{"id":"https://openalex.org/W4285340463","doi":"https://doi.org/10.1109/iccicc53683.2021.9811331","title":"FERNIE-ViL: Facial Expression Enhanced Vision-and-Language Model","display_name":"FERNIE-ViL: Facial Expression Enhanced Vision-and-Language Model","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W4285340463","doi":"https://doi.org/10.1109/iccicc53683.2021.9811331"},"language":"en","primary_location":{"id":"doi:10.1109/iccicc53683.2021.9811331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccicc53683.2021.9811331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 20th International Conference on Cognitive Informatics &amp; Cognitive Computing (ICCI*CC)","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/A5042351646","display_name":"Soo-Ryeon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Ryeon Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea","Korea University,Department of Computer Science and Engineering Department of Artificial Intelligence,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331501","display_name":"Dohyun Kim","orcid":"https://orcid.org/0000-0002-0562-351X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dohyun Kim","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508992","display_name":"Mingyu Lee","orcid":"https://orcid.org/0009-0000-2038-2032"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mingyu Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101595608","display_name":"SangKeun Lee","orcid":"https://orcid.org/0000-0002-6249-8217"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SangKeun Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea","Korea University,Department of Computer Science and Engineering Department of Artificial Intelligence,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996399998664856,"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","display_name":"Facial expression","score":0.717480480670929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6391582489013672},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.6254580020904541},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.6059930324554443},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.5964041948318481},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5486118793487549},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5234334468841553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46395960450172424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43921220302581787},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43200865387916565},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.43010762333869934},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.4254019558429718},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.41747045516967773},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4133506417274475},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3736782968044281},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.32908928394317627},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.30535900592803955},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.23886922001838684},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.20120787620544434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1978311538696289},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17772358655929565},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07867151498794556},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07461875677108765},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07132932543754578},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06681859493255615}],"concepts":[{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.717480480670929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6391582489013672},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.6254580020904541},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.6059930324554443},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.5964041948318481},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5486118793487549},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5234334468841553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46395960450172424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43921220302581787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43200865387916565},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.43010762333869934},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.4254019558429718},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.41747045516967773},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4133506417274475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3736782968044281},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.32908928394317627},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30535900592803955},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.23886922001838684},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.20120787620544434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1978311538696289},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17772358655929565},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07867151498794556},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07461875677108765},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07132932543754578},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06681859493255615},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccicc53683.2021.9811331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccicc53683.2021.9811331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 20th International Conference on Cognitive Informatics &amp; Cognitive Computing (ICCI*CC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2041616772","https://openalex.org/W2150283722","https://openalex.org/W2161518694","https://openalex.org/W2170179129","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2745461083","https://openalex.org/W2897037347","https://openalex.org/W2903020943","https://openalex.org/W2938404524","https://openalex.org/W2963115613","https://openalex.org/W2963583748","https://openalex.org/W2966715458","https://openalex.org/W2995034616","https://openalex.org/W3090449556","https://openalex.org/W3161346624","https://openalex.org/W3173909648","https://openalex.org/W4248476540","https://openalex.org/W4290610135","https://openalex.org/W6620707391","https://openalex.org/W6755947051","https://openalex.org/W6766904570","https://openalex.org/W6771710517","https://openalex.org/W6795785952","https://openalex.org/W6997531736"],"related_works":["https://openalex.org/W2355913164","https://openalex.org/W4205986151","https://openalex.org/W1153638794","https://openalex.org/W2168968280","https://openalex.org/W2116055069","https://openalex.org/W4323520705","https://openalex.org/W2356663679","https://openalex.org/W2169777806","https://openalex.org/W3027190010","https://openalex.org/W2162992774"],"abstract_inverted_index":{"Visual":[0,14],"cognition":[1],"requires":[2],"analyzing":[3],"actions,":[4],"intentions,":[5],"and":[6,24,43,50,59,70,110],"emotions":[7,42],"of":[8,77],"persons":[9],"in":[10,45],"a":[11,19,92],"given":[12,29],"image.":[13],"Commonsense":[15],"Reasoning":[16],"(VCR)":[17],"is":[18],"task":[20],"that":[21,68,118],"selects":[22],"rationales":[23],"answers":[25],"to":[26,56,74,97],"questions":[27],"for":[28],"images.":[30],"In":[31,80],"VCR,":[32],"facial":[33,86,93],"expressions":[34],"are":[35,53,72],"important":[36],"nonverbal":[37],"signals":[38],"because":[39],"they":[40],"convey":[41],"intentions":[44],"human":[46,128],"interactions.":[47,129],"However,":[48],"ERNIE-ViL":[49,69],"UNITER,":[51],"which":[52,90],"vision-and-language":[54,100],"models":[55],"get":[57],"image":[58],"text":[60],"representations,":[61],"do":[62],"not":[63],"learn":[64],"them.":[65],"We":[66],"find":[67],"UNITER":[71],"vulnerable":[73],"the":[75,98],"problem":[76],"identifying":[78],"emotions.":[79],"this":[81],"paper,":[82],"therefore,":[83],"we":[84],"propose":[85],"expression":[87,94],"recognition":[88,95],"FERNIE-ViL,":[89],"adapts":[91],"module":[96],"existing":[99],"model.":[101],"Experimental":[102],"results":[103],"(2.4%":[104],"point":[105,112],"improvement":[106,113],"on":[107,114],"VCR":[108,115],"Q&#x2192;A":[109],"0.3%":[111],"QA&#x2192;R)":[116],"demonstrate":[117],"our":[119],"method":[120],"can":[121],"enhance":[122],"visual":[123],"commonsense":[124],"reasoning":[125],"by":[126],"understanding":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
