{"id":"https://openalex.org/W4415538389","doi":"https://doi.org/10.1145/3746027.3755459","title":"Multimodal Emotion Recognition with Missing Modality via a Unified Multi-task Pre-training Framework","display_name":"Multimodal Emotion Recognition with Missing Modality via a Unified Multi-task Pre-training Framework","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538389","doi":"https://doi.org/10.1145/3746027.3755459"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755459","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":"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/A5044354789","display_name":"Ziyi Li","orcid":"https://orcid.org/0000-0002-8944-741X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyi Li","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8944-741X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056335002","display_name":"Wei\u2010Long Zheng","orcid":"https://orcid.org/0000-0002-9474-6369"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Long Zheng","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9474-6369","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040440605","display_name":"Bao\u2010Liang Lu","orcid":"https://orcid.org/0000-0001-8359-0058"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao-Liang Lu","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8359-0058","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044354789"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30267314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5717","last_page":"5725"},"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":0.9925000071525574,"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":0.9919999837875366,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8192999958992004},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.621399998664856},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.45559999346733093},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4352000057697296}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8192999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767000198364258},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.621399998664856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057000160217285},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4449999928474426},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4352000057697296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755459","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6849855026","display_name":null,"funder_award_id":"62376158","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2085497785","https://openalex.org/W2604438509","https://openalex.org/W2786768213","https://openalex.org/W3159301005","https://openalex.org/W3175825020","https://openalex.org/W4220704297","https://openalex.org/W4291023040","https://openalex.org/W4304014187","https://openalex.org/W4304086659","https://openalex.org/W4386071687","https://openalex.org/W4386071994","https://openalex.org/W4386800155","https://openalex.org/W4390351000","https://openalex.org/W4390414889","https://openalex.org/W4402703093","https://openalex.org/W4403780849"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1],"recognition":[2],"based":[3,61],"on":[4,62,139],"physiological":[5],"signals":[6],"faces":[7],"the":[8,63,123],"challenge":[9],"of":[10,65],"missing":[11,34],"modality":[12,91,110,113,159],"due":[13],"to":[14,32,37,43,126,128],"issues":[15],"such":[16],"as":[17],"inaccurate":[18],"signal":[19],"synchronization":[20],"and":[21,48,85,93,101,112,131,154],"inadequate":[22],"device":[23],"contact.":[24],"Existing":[25],"methods":[26],"either":[27],"require":[28],"additional":[29],"generative":[30],"modules":[31],"handle":[33],"modalities,":[35],"leading":[36],"extra":[38],"computational":[39],"overhead,":[40],"or":[41],"fail":[42],"effectively":[44],"capture":[45],"both":[46,83,98,129,150],"modality-specific":[47,99],"joint":[49,78,102],"representation.":[50],"In":[51],"contrast,":[52],"we":[53],"propose":[54],"a":[55,77],"Unified":[56],"Multi-task":[57],"Pre-training":[58],"(UMAP)":[59],"framework":[60],"mixture":[64],"experts":[66,92],"structure.":[67],"Our":[68],"approach":[69],"offers":[70],"two":[71],"key":[72],"advantages:":[73],"(1)":[74],"It":[75],"retains":[76],"structure":[79],"while":[80],"flexibly":[81],"handling":[82],"unimodal":[84],"multimodal":[86,103,152],"inputs":[87],"by":[88],"selecting":[89],"lightweight":[90],"shared":[94],"experts,":[95],"thus":[96],"preserving":[97],"features":[100],"information.":[104],"2)":[105],"Three":[106],"pre-training":[107],"tasks-contrastive":[108],"learning,":[109],"matching,":[111],"generation-are":[114],"integrated":[115],"into":[116],"UMAP":[117,145],"through":[118],"different":[119],"attention":[120],"masks,":[121],"enhancing":[122],"model's":[124],"ability":[125],"adapt":[127],"complete":[130],"incomplete":[132],"modalities":[133],"during":[134],"fine-tuning.":[135],"Comprehensive":[136],"experiments":[137],"conducted":[138],"three":[140],"benchmark":[141],"datasets":[142],"demonstrate":[143],"that":[144],"achieves":[146],"state-of-the-art":[147],"(SOTA)":[148],"performance,":[149],"in":[151,155],"scenarios":[153],"cases":[156],"where":[157],"any":[158],"is":[160,164],"missing.":[161],"The":[162],"code":[163],"available":[165],"at":[166],"https://github.com/iiieeeve/UMAP.":[167]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}