{"id":"https://openalex.org/W4415708821","doi":"https://doi.org/10.1109/icme59968.2025.11209909","title":"Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion","display_name":"Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708821","doi":"https://doi.org/10.1109/icme59968.2025.11209909"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209909","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 Multimedia and Expo (ICME)","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/A5061078777","display_name":"Jiagen Li","orcid":"https://orcid.org/0000-0001-8084-1560"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]},{"id":"https://openalex.org/I78974044","display_name":"East China University of Political Science and Law","ror":"https://ror.org/01d1erx18","country_code":"CN","type":"education","lineage":["https://openalex.org/I78974044"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiagen Li","raw_affiliation_strings":["East China University of Science and Technology,Dept. School of Information Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Dept. School of Information Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I143593769","https://openalex.org/I78974044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110365337","display_name":"Rui Yu","orcid":"https://orcid.org/0000-0001-8500-0955"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]},{"id":"https://openalex.org/I78974044","display_name":"East China University of Political Science and Law","ror":"https://ror.org/01d1erx18","country_code":"CN","type":"education","lineage":["https://openalex.org/I78974044"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yu","raw_affiliation_strings":["East China University of Science and Technology,Dept. School of Information Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Dept. School of Information Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I143593769","https://openalex.org/I78974044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078471793","display_name":"Huihao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihao Huang","raw_affiliation_strings":["South China Agricultural University,Dept. School of Mathematics and Informatics,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Dept. School of Mathematics and Informatics,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079742998","display_name":"Huaicheng Yan","orcid":"https://orcid.org/0000-0001-5496-1809"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]},{"id":"https://openalex.org/I78974044","display_name":"East China University of Political Science and Law","ror":"https://ror.org/01d1erx18","country_code":"CN","type":"education","lineage":["https://openalex.org/I78974044"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaicheng Yan","raw_affiliation_strings":["East China University of Science and Technology,Dept. School of Information Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Dept. School of Information Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I143593769","https://openalex.org/I78974044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4863,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94773809,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9790999889373779,"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":0.9790999889373779,"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/T12031","display_name":"Speech and dialogue systems","score":0.004100000020116568,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0032999999821186066,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5558000206947327},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4846999943256378},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.460999995470047},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4498000144958496},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.41839998960494995},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.40560001134872437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394000291824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6315000057220459},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.477400004863739},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209909","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321881","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457"},{"id":"https://openalex.org/F4320326149","display_name":"Shanghai International Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2886300652","https://openalex.org/W2963686995","https://openalex.org/W2963702064","https://openalex.org/W2964300796","https://openalex.org/W2985882473","https://openalex.org/W3120680448","https://openalex.org/W3137028092","https://openalex.org/W3173396651","https://openalex.org/W3199262595","https://openalex.org/W4221147459","https://openalex.org/W4221163935","https://openalex.org/W4367281761","https://openalex.org/W4385571916","https://openalex.org/W4389519350","https://openalex.org/W4402772396"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Emotion":[1],"Recognition":[2],"in":[3,39,116,132],"Conversations":[4],"(MERC)":[5],"identifies":[6],"emotional":[7],"states":[8],"across":[9],"text,":[10],"audio":[11],"and":[12,21,46,71,101,118,124,135],"video,":[13],"which":[14,106],"is":[15],"essential":[16],"for":[17,31,85,95],"intelligent":[18],"dialogue":[19],"systems":[20],"opinion":[22],"analysis.":[23],"Existing":[24],"methods":[25],"emphasize":[26],"heterogeneous":[27,59,99],"modal":[28,44],"fusion":[29,97,115],"directly":[30],"cross-modal":[32],"integration,":[33],"but":[34],"often":[35],"suffer":[36],"from":[37],"disorientation":[38],"multimodal":[40,60,114],"learning":[41],"due":[42],"to":[43,112],"heterogeneity":[45],"lack":[47],"of":[48,65,82,98],"instructive":[49],"guidance.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"propose":[55],"SUMMER,":[56],"a":[57,78,90,108],"novel":[58],"integration":[61],"framework":[62],"leveraging":[63],"Mixture":[64,81],"Experts":[66,83],"with":[67],"Hierarchical":[68,91],"Cross-modal":[69],"Fusion":[70,93],"Interactive":[72,102],"Knowledge":[73,103],"Distillation.":[74],"Key":[75],"components":[76],"include":[77],"Sparse":[79],"Dynamic":[80],"(SDMoE)":[84],"capturing":[86],"dynamic":[87],"token-wise":[88],"interactions,":[89],"Cross-Modal":[92],"(HCMF)":[94],"effective":[96],"modalities,":[100],"Distillation":[104],"(IKD),":[105],"uses":[107],"pretrained":[109],"unimodal":[110],"teacher":[111],"guide":[113],"latent":[117],"logit":[119],"spaces.":[120],"Experiments":[121],"on":[122],"IEMOCAP":[123],"MELD":[125],"show":[126],"SUMMER":[127],"outperforms":[128],"state-of-the-art":[129],"methods,":[130],"particularly":[131],"recognizing":[133],"minority":[134],"semantically":[136],"similar":[137],"emotions.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}
