{"id":"https://openalex.org/W7160278046","doi":"https://doi.org/10.1109/wacv61042.2026.00476","title":"Robust Multimodal Emotion Recognition from Incomplete Modalities via Query-Based Unimodal and Cross-Modal Learning","display_name":"Robust Multimodal Emotion Recognition from Incomplete Modalities via Query-Based Unimodal and Cross-Modal Learning","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160278046","doi":"https://doi.org/10.1109/wacv61042.2026.00476"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00476","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/A5040046908","display_name":"Ryo Miyoshi","orcid":"https://orcid.org/0000-0003-4676-1959"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Miyoshi","raw_affiliation_strings":["CyberAgent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135302207","display_name":"Mayu Otani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mayu Otani","raw_affiliation_strings":["CyberAgent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032387791","display_name":"Yuki Okafuji","orcid":"https://orcid.org/0000-0002-9547-3681"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Okafuji","raw_affiliation_strings":["CyberAgent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberAgent","institution_ids":["https://openalex.org/I4210089607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089607"],"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":"4901","last_page":"4911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9638000130653381,"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":0.9638000130653381,"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":0.010599999688565731,"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/T10057","display_name":"Face and Expression Recognition","score":0.0035000001080334187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4474000036716461},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42239999771118164},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.301800012588501},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.2858999967575073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2825999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5264999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3955000042915344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00476","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1998476814","https://openalex.org/W2122563357","https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2740550900","https://openalex.org/W2741295496","https://openalex.org/W2787581402","https://openalex.org/W2807126412","https://openalex.org/W2883409523","https://openalex.org/W2962931510","https://openalex.org/W2963686995","https://openalex.org/W2963710346","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964266095","https://openalex.org/W2964346351","https://openalex.org/W3012159372","https://openalex.org/W3093051361","https://openalex.org/W3093370878","https://openalex.org/W3096609285","https://openalex.org/W3139270985","https://openalex.org/W3169801598","https://openalex.org/W3171007011","https://openalex.org/W3176404283","https://openalex.org/W3196324893","https://openalex.org/W3205519684","https://openalex.org/W3206201541","https://openalex.org/W4225568094","https://openalex.org/W4308222497","https://openalex.org/W4312639100","https://openalex.org/W4313156423","https://openalex.org/W4313639237","https://openalex.org/W4361856922","https://openalex.org/W4376455521","https://openalex.org/W4386075879","https://openalex.org/W4390872007","https://openalex.org/W4393028958","https://openalex.org/W4393147709","https://openalex.org/W4394597819","https://openalex.org/W4402727412","https://openalex.org/W4415795657","https://openalex.org/W7133205100","https://openalex.org/W7133220561"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"(MER)":[3],"aims":[4],"to":[5,36,88,111],"identify":[6],"human":[7],"emotions":[8],"from":[9],"inputs":[10],"such":[11],"as":[12],"text,":[13],"vision,":[14],"and":[15,27,78,108,126],"audio.":[16],"However,":[17],"existing":[18,112],"methods":[19],"often":[20],"assume":[21],"complete":[22],"modality":[23,56],"availability":[24],"during":[25],"training":[26],"inference,":[28],"which":[29],"is":[30],"unrealistic":[31],"in":[32],"real-world":[33,131],"scenarios":[34],"due":[35],"sensor":[37],"failures":[38],"or":[39,62],"privacy":[40],"constraints.":[41],"We":[42],"propose":[43],"Dual-Query":[44],"Fusion":[45],"(DQF),":[46],"a":[47],"framework":[48],"that":[49,103],"enables":[50],"robust":[51],"MER":[52,132],"using":[53],"only":[54],"incomplete":[55,119],"inputs,":[57],"without":[58],"relying":[59],"on":[60,98,118],"reconstruction":[61],"knowledge":[63],"distillation.":[64],"DQF":[65,104,129],"introduces":[66],"two":[67,99],"types":[68],"of":[69,128],"learnable":[70],"queries:":[71],"Q-UA":[72],"for":[73,80,130],"extracting":[74],"informative":[75],"unimodal":[76],"features,":[77],"Q-CA":[79],"adaptive":[81],"cross-modal":[82],"integration.":[83],"These":[84,121],"modules":[85],"are":[86,95],"designed":[87],"operate":[89],"effectively":[90],"even":[91,114],"when":[92,115],"some":[93],"modalities":[94],"missing.":[96],"Experiments":[97],"public":[100],"datasets":[101],"demonstrate":[102],"achieves":[105],"superior":[106],"performance":[107],"robustness":[109],"compared":[110],"methods,":[113],"trained":[116],"exclusively":[117],"inputs.":[120],"results":[122],"highlight":[123],"the":[124],"effectiveness":[125],"practicality":[127],"tasks.":[133]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}