{"id":"https://openalex.org/W4387969351","doi":"https://doi.org/10.1145/3581783.3611805","title":"Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation","display_name":"Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969351","doi":"https://doi.org/10.1145/3581783.3611805"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611805","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":"conference-paper","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/A5076465587","display_name":"Shihao Zou","orcid":"https://orcid.org/0000-0002-6648-3995"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Zou","raw_affiliation_strings":["Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-6648-3995","affiliations":[{"raw_affiliation_string":"Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073610035","display_name":"Xianying Huang","orcid":"https://orcid.org/0000-0002-3667-6198"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianying Huang","raw_affiliation_strings":["Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-3667-6198","affiliations":[{"raw_affiliation_string":"Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102994819","display_name":"Xudong Shen","orcid":"https://orcid.org/0009-0008-0583-9717"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Shen","raw_affiliation_strings":["Chongqing University of Technology, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0008-0583-9717","affiliations":[{"raw_affiliation_string":"Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50632499"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5994","last_page":"6003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9801999926567078,"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":0.7440347671508789},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.654491126537323},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6317158937454224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6032634973526001},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5354599952697754},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49618250131607056},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48097100853919983},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.47829657793045044},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4682876467704773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39141547679901123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37064844369888306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.354564905166626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3501841425895691},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0935879647731781},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08237975835800171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440347671508789},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.654491126537323},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6317158937454224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032634973526001},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5354599952697754},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49618250131607056},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48097100853919983},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.47829657793045044},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4682876467704773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39141547679901123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37064844369888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.354564905166626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3501841425895691},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0935879647731781},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08237975835800171},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611805","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/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G2796437284","display_name":null,"funder_award_id":"CSTB2022NSCQ","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G6882169372","display_name":null,"funder_award_id":"62141201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G811181622","display_name":null,"funder_award_id":"CSTB2022NSCQ-MSX1672","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321135","display_name":"Chongqing University","ror":"https://ror.org/023rhb549"},{"id":"https://openalex.org/F4320322955","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327639","display_name":"Centre Scientifique et Technique du B\u00e2timent","ror":"https://ror.org/02fsd1928"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2085662862","https://openalex.org/W2113491937","https://openalex.org/W2146334809","https://openalex.org/W2740550900","https://openalex.org/W2805662932","https://openalex.org/W2891359673","https://openalex.org/W2962739339","https://openalex.org/W2963446712","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W3034999214","https://openalex.org/W3037611961","https://openalex.org/W3092695663","https://openalex.org/W3099056802","https://openalex.org/W3167098825","https://openalex.org/W3175552668","https://openalex.org/W3176849538","https://openalex.org/W3214432797","https://openalex.org/W3216650611","https://openalex.org/W4214689917","https://openalex.org/W4221154966","https://openalex.org/W4226025958","https://openalex.org/W4248168528","https://openalex.org/W4287887917","https://openalex.org/W4303649263","https://openalex.org/W4313639237","https://openalex.org/W6600895146"],"related_works":["https://openalex.org/W4389505417","https://openalex.org/W2962931510","https://openalex.org/W4380551887","https://openalex.org/W4285159263","https://openalex.org/W2904518532","https://openalex.org/W4280529741","https://openalex.org/W4293919860","https://openalex.org/W2963650472","https://openalex.org/W4387634401","https://openalex.org/W4401552326"],"abstract_inverted_index":{"Emotion":[0],"Recognition":[1],"in":[2,9,19,33,131,205],"Conversation":[3],"(ERC)":[4],"plays":[5],"an":[6],"important":[7],"role":[8],"driving":[10],"the":[11,30,34,41,63,70,124,151,159,176,188],"development":[12],"of":[13,44,65,123,179,190],"human-machine":[14],"interaction.":[15],"Emotions":[16],"can":[17],"exist":[18],"multiple":[20],"modalities,":[21],"and":[22,39,60,86,135,182],"multimodal":[23,92,116,145,180],"ERC":[24,206],"mainly":[25],"faces":[26],"two":[27,208],"problems:":[28],"(1)":[29],"noise":[31],"problem":[32,43],"cross-modal":[35,111],"information":[36,94,112,118,128,141,189],"fusion":[37,117,146,181],"process,":[38],"(2)":[40],"prediction":[42],"less":[45],"sample":[46],"emotion":[47,75],"labels":[48,164,191],"that":[49,198],"are":[50],"semantically":[51],"similar":[52],"but":[53],"different":[54],"categories.":[55],"To":[56],"address":[57],"these":[58],"issues":[59],"fully":[61],"utilize":[62],"features":[64,134],"each":[66,120],"modality,":[67],"we":[68,102,149],"adopted":[69],"following":[71],"strategies:":[72],"first,":[73],"deep":[74],"cues":[76],"extraction":[77],"was":[78],"performed":[79],"on":[80,207],"modalities":[81,96],"with":[82,97,138,165,192],"strong":[83],"representation":[84,99,177],"ability,":[85],"feature":[87],"filters":[88],"were":[89],"designed":[90,103],"as":[91],"prompt":[93,127],"for":[95],"weak":[98],"ability.":[100],"Then,":[101],"a":[104],"Multimodal":[105],"Prompt":[106],"Transformer":[107],"(MPT)":[108],"to":[109,129,142,157,162,174,186],"perform":[110],"fusion.":[113],"MPT":[114],"embeds":[115],"into":[119],"attention":[121],"layer":[122],"Transformer,":[125],"allowing":[126],"participate":[130],"encoding":[132],"textual":[133,140],"being":[136],"fused":[137],"multi-level":[139],"obtain":[143],"better":[144],"features.":[147],"Finally,":[148],"used":[150],"Hybrid":[152],"Contrastive":[153],"Learning":[154],"(HCL)":[155],"strategy":[156,169],"optimize":[158],"model's":[160],"ability":[161,178],"handle":[163],"few":[166,193],"samples.":[167,194],"This":[168],"uses":[170],"unsupervised":[171],"contrastive":[172,184],"learning":[173,185],"improve":[175],"supervised":[183],"mine":[187],"Experimental":[195],"results":[196],"show":[197],"our":[199],"proposed":[200],"model":[201],"outperforms":[202],"state-of-the-art":[203],"models":[204],"benchmark":[209],"datasets.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}