{"id":"https://openalex.org/W4416017929","doi":"https://doi.org/10.1145/3746252.3761430","title":"ESED: Emotion-Specific Evidence Decomposition for Uncertainty-Aware Multimodal Emotion Recognition in Conversation","display_name":"ESED: Emotion-Specific Evidence Decomposition for Uncertainty-Aware Multimodal Emotion Recognition in Conversation","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017929","doi":"https://doi.org/10.1145/3746252.3761430"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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/A5064024870","display_name":"Zeng Gang Xiong","orcid":"https://orcid.org/0009-0001-1110-6527"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zechang Xiong","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1110-6527","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023589208","display_name":"Zhenyan Ji","orcid":"https://orcid.org/0000-0002-6566-9464"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyan Ji","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6566-9464","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenkang Kong","orcid":"https://orcid.org/0009-0000-0432-8810"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenkang Kong","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0432-8810","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033112359","display_name":"Jiuqian Dai","orcid":"https://orcid.org/0000-0002-4620-0441"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuqian Dai","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4620-0441","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069744156","display_name":"Shen Yin","orcid":"https://orcid.org/0000-0002-3802-9269"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Shen Yin","raw_affiliation_strings":["Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":"https://orcid.org/0000-0002-3802-9269","affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064024870"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33242816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3582","last_page":"3591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.991599977016449,"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":0.991599977016449,"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":0.0020000000949949026,"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/T12488","display_name":"Mental Health via Writing","score":0.0005000000237487257,"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/emotion-recognition","display_name":"Emotion recognition","score":0.5895000100135803},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.545199990272522},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4625000059604645},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.41019999980926514},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6377999782562256},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.27480000257492065}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5792476445","display_name":null,"funder_award_id":"No.52175493 and No.51935002","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2964300796","https://openalex.org/W3173396651","https://openalex.org/W3183891373","https://openalex.org/W3209984917","https://openalex.org/W4221154966","https://openalex.org/W4224926219","https://openalex.org/W4281701185","https://openalex.org/W4283800180","https://openalex.org/W4285076876","https://openalex.org/W4297499129","https://openalex.org/W4311593456","https://openalex.org/W4360930863","https://openalex.org/W4385570630","https://openalex.org/W4387968266","https://openalex.org/W4387969701","https://openalex.org/W4390414889","https://openalex.org/W4393146934","https://openalex.org/W4393156830","https://openalex.org/W4393397422","https://openalex.org/W4396785645","https://openalex.org/W4397007529","https://openalex.org/W4400849567","https://openalex.org/W4401016710","https://openalex.org/W4401687226","https://openalex.org/W4402955899","https://openalex.org/W4403780491","https://openalex.org/W4403791052","https://openalex.org/W4405513150","https://openalex.org/W4408459007","https://openalex.org/W4409346698"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"in":[3],"conversations":[4],"is":[5,145],"inherently":[6],"challenging":[7],"due":[8],"to":[9,21,71],"ambiguous":[10],"cues,":[11],"modality":[12],"conflicts,":[13],"and":[14,23,74,113,131,139,167],"temporal":[15,119,140],"dynamics,":[16],"all":[17],"of":[18,47,110,151,173],"which":[19],"contribute":[20],"complex":[22],"diverse":[24],"uncertainty":[25,32,48],"sources.":[26],"While":[27],"some":[28],"recent":[29],"methods":[30,163],"incorporate":[31],"modeling,":[33],"they":[34],"often":[35],"focus":[36],"on":[37,127,164],"overall":[38],"prediction":[39,135,144],"confidence,":[40],"without":[41],"explicitly":[42,72],"distinguishing":[43],"the":[44,106,161,165,171],"different":[45],"sources":[46],"introduced":[49],"by":[50],"underlying":[51],"factors.":[52],"To":[53],"address":[54],"these":[55,152],"challenges,":[56],"we":[57],"propose":[58],"a":[59],"novel":[60],"Emotion-Specific":[61],"Evidence":[62],"Decomposition":[63],"framework":[64],"(ESED)":[65],"that":[66,158],"leverages":[67],"evidential":[68],"deep":[69],"learning":[70],"model":[73],"disentangle":[75],"multimodal":[76],"emotional":[77,98,108,128],"uncertainty.":[78],"Rather":[79],"than":[80],"directly":[81],"fusing":[82],"features,":[83],"ESED":[84,159],"decomposes":[85],"each":[86,111],"modality's":[87],"evidence":[88],"into":[89],"three":[90],"interpretable":[91],"components:":[92],"(1)":[93],"emotion-consistent":[94],"evidence,":[95,104,116],"capturing":[96],"shared":[97],"cues":[99],"across":[100],"modalities;":[101],"(2)":[102],"emotion-specific":[103],"highlighting":[105],"unique":[107],"role":[109],"modality;":[112],"(3)":[114],"dynamic":[115],"modeling":[117],"utterance-level":[118],"variations.":[120],"These":[121],"components":[122],"are":[123],"adaptively":[124],"weighted":[125,153],"based":[126],"intensity,":[129],"ambiguity,":[130],"dynamicity,":[132],"quantified":[133],"via":[134],"entropy,":[136],"inter-modal":[137],"divergence,":[138],"variance.":[141],"The":[142],"final":[143],"obtained":[146],"through":[147],"an":[148],"adaptive":[149],"fusion":[150],"components.":[154],"Extensive":[155],"experiments":[156],"demonstrate":[157],"outperforms":[160],"state-of-the-art":[162],"MELD":[166],"IEMOCAP":[168],"datasets,":[169],"demonstrating":[170],"effectiveness":[172],"our":[174],"proposed":[175],"method.":[176]},"counts_by_year":[],"updated_date":"2025-11-08T23:25:12.792448","created_date":"2025-11-08T00:00:00"}