{"id":"https://openalex.org/W4400527853","doi":"https://doi.org/10.1109/fg59268.2024.10581982","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","display_name":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400527853","doi":"https://doi.org/10.1109/fg59268.2024.10581982"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10581982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5080786995","display_name":"Niki Maria Foteinopoulou","orcid":"https://orcid.org/0000-0003-4481-9360"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niki Maria Foteinopoulou","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London,London,United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031205865","display_name":"Ioannis Patras","orcid":"https://orcid.org/0000-0003-3913-4738"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ioannis Patras","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London,London,United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":29.6497,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.99875648,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9587000012397766,"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":0.9587000012397766,"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":0.6930156350135803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5837095379829407},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5700880289077759},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.5164427757263184},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.5030266642570496},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.478439599275589},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.45563095808029175},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.450501024723053},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4406161606311798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3882949650287628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.296337366104126},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06852796673774719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930156350135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5837095379829407},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5700880289077759},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5164427757263184},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.5030266642570496},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.478439599275589},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.45563095808029175},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.450501024723053},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4406161606311798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3882949650287628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.296337366104126},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06852796673774719},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg59268.2024.10581982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4397263494","display_name":null,"funder_award_id":"951911","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7258775301","display_name":"DTP 2018-19 Queen Mary University of London","funder_award_id":"EP/R513106/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4205986151","https://openalex.org/W2355913164","https://openalex.org/W1153638794","https://openalex.org/W2168968280","https://openalex.org/W2116055069","https://openalex.org/W2162992774","https://openalex.org/W4323520705","https://openalex.org/W2356663679","https://openalex.org/W2169777806","https://openalex.org/W3027190010"],"abstract_inverted_index":{"Facial":[0],"Expression":[1],"Recognition":[2],"(FER)":[3],"is":[4,196,204],"a":[5,46,182],"crucial":[6],"task":[7,159],"in":[8,40,126,134],"affective":[9],"computing,":[10],"but":[11],"its":[12,21],"conventional":[13],"focus":[14],"on":[15,92,95,140,156,207],"the":[16,24,32,58,71,89,146,150,157],"seven":[17],"basic":[18],"emotions":[19,38],"limits":[20],"applicability":[22],"to":[23,69,112,170,188,198],"complex":[25],"and":[26,36,132,173],"expanding":[27],"emotional":[28,62],"spectrum.":[29],"To":[30,80],"address":[31],"issue":[33],"of":[34,57,73,88,128,136,160,186],"new":[35],"unseen":[37],"present":[39],"dynamic":[41,98],"in-the-wild":[42],"FER,":[43,119],"we":[44,83,120,144,180],"propose":[45],"novel":[47],"vision-language":[48],"model":[49,90],"that":[50,104],"utilises":[51],"sample-level":[52,93,154],"text":[53],"descriptions":[54,94,155],"(i.e.":[55],"captions":[56],"context,":[59],"expressions":[60],"or":[61,168],"cues)":[63],"as":[64],"natural":[65],"language":[66],"supervision,":[67],"aiming":[68],"enhance":[70],"learning":[72],"rich":[74],"latent":[75],"representations,":[76],"for":[77,116,190],"zero-shot":[78,86,117],"classification.":[79],"test":[81],"this,":[82],"evaluate":[84,145],"using":[85,153],"classification":[87],"trained":[91,152],"four":[96],"popular":[97],"FER":[99],"datasets.":[100,142],"Our":[101],"findings":[102],"show":[103],"this":[105],"approach":[106],"yields":[107],"significant":[108],"improvements":[109],"when":[110],"compared":[111],"baseline":[113],"methods.":[114],"Specifically,":[115],"video":[118],"outperform":[121],"CLIP":[122],"by":[123],"over":[124],"10%":[125],"terms":[127,135],"Weighted":[129],"Average":[130,138],"Recall":[131,139],"5%":[133],"Unweighted":[137],"several":[141],"Furthermore,":[143],"representations":[147],"obtained":[148],"from":[149],"network":[151],"downstream":[158],"mental":[161],"health":[162],"symptom":[163,192],"estimation,":[164,194],"achieving":[165],"performance":[166],"comparable":[167,197],"superior":[169],"state-of-the-art":[171],"methods":[172],"strong":[174],"agreement":[175],"with":[176],"human":[177,199],"experts.":[178],"Namely,":[179],"achieved":[181],"Pearson's":[183],"correlation":[184],"coefficient":[185],"up":[187],"0.85":[189],"schizophrenia":[191],"severity":[193],"which":[195],"experts'":[200],"agreement.":[201],"The":[202],"code":[203],"publicly":[205],"available":[206],"https://github.com/NickyFot/EmoCLIP.git.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":6}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}