{"id":"https://openalex.org/W4415540054","doi":"https://doi.org/10.1145/3746027.3754758","title":"DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition","display_name":"DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540054","doi":"https://doi.org/10.1145/3746027.3754758"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081285472","display_name":"Peiyuan Jiang","orcid":"https://orcid.org/0009-0003-3913-9333"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peiyuan Jiang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742036","display_name":"Yao Liu","orcid":"https://orcid.org/0000-0001-5342-9896"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Liu","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077109703","display_name":"Qiao Liu","orcid":"https://orcid.org/0000-0002-2573-9544"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Liu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110057860","display_name":"Z. H. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongshun Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002274451","display_name":"Jiaye Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaye Yang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641711","display_name":"Lu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Liu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110681756","display_name":"Daping Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139481","display_name":"Science and Technology Department of Sichuan Province","ror":"https://ror.org/04323m874","country_code":"CN","type":"funder","lineage":["https://openalex.org/I4210139481"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daibing Yao","raw_affiliation_strings":["Yizhou Prison, Sichuan Province, Chengdu, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"Yizhou Prison, Sichuan Province, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I4210139481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5081285472"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.406,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91055822,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"955","last_page":"964"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.782800018787384},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7069000005722046},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6439999938011169},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6067000031471252},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5805000066757202},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.525600016117096},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5023000240325928},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4778999984264374}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.782800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199000120162964},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7069000005722046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6439999938011169},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590399980545044},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45890000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01644","pdf_url":"https://arxiv.org/pdf/2508.01644","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2508.01644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01644","pdf_url":"https://arxiv.org/pdf/2508.01644","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2085662862","https://openalex.org/W2146334809","https://openalex.org/W2619383789","https://openalex.org/W2891359673","https://openalex.org/W2937584914","https://openalex.org/W2944366138","https://openalex.org/W2946545382","https://openalex.org/W2963686995","https://openalex.org/W2964010806","https://openalex.org/W3096963953","https://openalex.org/W3162461068","https://openalex.org/W3163091219","https://openalex.org/W3173396651","https://openalex.org/W3176445421","https://openalex.org/W3183891373","https://openalex.org/W3194998303","https://openalex.org/W3209984917","https://openalex.org/W4206326349","https://openalex.org/W4224916926","https://openalex.org/W4224917001","https://openalex.org/W4224920209","https://openalex.org/W4281397735","https://openalex.org/W4304092664","https://openalex.org/W4306250392","https://openalex.org/W4313457093","https://openalex.org/W4313598803","https://openalex.org/W4321482228","https://openalex.org/W4323050314","https://openalex.org/W4323896824","https://openalex.org/W4382202684","https://openalex.org/W4382237564","https://openalex.org/W4385571916","https://openalex.org/W4385807537","https://openalex.org/W4389752793","https://openalex.org/W4390351000","https://openalex.org/W4392903310","https://openalex.org/W4392903739","https://openalex.org/W4393156571","https://openalex.org/W4397007529","https://openalex.org/W4402955899","https://openalex.org/W4404371462"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"(MER)":[3],"aims":[4],"to":[5,78,110,140],"identify":[6],"emotional":[7,24,105,145],"states":[8],"by":[9,169],"integrating":[10],"and":[11,21,60,83,103,185],"analyzing":[12],"information":[13,71,106],"from":[14,107,119],"multiple":[15],"modalities.":[16],"However,":[17],"inherent":[18],"modality":[19,76,88,102,122],"heterogeneity":[20],"inconsistencies":[22],"in":[23],"cues":[25,143],"remain":[26],"key":[27],"challenges":[28],"that":[29,98,149,176],"hinder":[30],"performance.":[31],"To":[32,115],"address":[33],"these":[34],"issues,":[35],"we":[36,128],"propose":[37],"a":[38,61,68,92],"Decoupled":[39],"Representations":[40],"with":[41,74],"Knowledge":[42,62],"Fusion":[43,63,95],"(DRKF)":[44],"method":[45,73],"for":[46],"MER.":[47],"DRKF":[48,177],"consists":[49],"of":[50,144],"two":[51],"main":[52],"modules:":[53],"an":[54,130,155],"Optimized":[55],"Representation":[56],"Learning":[57],"(ORL)":[58],"Module":[59],"(KF)":[64],"Module.":[65],"ORL":[66],"employs":[67],"contrastive":[69],"mutual":[70],"estimation":[72],"progressive":[75],"augmentation":[77],"decouple":[79],"task-relevant":[80],"shared":[81],"representations":[82],"modality-specific":[84],"features":[85],"while":[86],"mitigating":[87],"heterogeneity.":[89],"KF":[90],"includes":[91],"lightweight":[93],"self-attention-based":[94],"Encoder":[96],"(FE)":[97],"identifies":[99],"the":[100,112,137,152,159],"dominant":[101,121,157],"integrates":[104],"other":[108],"modalities":[109],"enhance":[111],"fused":[113,138],"representation.":[114],"handle":[116],"potential":[117],"errors":[118],"incorrect":[120],"selection":[123],"under":[124],"emotionally":[125],"inconsistent":[126],"conditions,":[127],"introduce":[129],"Emotion":[131,160],"Discrimination":[132],"Submodule":[133,162],"(ED),":[134],"which":[135],"enforces":[136],"representation":[139],"retain":[141],"discriminative":[142],"inconsistency.":[146],"This":[147],"ensures":[148],"even":[150],"if":[151],"FE":[153],"selects":[154],"inappropriate":[156],"modality,":[158],"Classification":[161],"(EC)":[163],"can":[164],"still":[165],"make":[166],"accurate":[167],"predictions":[168],"leveraging":[170],"preserved":[171],"inconsistency":[172],"information.":[173],"Experiments":[174],"show":[175],"achieves":[178],"state-of-the-art":[179],"(SOTA)":[180],"performance":[181],"on":[182],"IEMOCAP,":[183],"MELD,":[184],"M3ED.":[186],"The":[187],"source":[188],"code":[189],"is":[190],"publicly":[191],"available":[192],"at":[193],"https://github.com/PANPANKK/DRKF.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}
