{"id":"https://openalex.org/W4403791798","doi":"https://doi.org/10.1145/3664647.3681287","title":"FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training","display_name":"FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791798","doi":"https://doi.org/10.1145/3664647.3681287"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681287","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5100332356","display_name":"Yudong Li","orcid":"https://orcid.org/0000-0001-6779-8836"},"institutions":[{"id":"https://openalex.org/I4210104064","display_name":"Shenzhen Academy of Robotics","ror":"https://ror.org/01h027j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210104064"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yudong Li","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University & Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University & Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China","institution_ids":["https://openalex.org/I4210104064","https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033865377","display_name":"Xianxu Hou","orcid":"https://orcid.org/0000-0002-8728-2842"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianxu Hou","raw_affiliation_strings":["School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114416552","display_name":"Zheng Dezhi","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Dezhi","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University & Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University & Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019313200","display_name":"Linlin Shen","orcid":"https://orcid.org/0000-0003-1420-0815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University & Shenzhen, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, Chile"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University & Shenzhen, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, Chile","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055811120","display_name":"Zhe Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Zhao","raw_affiliation_strings":["Tencent AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100332356"],"corresponding_institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210104064"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19224111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9973999857902527,"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":0.9973999857902527,"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/T13953","display_name":"Digital Imaging in Medicine","score":0.9765999913215637,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9628000259399414,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5823956727981567},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.545491635799408},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5006978511810303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49319881200790405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4726009964942932},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4162767827510834},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1762717366218567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823956727981567},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.545491635799408},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5006978511810303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49319881200790405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4726009964942932},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4162767827510834},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1762717366218567},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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:10.1145/3664647.3681287","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2006902452","https://openalex.org/W2058961190","https://openalex.org/W2115651492","https://openalex.org/W2295107390","https://openalex.org/W2440214111","https://openalex.org/W2462523589","https://openalex.org/W2510725918","https://openalex.org/W2738672149","https://openalex.org/W2745497104","https://openalex.org/W2798685991","https://openalex.org/W2884822772","https://openalex.org/W2962786991","https://openalex.org/W2963789946","https://openalex.org/W2964347177","https://openalex.org/W2998428583","https://openalex.org/W3010526057","https://openalex.org/W3034384783","https://openalex.org/W3034521057","https://openalex.org/W3034552680","https://openalex.org/W3035418072","https://openalex.org/W3092693034","https://openalex.org/W3092820011","https://openalex.org/W3093565423","https://openalex.org/W3120485916","https://openalex.org/W3122081138","https://openalex.org/W3122591556","https://openalex.org/W3146133395","https://openalex.org/W3176641147","https://openalex.org/W3202069916","https://openalex.org/W3208722310","https://openalex.org/W4285414583","https://openalex.org/W4285601021","https://openalex.org/W4304092233","https://openalex.org/W4306820534","https://openalex.org/W4313130906","https://openalex.org/W4313135108","https://openalex.org/W4313161555","https://openalex.org/W4382461431","https://openalex.org/W4385565577","https://openalex.org/W4385572634","https://openalex.org/W4386065626","https://openalex.org/W4386071798"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W3204019825"],"abstract_inverted_index":{"While":[0],"significant":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"in":[6,20,151],"multi-modal":[7],"learning":[8],"driven":[9],"by":[10,60],"large-scale":[11,44],"image-text":[12],"datasets,":[13],"there":[14],"is":[15,58],"still":[16],"a":[17,43,70,99,152],"noticeable":[18],"gap":[19],"the":[21,27,34,62,104,112,119,123],"availability":[22],"of":[23,36,114,154],"such":[24],"datasets":[25],"within":[26],"facial":[28,37],"domain.":[29],"To":[30,110],"facilitate":[31],"and":[32,69,80,94,132,163,169],"advance":[33],"field":[35],"representation":[38,135],"learning,":[39],"we":[40,117],"present":[41],"FLIP-80M,":[42,125],"visual-linguistic":[45],"dataset":[46,67,107,168],"comprising":[47],"over":[48],"80":[49],"million":[50],"face":[51,87,89,155,159,161,164],"images":[52],"paired":[53],"with":[54],"text":[55,92],"descriptions.":[56],"FLIP-80M":[57,101],"constructed":[59],"leveraging":[61],"large":[63],"openly":[64],"available":[65,172],"image-text-pair":[66],"LAION-5B":[68],"mixed-method":[71],"approach":[72],"to":[73,108,126],"filter":[74],"face-related":[75],"pairs":[76],"from":[77],"both":[78],"visual":[79],"linguistic":[81],"perspectives.":[82],"Our":[83,141],"curation":[84],"process":[85],"involves":[86],"detection,":[88],"caption":[90],"classification,":[91],"de-noising,":[93],"synthesis-based":[95],"image":[96],"augmentation.":[97],"As":[98],"result,":[100],"stands":[102],"as":[103],"largest":[105],"face-text":[106],"date.":[109],"evaluate":[111],"potential":[113],"our":[115,145],"dataset,":[116],"fine-tune":[118],"CLIP":[120],"model":[121,147],"using":[122],"proposed":[124],"create":[127],"FLIP":[128,146],"(Facial":[129],"Language-Image":[130],"Pretraining)":[131],"assess":[133],"its":[134],"capabilities":[136],"across":[137],"various":[138],"downstream":[139],"tasks.":[140],"experiments":[142],"demonstrate":[143],"that":[144],"achieves":[148],"state-of-the-art":[149],"results":[150],"range":[153],"analysis":[156],"tasks,":[157],"including":[158],"parsing,":[160],"alignment,":[162],"attribute":[165],"classification.":[166],"The":[167],"models":[170],"are":[171],"at":[173],"https://github.com/ydli-ai/FLIP.":[174]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}