0.9537000060081482,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.8026428818702698},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7421634197235107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7011352777481079},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4324072003364563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4207783341407776},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10111653804779053}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8026428818702698},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7421634197235107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011352777481079},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4324072003364563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4207783341407776},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10111653804779053},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":27,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2147934395","https://openalex.org/W2963270767","https://openalex.org/W2963800675","https://openalex.org/W3095251683","https://openalex.org/W3096963953","https://openalex.org/W3128376221","https://openalex.org/W3163091219","https://openalex.org/W3197977579","https://openalex.org/W4200591749","https://openalex.org/W4224917001","https://openalex.org/W4226425326","https://openalex.org/W4297841589","https://openalex.org/W4372260110","https://openalex.org/W4372260395","https://openalex.org/W4372266552","https://openalex.org/W4372267501","https://openalex.org/W4372347367","https://openalex.org/W4385807537","https://openalex.org/W4385822446","https://openalex.org/W4385822492","https://openalex.org/W4386075815","https://openalex.org/W4392903310","https://openalex.org/W4408353073","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W3105646692","https://openalex.org/W4387914125"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"(MER),":[3],"leveraging":[4],"speech":[5],"and":[6,59,84],"text,":[7],"has":[8],"emerged":[9],"as":[10],"a":[11,39,44,70,91],"pivotal":[12],"domain":[13],"within":[14],"human-computer":[15],"interaction,":[16],"demanding":[17],"sophisticated":[18],"methods":[19],"for":[20],"effective":[21],"multimodal":[22],"integration.":[23],"The":[24],"challenge":[25],"of":[26,94],"aligning":[27],"features":[28],"across":[29,97],"these":[30],"modalities":[31],"is":[32],"significant,":[33],"with":[34],"most":[35],"existing":[36],"approaches":[37],"adopting":[38],"singular":[40],"alignment":[41,86],"strategy.":[42],"Such":[43],"narrow":[45],"focus":[46],"not":[47],"only":[48],"limits":[49],"model":[50],"performance":[51],"but":[52],"also":[53],"fails":[54],"to":[55],"address":[56],"the":[57],"complexity":[58],"ambiguity":[60],"inherent":[61],"in":[62],"emotional":[63,95],"expressions.":[64],"In":[65],"response,":[66],"this":[67],"paper":[68],"introduces":[69],"Multi-Granularity":[71],"Cross-Modal":[72],"Alignment":[73],"(MGCMA)":[74],"framework,":[75],"distinguished":[76],"by":[77],"its":[78],"comprehensive":[79],"approach":[80],"encompassing":[81],"distribution-based,":[82],"instance-based,":[83],"token-based":[85],"modules.":[87],"This":[88],"framework":[89],"enables":[90],"multi-level":[92],"perception":[93],"information":[96],"modalities.":[98],"Our":[99],"experiments":[100],"on":[101],"IEMOCAP":[102],"demonstrate":[103],"that":[104],"our":[105],"proposed":[106],"method":[107],"outperforms":[108],"current":[109],"state-of-the-art":[110],"techniques.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}