{"id":"https://openalex.org/W4387967914","doi":"https://doi.org/10.1145/3581783.3612517","title":"Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation","display_name":"Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967914","doi":"https://doi.org/10.1145/3581783.3612517"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5078148438","display_name":"Sidharth Anand","orcid":"https://orcid.org/0000-0001-5750-6860"},"institutions":[{"id":"https://openalex.org/I4210101034","display_name":"Birla Institute of Technology and Science - Hyderabad Campus","ror":"https://ror.org/014ctt859","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101034","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sidharth Anand","raw_affiliation_strings":["BITS Pilani, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-5750-6860","affiliations":[{"raw_affiliation_string":"BITS Pilani, Hyderabad, India","institution_ids":["https://openalex.org/I4210101034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087498355","display_name":"Naresh Kumar Devulapally","orcid":"https://orcid.org/0000-0003-3114-1044"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naresh Kumar Devulapally","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3114-1044","affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102791840","display_name":"Sreyasee Das Bhattacharjee","orcid":"https://orcid.org/0000-0001-5393-0840"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyasee Das Bhattacharjee","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5393-0840","affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":null,"display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7901-8793"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-7901-8793","affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078148438"],"corresponding_institution_ids":["https://openalex.org/I4210101034"],"apc_list":null,"apc_paid":null,"fwci":5.2091,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96030012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6090","last_page":"6100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9947999715805054,"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":0.9941999912261963,"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":0.7312154769897461},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6950478553771973},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6896765828132629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557224690914154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5386014580726624},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42786848545074463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35278820991516113},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3502243161201477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312154769897461},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6950478553771973},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6896765828132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557224690914154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5386014580726624},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42786848545074463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35278820991516113},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3502243161201477},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332641","display_name":"University at Buffalo","ror":"https://ror.org/01y64my43"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1763311249","https://openalex.org/W2031822154","https://openalex.org/W2133782814","https://openalex.org/W2168465881","https://openalex.org/W2252920314","https://openalex.org/W2546919788","https://openalex.org/W2547246052","https://openalex.org/W2583643061","https://openalex.org/W2619383789","https://openalex.org/W2883409523","https://openalex.org/W2891359673","https://openalex.org/W2964300796","https://openalex.org/W2971092323","https://openalex.org/W2980906155","https://openalex.org/W2997258743","https://openalex.org/W3003317175","https://openalex.org/W3034266838","https://openalex.org/W3037309139","https://openalex.org/W3037572520","https://openalex.org/W3093051361","https://openalex.org/W3102187622","https://openalex.org/W3120680448","https://openalex.org/W3123554940","https://openalex.org/W3127463063","https://openalex.org/W3128412859","https://openalex.org/W3168258251","https://openalex.org/W3170360335","https://openalex.org/W3171558850","https://openalex.org/W3176028309","https://openalex.org/W4205727320","https://openalex.org/W4210389516","https://openalex.org/W4214612132","https://openalex.org/W4281701185","https://openalex.org/W4297094917","https://openalex.org/W4300772090","https://openalex.org/W4309947032","https://openalex.org/W4310007437","https://openalex.org/W4311057028","https://openalex.org/W4312706447","https://openalex.org/W4319878207","https://openalex.org/W4321442004","https://openalex.org/W6695661434"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W1527532029","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2772323916","https://openalex.org/W2281307425","https://openalex.org/W1511346092","https://openalex.org/W2464405057"],"abstract_inverted_index":{"Evaluating":[0],"speaker":[1,75,173],"emotion":[2,71],"in":[3,73,112,225],"conversations":[4],"is":[5,81,159,191],"crucial":[6],"for":[7,88,132],"various":[8],"applications":[9],"requiring":[10],"human-computer":[11],"interaction.":[12],"However,":[13],"co-occurrences":[14],"of":[15,32,49],"multiple":[16,117,134],"emotional":[17],"states":[18],"(e.g.":[19],"'anger'":[20],"and":[21,35,53,56,216,240],"'frustration'":[22],"may":[23,28,39],"occur":[24],"together":[25],"or":[26],"one":[27],"influence":[29,48],"the":[30,33,44,61,69,143,148,152,168,199,204,226],"occurrence":[31],"other)":[34],"their":[36,50,187],"dynamic":[37],"evolution":[38],"vary":[40],"dramatically":[41],"due":[42],"to":[43,83,166,184],"speaker's":[45],"internal":[46],"(e.g.,":[47,213],"personalized":[51],"socio-cultural-educational":[52],"demographic":[54],"backgrounds)":[55],"external":[57],"contexts.":[58],"Thus":[59],"far,":[60],"previous":[62],"focus":[63],"has":[64],"been":[65],"on":[66,208],"evaluating":[67],"only":[68,202],"dominant":[70],"observed":[72],"a":[74,77,127,162],"at":[76],"given":[78],"time,":[79],"which":[80,113],"susceptible":[82],"producing":[84],"misleading":[85],"classification":[86],"decisions":[87],"difficult":[89],"multi-labels":[90],"during":[91],"testing.":[92],"In":[93,197],"this":[94],"work,":[95],"we":[96],"present":[97],"Self-supervised":[98],"Multi-":[99],"Label":[100],"Peer":[101],"Collaborative":[102],"Distillation":[103,140],"(SeMuL-PCD)":[104],"Learning":[105],"via":[106],"an":[107,234],"efficient":[108],"Multimodal":[109,139],"Transformer":[110],"Network,":[111],"complementary":[114],"feedback":[115],"from":[116],"mode-specific":[118,188],"peer":[119,153,157,177],"networks":[120],"(e.g.transcript,":[121],"audio,":[122],"visual)":[123],"are":[124],"distilled":[125],"into":[126],"single":[128],"mode-ensembled":[129],"fusion":[130,144],"network":[131,145,158,183],"estimating":[133],"emotions":[135],"simultaneously.":[136],"The":[137,230],"proposed":[138],"Loss":[141],"calibrates":[142],"by":[146],"minimizing":[147],"Kullback-Leibler":[149],"divergence":[150],"with":[151,219],"networks.":[154],"Additionally,":[155],"each":[156,182],"conditioned":[160],"using":[161],"self-supervised":[163],"contrastive":[164],"objective":[165],"improve":[167],"generalization":[169,236],"across":[170,193,238],"diverse":[171],"socio-demographic":[172],"backgrounds.":[174],"By":[175],"enabling":[176],"collaborative":[178],"learning":[179],"that":[180],"allows":[181],"independently":[185],"learn":[186],"discriminative":[189],"patterns,SeMUL-PCD":[190],"effective":[192],"different":[194],"conversation":[195],"environments.":[196],"particular,":[198],"model":[200,231],"not":[201],"outperforms":[203],"current":[205],"state-of-the-art":[206],"models":[207],"several":[209],"large-scale":[210],"public":[211],"datasets":[212],"MOSEI,":[214],"EmoReact":[215],"ElderReact),":[217],"but":[218],"around":[220],"17%":[221],"improved":[222],"weighted":[223],"F1-score":[224],"cross-dataset":[227],"experimental":[228],"settings.":[229],"also":[232],"demonstrates":[233],"impressive":[235],"ability":[237],"age":[239],"demography-diverse":[241],"populations.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}