{"id":"https://openalex.org/W4376455521","doi":"https://doi.org/10.1109/taffc.2023.3274829","title":"Efficient Multimodal Transformer With Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis","display_name":"Efficient Multimodal Transformer With Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis","publication_year":2023,"publication_date":"2023-05-10","ids":{"openalex":"https://openalex.org/W4376455521","doi":"https://doi.org/10.1109/taffc.2023.3274829"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2023.3274829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2023.3274829","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-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/A5027572653","display_name":"Licai Sun","orcid":"https://orcid.org/0000-0002-7944-3458"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licai Sun","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","National Laboratory of attern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7944-3458","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of attern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001973434","display_name":"Zheng Lian","orcid":"https://orcid.org/0000-0001-9477-0599"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Lian","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9477-0599","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395562","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0003-1529-1552"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1529-1552","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.9108,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99783901,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"309","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150632739067078},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6031512022018433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.587989330291748},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5110396146774292},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44428879022598267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4283655881881714},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4199889600276947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3206629753112793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150632739067078},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6031512022018433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.587989330291748},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5110396146774292},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44428879022598267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4283655881881714},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4199889600276947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3206629753112793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2023.3274829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2023.3274829","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1202467192","display_name":null,"funder_award_id":"U21B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1448168285","display_name":null,"funder_award_id":"62276259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8569810394","display_name":null,"funder_award_id":"62201572","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2025768430","https://openalex.org/W2064675550","https://openalex.org/W2095176743","https://openalex.org/W2098689807","https://openalex.org/W2122563357","https://openalex.org/W2191779130","https://openalex.org/W2519656895","https://openalex.org/W2556418146","https://openalex.org/W2584561145","https://openalex.org/W2740550900","https://openalex.org/W2741295496","https://openalex.org/W2753840835","https://openalex.org/W2767249564","https://openalex.org/W2787581402","https://openalex.org/W2807126412","https://openalex.org/W2883409523","https://openalex.org/W2949391930","https://openalex.org/W2962931510","https://openalex.org/W2963063161","https://openalex.org/W2963420272","https://openalex.org/W2963710346","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W2964266095","https://openalex.org/W2964346351","https://openalex.org/W2972965453","https://openalex.org/W2979826702","https://openalex.org/W2990629080","https://openalex.org/W3023371261","https://openalex.org/W3034266838","https://openalex.org/W3034849760","https://openalex.org/W3035524453","https://openalex.org/W3093051361","https://openalex.org/W3098042509","https://openalex.org/W3099424485","https://openalex.org/W3114214226","https://openalex.org/W3119957342","https://openalex.org/W3120680448","https://openalex.org/W3128412859","https://openalex.org/W3160183718","https://openalex.org/W3169801598","https://openalex.org/W3170863103","https://openalex.org/W3171007011","https://openalex.org/W3175825020","https://openalex.org/W3177085913","https://openalex.org/W3196215173","https://openalex.org/W3205519684","https://openalex.org/W3206201541","https://openalex.org/W3209059054","https://openalex.org/W3214432797","https://openalex.org/W4221155339","https://openalex.org/W4224916778","https://openalex.org/W4254724182","https://openalex.org/W4285248692","https://openalex.org/W4287887284","https://openalex.org/W4313156423","https://openalex.org/W4313639237","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6755207826","https://openalex.org/W6755477022","https://openalex.org/W6766978945","https://openalex.org/W6768021236","https://openalex.org/W6770782798","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6790830454","https://openalex.org/W6796761347","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W2548633793","https://openalex.org/W3013279174","https://openalex.org/W2941935829","https://openalex.org/W2596247554","https://openalex.org/W3132372214","https://openalex.org/W2905271011","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W4298151006"],"abstract_inverted_index":{"With":[0],"the":[1,26,86,105,126,131,142,152],"proliferation":[2],"of":[3,109,166],"user-generated":[4],"online":[5],"videos,":[6],"Multimodal":[7,70],"Sentiment":[8],"Analysis":[9],"(MSA)":[10],"has":[11],"attracted":[12],"increasing":[13],"attention":[14],"recently.":[15],"Despite":[16],"significant":[17],"progress,":[18],"there":[19],"are":[20],"still":[21],"two":[22,163],"major":[23],"challenges":[24],"on":[25,130,182],"way":[27],"towards":[28],"robust":[29],"MSA:":[30],"1)":[31],"inefficiency":[32],"when":[33],"modeling":[34],"cross-modal":[35,112],"interactions":[36],"in":[37,52,125,193],"unaligned":[38],"multimodal":[39,88],"data;":[40],"and":[41,62,96,159,169,196],"2)":[42],"vulnerability":[43],"to":[44,65,90,118,139,144,174],"random":[45],"modality":[46,84,128,198],"feature":[47,137],"missing":[48],"which":[49],"typically":[50],"occurs":[51],"realistic":[53],"settings.":[54,199],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"a":[60],"generic":[61],"unified":[63],"framework":[64],"address":[66],"them,":[67],"named":[68],"Efficient":[69],"Transformer":[71],"with":[72,92],"Dual-Level":[73],"Feature":[74],"Restoration":[75],"(EMT-DLFR).":[76],"Concretely,":[77],"EMT":[78],"employs":[79],"utterance-level":[80],"representations":[81],"from":[82,148],"each":[83,99],"as":[85,162],"global":[87],"context":[89],"interact":[91],"local":[93],"unimodal":[94],"features":[95],"mutually":[97],"promote":[98],"other.":[100],"It":[101],"not":[102],"only":[103],"avoids":[104],"quadratic":[106],"scaling":[107],"cost":[108],"previous":[110],"local-local":[111],"interaction":[113],"methods":[114],"but":[115],"also":[116],"leads":[117],"better":[119],"performance.":[120],"To":[121],"improve":[122],"model":[123,143],"robustness":[124],"incomplete":[127,149,160,197],"setting,":[129],"one":[132,167],"hand,":[133,154],"DLFR":[134],"performs":[135],"low-level":[136],"reconstruction":[138],"implicitly":[140],"encourage":[141],"learn":[145],"semantic":[146],"information":[147],"data.":[150],"On":[151],"other":[153],"it":[155],"innovatively":[156],"regards":[157],"complete":[158,195],"data":[161],"different":[164],"views":[165],"sample":[168],"utilizes":[170],"siamese":[171],"representation":[172],"learning":[173],"explicitly":[175],"attract":[176],"their":[177],"high-level":[178],"representations.":[179],"Comprehensive":[180],"experiments":[181],"three":[183],"popular":[184],"datasets":[185],"demonstrate":[186],"that":[187],"our":[188],"method":[189],"achieves":[190],"superior":[191],"performance":[192],"both":[194]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":112},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":18}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}