{"id":"https://openalex.org/W4392903310","doi":"https://doi.org/10.1109/icassp48485.2024.10447667","title":"Fine-Grained Disentangled Representation Learning For Multimodal Emotion Recognition","display_name":"Fine-Grained Disentangled Representation Learning For Multimodal Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903310","doi":"https://doi.org/10.1109/icassp48485.2024.10447667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":true,"raw_author_name":"Haoqin Sun","raw_affiliation_strings":["Nankai University,Tianjin,China","Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, 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 University,Tianjin,China","Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","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":false,"raw_author_name":"Xuechen Wang","raw_affiliation_strings":["Nankai University,Tianjin,China","Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073069124","display_name":"Wenjia Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjia Zeng","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111320417","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-2497-1843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"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 University,Tianjin,China","Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035524175"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":11.5455,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98849668,"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":"11051","last_page":"11055"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9961000084877014,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9901000261306763,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7700822353363037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7176347374916077},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.713132381439209},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6528796553611755},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6161627173423767},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6052655577659607},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5723479390144348},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5636559128761292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5289663672447205},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5163735151290894},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5157909393310547},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4541075825691223},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36366477608680725},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3269157409667969},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07532212138175964}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7700822353363037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7176347374916077},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.713132381439209},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6528796553611755},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6161627173423767},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6052655577659607},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5723479390144348},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5636559128761292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289663672447205},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5163735151290894},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5157909393310547},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4541075825691223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36366477608680725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3269157409667969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07532212138175964},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1589332668","https://openalex.org/W1731081199","https://openalex.org/W2102953093","https://openalex.org/W2140801466","https://openalex.org/W2146334809","https://openalex.org/W2187089797","https://openalex.org/W2896457183","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W3004205097","https://openalex.org/W3036601975","https://openalex.org/W3093051361","https://openalex.org/W3169801598","https://openalex.org/W4214825215","https://openalex.org/W4221163935","https://openalex.org/W4224920209","https://openalex.org/W4225635674","https://openalex.org/W4297841880","https://openalex.org/W4304092664","https://openalex.org/W4319771047","https://openalex.org/W4372260110","https://openalex.org/W4372347367","https://openalex.org/W4385245566","https://openalex.org/W4385823265","https://openalex.org/W6637618735","https://openalex.org/W6755207826","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3100286349","https://openalex.org/W2896134808","https://openalex.org/W4289378085","https://openalex.org/W4294291164","https://openalex.org/W3172436493","https://openalex.org/W1887135636","https://openalex.org/W4287164812","https://openalex.org/W2386063599","https://openalex.org/W1975884855","https://openalex.org/W3213150849"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"(MMER)":[3],"is":[4],"an":[5],"active":[6],"research":[7],"field":[8],"that":[9,118,137],"aims":[10],"to":[11,50,61,81,96,116],"accurately":[12],"recognize":[13],"human":[14],"emotions":[15],"by":[16],"fusing":[17],"multiple":[18],"perceptual":[19],"modalities.":[20],"However,":[21],"inherent":[22],"heterogeneity":[23],"across":[24],"modalities":[25],"introduces":[26],"distribution":[27],"gaps":[28],"and":[29,58,67,105,145,149],"information":[30],"redundancy,":[31],"posing":[32],"significant":[33],"challenges":[34],"for":[35],"MMER.":[36],"In":[37,71],"this":[38],"paper,":[39],"we":[40,55,75,90,110],"propose":[41],"a":[42,77,92,112],"novel":[43],"fine-grained":[44,78,93,113],"disentangled":[45],"representation":[46],"learning":[47,102],"(FDRL)":[48],"framework":[49],"address":[51],"these":[52],"challenges.":[53],"Specifically,":[54],"design":[56],"modality-shared":[57,66,83],"modality-private":[59,68,103],"encoders":[60,127],"project":[62],"each":[63],"modality":[64],"into":[65],"subspaces,":[69,100],"respectively.":[70,151],"the":[72,98,119,122,126,133,140],"shared":[73],"subspace,":[74],"introduce":[76,111],"alignment":[79],"component":[80,95,115],"learn":[82],"representations,":[84],"thus":[85],"capturing":[86],"modal":[87],"consistency.":[88],"Subsequently,":[89],"tailor":[91],"disparity":[94],"constrain":[97],"private":[99],"thereby":[101],"representations":[104,124],"enhancing":[106],"their":[107],"diversity.":[108],"Lastly,":[109],"predictor":[114],"ensure":[117],"labels":[120],"of":[121],"output":[123],"from":[125],"remain":[128],"unchanged.":[129],"Experimental":[130],"results":[131],"on":[132,147],"IEMOCAP":[134],"dataset":[135],"show":[136],"FDRL":[138],"outperforms":[139],"state-of-the-art":[141],"methods,":[142],"achieving":[143],"78.34%":[144],"79.44%":[146],"WAR":[148],"UAR,":[150]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}