{"id":"https://openalex.org/W4367281761","doi":"https://doi.org/10.1109/tmm.2023.3271019","title":"A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations","display_name":"A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations","publication_year":2023,"publication_date":"2023-04-27","ids":{"openalex":"https://openalex.org/W4367281761","doi":"https://doi.org/10.1109/tmm.2023.3271019"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3271019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3271019","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.20494","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100452344","display_name":"Hui Ma","orcid":"https://orcid.org/0000-0002-7146-8036"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ma","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-7146-8036","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370452","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-4656-7446"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4656-7446","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-0872-7688","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077216037","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-6933-922X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6933-922X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046020427","display_name":"Yijia Zhang","orcid":"https://orcid.org/0000-0002-5843-4675"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijia Zhang","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-5843-4675","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062895972","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-5453-978X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-978X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.5188,"has_fulltext":true,"cited_by_count":140,"citation_normalized_percentile":{"value":0.9983352,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"776","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9975000023841858,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.984499990940094,"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/computer-science","display_name":"Computer science","score":0.7897180914878845},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6909758448600769},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6259252429008484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5557248592376709},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4920894503593445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4358363449573517},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42686235904693604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34697550535202026},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3324839472770691},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09288862347602844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0821598470211029},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08010983467102051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897180914878845},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6909758448600769},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6259252429008484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5557248592376709},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4920894503593445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4358363449573517},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42686235904693604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34697550535202026},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3324839472770691},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09288862347602844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0821598470211029},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08010983467102051},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2023.3271019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3271019","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2310.20494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.20494","pdf_url":"https://arxiv.org/pdf/2310.20494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.20494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.20494","pdf_url":"https://arxiv.org/pdf/2310.20494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1570808242","display_name":null,"funder_award_id":"2021-BS-067","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G571088143","display_name":null,"funder_award_id":"DUT21RC(3)015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7575631531","display_name":null,"funder_award_id":"62006034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367281761.pdf","grobid_xml":"https://content.openalex.org/works/W4367281761.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1832693441","https://openalex.org/W1987030537","https://openalex.org/W2079725295","https://openalex.org/W2090777335","https://openalex.org/W2102953093","https://openalex.org/W2146334809","https://openalex.org/W2158943324","https://openalex.org/W2184126968","https://openalex.org/W2187089797","https://openalex.org/W2546919788","https://openalex.org/W2583643061","https://openalex.org/W2620998106","https://openalex.org/W2739879705","https://openalex.org/W2787581402","https://openalex.org/W2805662932","https://openalex.org/W2886193235","https://openalex.org/W2886300652","https://openalex.org/W2887783173","https://openalex.org/W2891359673","https://openalex.org/W2896457183","https://openalex.org/W2939362715","https://openalex.org/W2963128932","https://openalex.org/W2963446712","https://openalex.org/W2963686995","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964300796","https://openalex.org/W2964346351","https://openalex.org/W2965373594","https://openalex.org/W2981441441","https://openalex.org/W2982605440","https://openalex.org/W2985882473","https://openalex.org/W2987861506","https://openalex.org/W2996849360","https://openalex.org/W2997224071","https://openalex.org/W2998563994","https://openalex.org/W3034266838","https://openalex.org/W3034342078","https://openalex.org/W3034756453","https://openalex.org/W3040953174","https://openalex.org/W3094378983","https://openalex.org/W3096318498","https://openalex.org/W3098556456","https://openalex.org/W3116016199","https://openalex.org/W3128412859","https://openalex.org/W3137028092","https://openalex.org/W3173396651","https://openalex.org/W3174340663","https://openalex.org/W3203741465","https://openalex.org/W3205421042","https://openalex.org/W3206201541","https://openalex.org/W3207810231","https://openalex.org/W3211488063","https://openalex.org/W3216650611","https://openalex.org/W3217114103","https://openalex.org/W4221154966","https://openalex.org/W4303649263","https://openalex.org/W4309427394","https://openalex.org/W4385245566","https://openalex.org/W4385573848","https://openalex.org/W6631190155","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6766673545","https://openalex.org/W6772695483","https://openalex.org/W6805026025"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,47],"in":[2,14,48,70],"conversations":[3],"(ERC),":[4],"the":[5,9,34,39,101,142,162],"task":[6],"of":[7,11,41,141,156],"recognizing":[8],"emotion":[10,46],"each":[12,166],"utterance":[13],"a":[15,78,125],"conversation,":[16],"is":[17,95],"crucial":[18],"for":[19,100],"building":[20],"empathetic":[21],"machines.":[22],"Existing":[23],"studies":[24],"focus":[25],"mainly":[26],"on":[27,33,169],"capturing":[28,51],"context-":[29],"and":[30,53,63,108,114,117,158,171],"speaker-sensitive":[31],"dependencies":[32],"textual":[35,49],"modality":[36],"but":[37],"ignore":[38],"significance":[40],"multimodal":[42,71],"information.":[43],"Different":[44],"from":[45,161],"conversations,":[50],"intra-":[52,107,113],"inter-modal":[54,109,115],"interactions":[55,110],"between":[56,60,120],"utterances,":[57],"learning":[58],"weights":[59,119],"different":[61],"modalities,":[62],"enhancing":[64],"modal":[65,135],"representations":[66],"play":[67],"important":[68],"roles":[69],"ERC.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,137,150],"propose":[77],"transformer-based":[79,104],"model":[80,105,144,164],"with":[81],"self-distillation":[82,152],"(SDT)":[83],"<xref":[84],"ref-type=\"fn\"":[85],"rid=\"fn1\"":[86],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[87,91],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><sup>1</sup></xref>":[88],"<fn":[89],"id=\"fn1\"":[90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><label><sup>1</sup></label>":[92],"The":[93,103],"code":[94],"available":[96],"at":[97],"<uri>https://github.com/butterfliesss/SDT</uri>.":[98],"</fn>":[99],"task.":[102],"captures":[106],"by":[111,123],"utilizing":[112],"transformers,":[116],"learns":[118],"modalities":[121],"dynamically":[122],"designing":[124],"hierarchical":[126],"gated":[127],"fusion":[128],"strategy.":[129],"Furthermore,":[130],"to":[131,153,165],"learn":[132],"more":[133],"expressive":[134],"representations,":[136],"treat":[138],"soft":[139,159],"labels":[140,160],"proposed":[143,163],"as":[145],"extra":[146],"training":[147],"supervision.":[148],"Specifically,":[149],"introduce":[151],"transfer":[154],"knowledge":[155],"hard":[157],"modality.":[167],"Experiments":[168],"IEMOCAP":[170],"MELD":[172],"datasets":[173],"demonstrate":[174],"that":[175],"SDT":[176],"outperforms":[177],"previous":[178],"state-of-the-art":[179],"baselines.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":41},{"year":2025,"cited_by_count":75},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2023-04-29T00:00:00"}
