{"id":"https://openalex.org/W3083650259","doi":"https://doi.org/10.1145/3394171.3413579","title":"Semi-supervised Multi-modal Emotion Recognition with Cross-Modal Distribution Matching","display_name":"Semi-supervised Multi-modal Emotion Recognition with Cross-Modal Distribution Matching","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3083650259","doi":"https://doi.org/10.1145/3394171.3413579","mag":"3083650259"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413579","doi":"https://doi.org/10.1145/3394171.3413579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413579","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.02598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101063775","display_name":"Jingjun Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjun Liang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074740984","display_name":"Ruichen Li","orcid":"https://orcid.org/0009-0003-8396-1084","observed_orcids":["https://orcid.org/0009-0003-8396-1084"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichen Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020","observed_orcids":["https://orcid.org/0000-0001-6486-6020"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":8.7767,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98086246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2852","last_page":"2861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0012000000569969416,"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/T10201","display_name":"Speech Recognition and Synthesis","score":9.999999747378752e-05,"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/emotion-recognition","display_name":"emotion recognition","score":0.8809999823570251},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.8880000114440918},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.765999972820282},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.8970000147819519},{"id":"https://openalex.org/keywords/limited-annotations","display_name":"limited annotations","score":0.42800000309944153},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.7979999780654907},{"id":"https://openalex.org/keywords/meld","display_name":"MELD","score":0.953000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214116096496582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144924759864807},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5949797034263611},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5801469087600708},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5693478584289551},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5623542070388794},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5268834233283997},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5022001266479492},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43360480666160583},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42693305015563965},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41655975580215454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3394171.3413579","doi":"https://doi.org/10.1145/3394171.3413579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413579","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.02598","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02598","pdf_url":"https://arxiv.org/pdf/2009.02598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2009.02598","doi":"https://doi.org/10.48550/arxiv.2009.02598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.02598","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.02598","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02598","pdf_url":"https://arxiv.org/pdf/2009.02598","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1491334068","https://openalex.org/W1779010541","https://openalex.org/W1966797434","https://openalex.org/W1974647172","https://openalex.org/W1976235033","https://openalex.org/W1987048275","https://openalex.org/W2003653478","https://openalex.org/W2032254851","https://openalex.org/W2077674591","https://openalex.org/W2080830759","https://openalex.org/W2085662862","https://openalex.org/W2099471712","https://openalex.org/W2113516703","https://openalex.org/W2116435618","https://openalex.org/W2123442489","https://openalex.org/W2124509324","https://openalex.org/W2125336414","https://openalex.org/W2146334809","https://openalex.org/W2170707709","https://openalex.org/W2397302540","https://openalex.org/W2432004435","https://openalex.org/W2461972671","https://openalex.org/W2474425654","https://openalex.org/W2481681431","https://openalex.org/W2523915246","https://openalex.org/W2531648894","https://openalex.org/W2604394529","https://openalex.org/W2626778328","https://openalex.org/W2740550900","https://openalex.org/W2765291577","https://openalex.org/W2791177851","https://openalex.org/W2805662932","https://openalex.org/W2886300652","https://openalex.org/W2887761937","https://openalex.org/W2891359673","https://openalex.org/W2895615590","https://openalex.org/W2896457183","https://openalex.org/W2897191477","https://openalex.org/W2913932916","https://openalex.org/W2947476638","https://openalex.org/W2962718314","https://openalex.org/W2962931510","https://openalex.org/W2963446712","https://openalex.org/W2963569749","https://openalex.org/W2964266095","https://openalex.org/W2964300796","https://openalex.org/W2965453734","https://openalex.org/W2966518489","https://openalex.org/W2972452068","https://openalex.org/W2972463723","https://openalex.org/W2981433620"],"related_works":["https://openalex.org/W4387698265","https://openalex.org/W2609485381","https://openalex.org/W4411599800","https://openalex.org/W3011140723","https://openalex.org/W4206326349","https://openalex.org/W4403863516","https://openalex.org/W4387968030","https://openalex.org/W4387698231","https://openalex.org/W4387969409","https://openalex.org/W4388191637"],"abstract_inverted_index":{"Automatic":[0],"emotion":[1,27,101,172],"recognition":[2,28,102,173],"is":[3,30,43,127],"an":[4],"active":[5],"research":[6],"topic":[7],"with":[8,49,192],"wide":[9],"range":[10],"of":[11,26,39,75,198],"applications.":[12],"Due":[13],"to":[14,45,59,114,139,169],"the":[15,24,40,73,116,120,123,130,141,156,171,181],"high":[16],"manual":[17],"annotation":[18],"cost":[19],"and":[20,35,68,149,166,205],"inevitable":[21],"label":[22],"ambiguity,":[23],"development":[25],"dataset":[29],"limited":[31,50],"in":[32],"both":[33],"scale":[34],"quality.":[36],"Therefore,":[37],"one":[38],"key":[41],"challenges":[42],"how":[44],"build":[46],"effective":[47],"models":[48],"data":[51,64,113,165],"resource.":[52],"Previous":[53],"works":[54],"have":[55],"explored":[56],"different":[57],"approaches":[58,78,179,194],"tackle":[60],"this":[61,93],"challenge":[62],"including":[63],"enhancement,":[65],"transfer":[66],"learning,":[67],"semi-supervised":[69,99,158],"learning":[70,159],"etc.":[71],"However,":[72],"weakness":[74],"these":[76],"existing":[77,193],"includes":[79],"such":[80,202],"as":[81,203],"training":[82,118],"instability,":[83],"large":[84],"performance":[85],"loss":[86],"during":[87],"transfer,":[88],"or":[89],"marginal":[90],"improvement.":[91],"In":[92],"work,":[94],"we":[95],"propose":[96],"a":[97],"novel":[98],"multi-modal":[100],"model":[103,117,143,160,186],"based":[104],"on":[105,144],"cross-modality":[106],"distribution":[107],"matching,":[108],"which":[109,175,195],"leverages":[110],"abundant":[111],"unlabeled":[112,164],"enhance":[115],"under":[119,180],"assumption":[121],"that":[122,155],"inner":[124],"emotional":[125],"status":[126],"consistent":[128],"at":[129],"utterance":[131],"level":[132],"across":[133],"modalities.":[134],"We":[135],"conduct":[136],"extensive":[137],"experiments":[138],"evaluate":[140],"proposed":[142,157,185],"two":[145],"benchmark":[146],"datasets,":[147],"IEMOCAP":[148],"MELD.":[150],"The":[151,184],"experiment":[152],"results":[153],"prove":[154],"can":[161],"effectively":[162],"utilize":[163],"combine":[167],"multi-modalities":[168],"boost":[170],"performance,":[174],"outperforms":[176],"other":[177],"state-of-the-art":[178],"same":[182],"condition.":[183],"also":[187],"achieves":[188],"competitive":[189],"capacity":[190],"compared":[191],"take":[196],"advantage":[197],"additional":[199],"auxiliary":[200],"information":[201],"speaker":[204],"interaction":[206],"context.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":8}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2020-09-11T00:00:00"}