{"id":"https://openalex.org/W7160297275","doi":"https://doi.org/10.1109/wacv61042.2026.00265","title":"Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation","display_name":"Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160297275","doi":"https://doi.org/10.1109/wacv61042.2026.00265"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5093234933","display_name":"Anh-Tuan Mai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh-Tuan Mai","raw_affiliation_strings":["VNU University of Engineering and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135289994","display_name":"Cam-Van Thi Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cam-Van Thi Nguyen","raw_affiliation_strings":["VNU University of Engineering and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135291075","display_name":"Duc-Trong Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc-Trong Le","raw_affiliation_strings":["VNU University of Engineering and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2700","last_page":"2709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.6593000292778015,"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":0.6593000292778015,"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/T12031","display_name":"Speech and dialogue systems","score":0.07479999959468842,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.03290000185370445,"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/conversation","display_name":"Conversation","score":0.715399980545044},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5734000205993652},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5702999830245972},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33160001039505005},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2777000069618225},{"id":"https://openalex.org/keywords/conversation-analysis","display_name":"Conversation analysis","score":0.2662000060081482}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5702999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5164999961853027},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42899999022483826},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36239999532699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3546999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C2780829048","wikidata":"https://www.wikidata.org/wiki/Q1624720","display_name":"Conversation analysis","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2081988641","https://openalex.org/W2085662862","https://openalex.org/W2146334809","https://openalex.org/W2286271878","https://openalex.org/W2341528187","https://openalex.org/W2619383789","https://openalex.org/W2787581402","https://openalex.org/W2805662932","https://openalex.org/W2807126412","https://openalex.org/W2949391930","https://openalex.org/W2963686995","https://openalex.org/W2970641574","https://openalex.org/W2973049979","https://openalex.org/W2985882473","https://openalex.org/W3098556456","https://openalex.org/W3165795751","https://openalex.org/W3173396651","https://openalex.org/W3173751215","https://openalex.org/W3176399185","https://openalex.org/W3179103990","https://openalex.org/W4206326349","https://openalex.org/W4221154966","https://openalex.org/W4287887917","https://openalex.org/W4313531231","https://openalex.org/W4367281761","https://openalex.org/W4387398498","https://openalex.org/W4389519350","https://openalex.org/W4394606408","https://openalex.org/W4403913147","https://openalex.org/W4409262900","https://openalex.org/W4411446656","https://openalex.org/W7131781060","https://openalex.org/W7133194810","https://openalex.org/W7133238715"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,188],"recognition":[2],"in":[3,59,77],"conversation":[4],"(MERC)":[5],"requires":[6],"representations":[7,148,181],"that":[8,26],"effectively":[9],"integrate":[10],"signals":[11,16],"from":[12],"multiple":[13,166],"modalities.":[14],"These":[15,169],"include":[17],"modality-specific":[18],"cues,":[19],"information":[20],"shared":[21],"across":[22,165],"modalities,":[23],"and":[24,41,62,98,111,127,160,178],"interactions":[25],"emerge":[27],"only":[28],"when":[29],"modalities":[30],"are":[31,149],"combined.":[32],"In":[33,81,114,129],"information-theoretic":[34],"terms,":[35],"these":[36,79,139],"correspond":[37],"to":[38,86],"unique,":[39],"redundant,":[40],"synergistic":[42],"contributions.":[43],"An":[44],"ideal":[45],"representation":[46],"should":[47],"leverage":[48],"all":[49],"three,":[50],"yet":[51],"achieving":[52],"such":[53],"balance":[54],"remains":[55],"challenging.":[56],"Recent":[57],"advances":[58],"contrastive":[60],"learning":[61],"augmentation-based":[63],"methods":[64],"have":[65],"made":[66],"progress,":[67],"but":[68],"they":[69],"often":[70],"overlook":[71],"the":[72,94,115,130,136,172],"role":[73],"of":[74,138,174],"data":[75],"preparation":[76],"preserving":[78],"components.":[80],"particular,":[82],"applying":[83],"augmentations":[84],"directly":[85],"raw":[87],"inputs":[88],"or":[89],"fused":[90],"embeddings":[91],"can":[92],"blur":[93],"boundaries":[95],"between":[96],"modality-unique":[97],"cross-modal":[99],"signals.":[100],"To":[101],"address":[102],"this":[103],"challenge,":[104],"we":[105],"propose":[106],"a":[107,183],"two-phase":[108],"framework":[109],"Divide":[110,116],"Refine":[112,131],"(DnR).":[113],"phase,":[117,132],"each":[118],"modality":[119],"is":[120,192],"explicitly":[121,175],"decomposed":[122],"into":[123],"uniqueness,":[124],"pairwise":[125],"redundancy,":[126],"synergy.":[128],"tailored":[133],"objectives":[134],"enhance":[135],"informativeness":[137],"components":[140],"while":[141],"maintaining":[142],"their":[143],"distinct":[144],"roles.":[145],"The":[146],"refined":[147],"plug-and-play":[150],"compatible":[151],"with":[152],"diverse":[153],"multimodal":[154,180],"pipelines.":[155],"Extensive":[156],"experiments":[157],"on":[158],"IEMOCAP":[159],"MELD":[161],"demonstrate":[162],"consistent":[163],"improvements":[164],"MERC":[167],"backbones.":[168],"results":[170],"highlight":[171],"effectiveness":[173],"dividing,":[176],"refining,":[177],"recombining":[179],"as":[182],"principled":[184],"strategy":[185],"for":[186],"advancing":[187],"recognition.":[189],"Our":[190],"implementation":[191],"available":[193],"at":[194],"https://github.com/mattam301/DnR-WACV2026":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}