{"id":"https://openalex.org/W4402979749","doi":"https://doi.org/10.1109/icme57554.2024.10687508","title":"CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition","display_name":"CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979749","doi":"https://doi.org/10.1109/icme57554.2024.10687508"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5022963005","display_name":"Hanting Li","orcid":"https://orcid.org/0009-0004-1536-5958"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanting Li","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056229595","display_name":"Hongjing Niu","orcid":"https://orcid.org/0000-0002-9480-6464"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjing Niu","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037532013","display_name":"Zhaoqing Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoqing Zhu","raw_affiliation_strings":["Alibaba Group,Alibaba DAMO Academy for Discovery,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Alibaba DAMO Academy for Discovery,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101902561","display_name":"Feng Zhao","orcid":"https://orcid.org/0000-0003-3788-4455"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhao","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022963005"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":8.5028,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98494282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8794000148773193,"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/T11448","display_name":"Face recognition and analysis","score":0.8794000148773193,"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":0.8356000185012817,"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/T10057","display_name":"Face and Expression Recognition","score":0.8305000066757202,"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/computer-science","display_name":"Computer science","score":0.6500217914581299},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5935878753662109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.487490177154541},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4714670479297638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38174593448638916},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3634706139564514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3502596616744995},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14268732070922852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6500217914581299},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5935878753662109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487490177154541},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4714670479297638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38174593448638916},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3634706139564514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3502596616744995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14268732070922852}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1981918162","https://openalex.org/W2738672149","https://openalex.org/W2745497104","https://openalex.org/W2962934715","https://openalex.org/W2963524571","https://openalex.org/W3003720578","https://openalex.org/W3035336958","https://openalex.org/W3093370878","https://openalex.org/W3118405827","https://openalex.org/W3134095442","https://openalex.org/W3175546442","https://openalex.org/W3195286673","https://openalex.org/W3198377975","https://openalex.org/W3206349670","https://openalex.org/W3209798173","https://openalex.org/W4214926101","https://openalex.org/W4225568094","https://openalex.org/W4285606530","https://openalex.org/W4304099113","https://openalex.org/W4312310776","https://openalex.org/W4312823769","https://openalex.org/W4312980231","https://openalex.org/W4382240798","https://openalex.org/W6746052068","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6837937255","https://openalex.org/W6838989974","https://openalex.org/W6864202710"],"related_works":["https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W3129895999","https://openalex.org/W2328518092","https://openalex.org/W3101249758","https://openalex.org/W2382079200","https://openalex.org/W2374091470","https://openalex.org/W4388218547","https://openalex.org/W2379703849","https://openalex.org/W2642127892"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,7,55,131,146],"the":[3,20,27,48,72,86,129,144],"most":[4,35],"informative":[5],"behaviors":[6],"humans,":[8],"facial":[9,36,56,103],"expressions":[10,57],"are":[11,59],"often":[12],"compound":[13],"and":[14,58,74,101,122],"variable,":[15],"which":[16,50],"is":[17],"manifested":[18],"by":[19],"fact":[21],"that":[22],"different":[23,32],"people":[24],"may":[25],"express":[26],"same":[28],"expression":[29,37,113,120],"in":[30,89],"very":[31],"ways.":[33],"However,":[34],"recognition":[38],"(FER)":[39],"methods":[40],"still":[41],"use":[42,69],"one-hot":[43],"or":[44],"soft":[45],"labels":[46],"as":[47,71],"supervision,":[49],"lack":[51],"sufficient":[52],"semantic":[53],"descriptions":[54],"less":[60],"interpretable.":[61],"Recently,":[62],"contrastive":[63],"vision-language":[64],"pre-training":[65],"models":[66],"(e.g.,":[67],"CLIP)":[68],"text":[70,114],"supervision":[73],"have":[75],"injected":[76],"new":[77],"vitality":[78],"into":[79],"various":[80],"computer":[81],"vision":[82],"tasks,":[83],"benefiting":[84],"from":[85],"rich":[87],"semantics":[88],"text.":[90],"Therefore,":[91],"we":[92,110],"propose":[93],"CLIPER,":[94],"a":[95,123],"unified":[96],"framework":[97],"for":[98],"both":[99],"static":[100],"dynamic":[102],"Expression":[104],"Recognition":[105],"based":[106],"on":[107,137],"CLIP.":[108,132],"Besides,":[109],"introduce":[111],"multiple":[112],"descriptors":[115],"(METD)":[116],"to":[117,127,142],"learn":[118],"fine-grained":[119],"representations":[121],"two-stage":[124],"training":[125],"paradigm":[126],"reserve":[128],"interpretability":[130],"We":[133],"conduct":[134],"extensive":[135],"experiments":[136],"several":[138],"popular":[139],"FER":[140],"benchmarks":[141],"demonstrates":[143],"effectiveness":[145],"CLIPER.":[147],"The":[148],"source":[149],"code":[150],"will":[151],"be":[152],"available":[153],"at":[154],"https://github.com/muse1998/CLIPER.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":9}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}