{"id":"https://openalex.org/W4409660542","doi":"https://doi.org/10.1109/icit63637.2025.10965274","title":"Multimodal Emotion Recognition Based on Multi-Scale Facial Features and Cross-Modal Attention","display_name":"Multimodal Emotion Recognition Based on Multi-Scale Facial Features and Cross-Modal Attention","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4409660542","doi":"https://doi.org/10.1109/icit63637.2025.10965274"},"language":"en","primary_location":{"id":"doi:10.1109/icit63637.2025.10965274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit63637.2025.10965274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Industrial Technology (ICIT)","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":null,"display_name":"Chengao Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengao Bao","raw_affiliation_strings":["School of Automation, China University of Geosciences,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, China University of Geosciences,Wuhan,China,430074","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029643093","display_name":"Luefeng Chen","orcid":"https://orcid.org/0000-0003-3571-7493"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luefeng Chen","raw_affiliation_strings":["School of Automation, China University of Geosciences,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, China University of Geosciences,Wuhan,China,430074","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400746","display_name":"Min Li","orcid":"https://orcid.org/0000-0002-5773-8976"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["School of Automation, China University of Geosciences,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, China University of Geosciences,Wuhan,China,430074","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074710425","display_name":"Min Wu","orcid":"https://orcid.org/0000-0002-0668-8315"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Wu","raw_affiliation_strings":["School of Automation, China University of Geosciences,Wuhan,China,430074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, China University of Geosciences,Wuhan,China,430074","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003799782","display_name":"Witold Pedrycz","orcid":"https://orcid.org/0000-0002-9335-9930"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Witold Pedrycz","raw_affiliation_strings":["University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Canada,AB T6R 2G7"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Canada,AB T6R 2G7","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065389686","display_name":"Kaoru Hirota","orcid":"https://orcid.org/0000-0002-8118-9815"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaoru Hirota","raw_affiliation_strings":["Tokyo Institute of Technology,Yokohama,Japan,226-8502"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Yokohama,Japan,226-8502","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5119,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92067443,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.650600016117096,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.650600016117096,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.608299970626831,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.6061999797821045,"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/emotion-recognition","display_name":"Emotion recognition","score":0.6982293725013733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6976211667060852},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6404834389686584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5068607926368713},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4693663418292999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4620136320590973},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45919880270957947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35625791549682617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3434116244316101}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6982293725013733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6976211667060852},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6404834389686584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5068607926368713},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4693663418292999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4620136320590973},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45919880270957947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35625791549682617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434116244316101},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit63637.2025.10965274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit63637.2025.10965274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Industrial Technology (ICIT)","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":15,"referenced_works":["https://openalex.org/W1965947362","https://openalex.org/W1966797434","https://openalex.org/W2168692779","https://openalex.org/W2322480645","https://openalex.org/W2551403050","https://openalex.org/W2889544113","https://openalex.org/W3016138882","https://openalex.org/W3081192838","https://openalex.org/W3131500599","https://openalex.org/W3188758222","https://openalex.org/W4224221948","https://openalex.org/W4286544676","https://openalex.org/W4380153859","https://openalex.org/W4380320096","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"A":[0],"multi-modal":[1],"emotion":[2,95],"recognition":[3],"method":[4,118],"based":[5],"on":[6,119],"facial":[7],"multi-scale":[8],"features":[9,58,91],"and":[10,85,89,105,122,127],"cross-modal":[11,65],"attention":[12,66],"(MS-FCA)":[13],"network":[14,25],"is":[15,68,125],"proposed.":[16],"The":[17,64,108],"MSFCA":[18],"model":[19],"improves":[20],"the":[21,44,72,102,113,116,120,132,135],"traditional":[22],"single-branch":[23],"ViT":[24,29],"into":[26],"a":[27],"two-branch":[28],"architecture":[30],"by":[31],"using":[32,61],"classification":[33],"tokens":[34],"in":[35,43],"each":[36],"branch":[37],"to":[38,70],"interact":[39],"with":[40],"picture":[41],"embeddings":[42],"other":[45],"branch,":[46],"which":[47,130],"facilitates":[48],"effective":[49],"interactions":[50],"between":[51,75],"different":[52,76],"scales":[53],"of":[54,82,115,134],"information.":[55],"Subsequently,":[56],"audio":[57,90],"are":[59,99],"extracted":[60],"ResNet18":[62],"network.":[63],"mechanism":[67],"used":[69,100],"obtain":[71],"weight":[73],"matrices":[74],"modal":[77],"features,":[78],"making":[79],"full":[80],"use":[81],"inter-modal":[83],"correlation":[84],"effectively":[86],"fusing":[87],"visual":[88],"for":[92,101],"more":[93],"accurate":[94],"recognition.":[96],"Two":[97],"datasets":[98,124],"experiments:":[103],"eNTERFACE'05":[104,121],"REDVESS":[106,123],"dataset.":[107],"experimental":[109],"results":[110],"show":[111],"that":[112],"accuracy":[114],"proposed":[117,136],"85.42%":[126],"83.84%":[128],"respectively,":[129],"proves":[131],"effectiveness":[133],"method.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}