{"id":"https://openalex.org/W4392909359","doi":"https://doi.org/10.1109/icassp48485.2024.10447035","title":"Fusing Modality-Specific Representations and Decisions for Multimodal Emotion Recognition","display_name":"Fusing Modality-Specific Representations and Decisions for Multimodal Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909359","doi":"https://doi.org/10.1109/icassp48485.2024.10447035"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447035","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/A5054105228","display_name":"Yu-Ping Ruan","orcid":"https://orcid.org/0000-0002-9800-3271"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Ping Ruan","raw_affiliation_strings":["Zhejiang Lab,Hangzhou,P.R. China","Zhejiang Lab, Hangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Hangzhou,P.R. China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031301468","display_name":"Shoukang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoukang Han","raw_affiliation_strings":["Zhejiang Lab,Hangzhou,P.R. China","Zhejiang Lab, Hangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Hangzhou,P.R. China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021697903","display_name":"Taihao Li","orcid":"https://orcid.org/0000-0003-3279-7125"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taihao Li","raw_affiliation_strings":["Zhejiang Lab,Hangzhou,P.R. China","Zhejiang Lab, Hangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Hangzhou,P.R. China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049638215","display_name":"Yanfeng Wu","orcid":"https://orcid.org/0000-0002-1498-9177"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wu","raw_affiliation_strings":["Zhejiang Lab,Hangzhou,P.R. China","Zhejiang Lab, Hangzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Hangzhou,P.R. China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, P.R. China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":1.9325,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85065034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7925","last_page":"7929"},"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":0.9986000061035156,"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":0.9781000018119812,"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":0.8572138547897339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7381508946418762},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7204602956771851},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7030722498893738},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6987786889076233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922221541404724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4478239119052887},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4457443952560425},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3273891806602478},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06986552476882935}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8572138547897339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381508946418762},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7204602956771851},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7030722498893738},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6987786889076233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922221541404724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4478239119052887},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4457443952560425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3273891806602478},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06986552476882935},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/icassp48485.2024.10447035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447035","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":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307500","display_name":"Youth Foundation","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2074788634","https://openalex.org/W2194775991","https://openalex.org/W2883409523","https://openalex.org/W2896457183","https://openalex.org/W2955429306","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964346351","https://openalex.org/W2969889150","https://openalex.org/W2973049979","https://openalex.org/W2997258743","https://openalex.org/W3034323190","https://openalex.org/W3034849760","https://openalex.org/W3128412859","https://openalex.org/W3169801598","https://openalex.org/W3203381531","https://openalex.org/W4206326349","https://openalex.org/W4225275170","https://openalex.org/W4308222497","https://openalex.org/W4385245566","https://openalex.org/W4385571170","https://openalex.org/W6755207826"],"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/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"(MER)":[3],"is":[4,37],"important":[5,38],"for":[6,39,74,86,123,142,163],"building":[7],"humanoid":[8],"chatbots":[9],"and":[10,31,58,84,90,103,108,115,155],"has":[11,65],"gained":[12],"increasing":[13],"attention":[14],"in":[15,49,110],"recent":[16],"years.":[17],"Existing":[18],"studies":[19],"have":[20],"proven":[21],"that":[22],"extracting":[23],"better":[24],"modality-specific":[25,56,63,82,106,161],"representations,":[26,57],"which":[27],"keep":[28],"both":[29,80],"commonality":[30],"individuality":[32],"information":[33],"of":[34,61,150,159],"different":[35],"modalities,":[36],"the":[40,59,62,75,81,87,105,118,124,148,157,164],"MER":[41,88,133,165],"task.":[42,166],"However,":[43],"all":[44],"these":[45],"works":[46],"are":[47,129],"restricted":[48],"making":[50],"final":[51,125],"predictions":[52],"based":[53],"on":[54,131],"fusing":[55,94],"effectiveness":[60,158],"decisions":[64,85,109,162],"not":[66],"been":[67],"studied.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"first":[76,101],"time":[77],"to":[78],"fuse":[79],"representations":[83,107],"task":[89],"design":[91],"a":[92,98],"bi-channel":[93],"network":[95],"(BCFN).":[96],"Specifically,":[97],"BCFN":[99,153],"model":[100,154],"extracts":[102],"mixes":[104],"two":[111,119,132],"convolutional":[112],"blocks":[113],"respectively,":[114],"then":[116],"fuses":[117],"joint":[120],"multimodal":[121],"features":[122],"decision.":[126],"Extensive":[127],"experiments":[128],"conducted":[130],"benchmark":[134],"datasets":[135],"with":[136],"state-of-the-art":[137],"models":[138],"employed":[139],"as":[140],"baselines":[141],"comparison.":[143],"The":[144],"empirical":[145],"results":[146],"demonstrate":[147],"superiority":[149],"our":[151],"proposed":[152],"confirm":[156],"incorporating":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}