{"id":"https://openalex.org/W4394645697","doi":"https://doi.org/10.48550/arxiv.2106.04520","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","display_name":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","publication_year":2021,"publication_date":"2021-06-08","ids":{"openalex":"https://openalex.org/W4394645697","doi":"https://doi.org/10.48550/arxiv.2106.04520"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2106.04520","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04520","pdf_url":"https://arxiv.org/pdf/2106.04520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.04520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022963005","display_name":"Hanting Li","orcid":"https://orcid.org/0009-0004-1536-5958","observed_orcids":["https://orcid.org/0009-0004-1536-5958","https://orcid.org/0009-0007-1618-7980"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hanting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049261198","display_name":"Mingzhe Sui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sui, Mingzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401202","display_name":"Feng Zhao","orcid":"https://orcid.org/0000-0001-6767-8105","observed_orcids":["https://orcid.org/0000-0001-6767-8105","https://orcid.org/0009-0002-6717-0146","https://orcid.org/0000-0001-9199-4466"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993","observed_orcids":["https://orcid.org/0000-0003-2510-8993"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zha, Zhengjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101550662","display_name":"Feng Liang Wu","orcid":"https://orcid.org/0000-0003-1918-1596","observed_orcids":["https://orcid.org/0000-0003-1918-1596"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9312000274658203,"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":0.9312000274658203,"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/T11448","display_name":"Face recognition and analysis","score":0.06260000169277191,"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/T10057","display_name":"Face and Expression Recognition","score":0.00279999990016222,"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/facial-expression-recognition","display_name":"facial expression recognition","score":0.9710000157356262},{"id":"https://openalex.org/keywords/in-the-wild","display_name":"in-the-wild","score":0.7670000195503235},{"id":"https://openalex.org/keywords/label-noise-correction","display_name":"label noise correction","score":0.48399999737739563},{"id":"https://openalex.org/keywords/occlusion-handling","display_name":"occlusion handling","score":0.7099999785423279},{"id":"https://openalex.org/keywords/background-filtering","display_name":"background filtering","score":0.824999988079071},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.8669999837875366},{"id":"https://openalex.org/keywords/deit","display_name":"DeiT","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7637084126472473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158594727516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6627600193023682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4899732172489166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4898766875267029},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45705080032348633},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.416047602891922},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12866473197937012},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10423406958580017},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2106.04520","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04520","pdf_url":"https://arxiv.org/pdf/2106.04520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2106.04520","doi":"https://doi.org/10.48550/arxiv.2106.04520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.04520","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.04520","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04520","pdf_url":"https://arxiv.org/pdf/2106.04520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3167651619","https://openalex.org/W3209798173","https://openalex.org/W7162487722","https://openalex.org/W3141497777","https://openalex.org/W4321151193","https://openalex.org/W4386323600","https://openalex.org/W4285814448","https://openalex.org/W7202297483","https://openalex.org/W4391331275","https://openalex.org/W4413424202"],"abstract_inverted_index":{"Facial":[0],"Expression":[1],"Recognition":[2],"(FER)":[3],"in":[4,12,70,84,111,149,152],"the":[5,23,43,50,85,91,112,153],"wild":[6],"is":[7],"an":[8],"extremely":[9],"challenging":[10],"task":[11],"computer":[13],"vision":[14,58,106],"due":[15],"to":[16,35,125,145],"variant":[17],"backgrounds,":[18],"low-quality":[19],"facial":[20],"images,":[21,139],"and":[22,53,61,135,140,172,177],"subjectiveness":[24],"of":[25,116,137],"annotators.":[26],"These":[27],"uncertainties":[28],"make":[29],"it":[30],"difficult":[31],"for":[32,109],"neural":[33],"networks":[34,44],"learn":[36],"robust":[37],"features":[38],"on":[39,165,182],"limited-scale":[40],"datasets.":[41],"Moreover,":[42],"can":[45,130],"be":[46],"easily":[47],"distributed":[48],"by":[49],"above":[51],"factors":[52],"perform":[54],"incorrect":[55,147],"decisions.":[56],"Recently,":[57],"transformer":[59,107],"(ViT)":[60],"data-efficient":[62],"image":[63],"transformers":[64,78],"(DeiT)":[65],"present":[66],"their":[67],"significant":[68],"performance":[69],"traditional":[71],"classification":[72],"tasks.":[73],"The":[74],"self-attention":[75],"mechanism":[76],"makes":[77],"obtain":[79],"a":[80,101,119,127,141,179],"global":[81],"receptive":[82],"field":[83],"first":[86,99],"layer":[87],"which":[88,114],"dramatically":[89],"enhances":[90],"feature":[92],"extraction":[93],"capability.":[94],"In":[95],"this":[96],"work,":[97],"we":[98],"propose":[100],"novel":[102],"pure":[103],"transformer-based":[104,120],"mask":[105,121,128],"(MVT)":[108],"FER":[110,150],"wild,":[113],"consists":[115],"two":[117],"modules:":[118],"generation":[122],"network":[123],"(MGN)":[124],"generate":[126],"that":[129,159],"filter":[131],"out":[132],"complex":[133],"backgrounds":[134],"occlusion":[136],"face":[138],"dynamic":[142],"relabeling":[143],"module":[144],"rectify":[146],"labels":[148],"datasets":[151],"wild.":[154],"Extensive":[155],"experimental":[156],"results":[157],"demonstrate":[158],"our":[160],"MVT":[161],"outperforms":[162],"state-of-the-art":[163],"methods":[164],"RAF-DB":[166],"with":[167,170,174,184],"88.62%,":[168],"FERPlus":[169],"89.22%,":[171],"AffectNet-7":[173],"64.57%,":[175],"respectively,":[176],"achieves":[178],"comparable":[180],"result":[181],"AffectNet-8":[183],"61.40%.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2024-04-10T00:00:00"}