{"id":"https://openalex.org/W4403780780","doi":"https://doi.org/10.1145/3664647.3681231","title":"RobustFace: Adaptive Mining of Noise and Hard Samples for Robust Face Recognitions","display_name":"RobustFace: Adaptive Mining of Noise and Hard Samples for Robust Face Recognitions","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780780","doi":"https://doi.org/10.1145/3664647.3681231"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681231","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/A5100754091","display_name":"Yang Xin","orcid":"https://orcid.org/0009-0007-0449-2320"},"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":true,"raw_author_name":"Yang Xin","raw_affiliation_strings":["Shenzhen University, ShenZhen, GuangDong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, ShenZhen, GuangDong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048421704","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-3224-0063"},"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":"Yu Zhou","raw_affiliation_strings":["Shenzhen University, ShenZhen, GuangDong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, ShenZhen, GuangDong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005727907","display_name":"Jianmin Jiang","orcid":"https://orcid.org/0000-0002-7576-3999"},"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":"Jianmin Jiang","raw_affiliation_strings":["Shenzhen University, ShenZhen, GuangDong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, ShenZhen, GuangDong, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100754091"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.5499,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6718978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5065","last_page":"5073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10828","display_name":"Biometric Identification and Security","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/face","display_name":"Face (sociological concept)","score":0.6560553312301636},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6366770267486572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6208524107933044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37757405638694763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37384724617004395}],"concepts":[{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6560553312301636},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6366770267486572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208524107933044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37757405638694763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37384724617004395},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681231","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2024922353","https://openalex.org/W2087007396","https://openalex.org/W2341528187","https://openalex.org/W2515770085","https://openalex.org/W2663800299","https://openalex.org/W2736633948","https://openalex.org/W2871667416","https://openalex.org/W2887500939","https://openalex.org/W2962898354","https://openalex.org/W2963351448","https://openalex.org/W2963460857","https://openalex.org/W2963466847","https://openalex.org/W2963516811","https://openalex.org/W2963697299","https://openalex.org/W2963814162","https://openalex.org/W2964292098","https://openalex.org/W2967637014","https://openalex.org/W2969985801","https://openalex.org/W2998469040","https://openalex.org/W3035693354","https://openalex.org/W3101998545","https://openalex.org/W3109225549","https://openalex.org/W3119687891","https://openalex.org/W3167584510","https://openalex.org/W3169129566","https://openalex.org/W3199528201","https://openalex.org/W3210061328","https://openalex.org/W3217435001","https://openalex.org/W4214883769","https://openalex.org/W4304086144","https://openalex.org/W4312402191","https://openalex.org/W4312430254","https://openalex.org/W4312769845","https://openalex.org/W4388193481"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"While":[0,187],"margin-based":[1,75],"deep":[2,65],"face":[3,53,66],"recognition":[4,67,115],"models,":[5,172],"such":[6],"as":[7],"ArcFace":[8],"and":[9,108,163,184],"AdaFace,":[10],"have":[11],"achieved":[12],"remarkable":[13],"successes":[14],"over":[15],"recent":[16],"years,":[17],"they":[18],"may":[19],"suffer":[20,192],"from":[21,193],"degraded":[22],"performances":[23,116,145],"when":[24,35,153,174],"encountering":[25],"training":[26,127],"sets":[27],"corrupted":[28,180],"with":[29,78,148,155,160,181],"noises.":[30,186],"This":[31],"is":[32],"often":[33],"inevitable":[34],"massively":[36],"large":[37],"scale":[38],"datasets":[39,54,130,178],"need":[40],"to":[41,49,84,100,121],"be":[42],"dealt":[43],"with,":[44],"yet":[45],"it":[46],"remains":[47],"difficult":[48],"construct":[50],"clean":[51,156],"enough":[52],"under":[55,201],"these":[56,202],"circumstances.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,94],"propose":[62],"a":[63,96],"robust":[64],"model,":[68],"RobustFace,":[69],"by":[70,111],"combining":[71],"the":[72,79,87,103,113,118,132,149,170,175,188],"advantages":[73],"of":[74,81,89,134,198,210],"learning":[76],"models":[77,152,191],"strength":[80],"mining-based":[82],"approaches":[83],"effectively":[85],"mitigate":[86],"impact":[88],"noises":[90],"during":[91],"trainings.":[92],"Specifically,":[93],"introduce":[95],"noise-adaptive":[97],"mining":[98],"strategy":[99],"dynamically":[101],"adjust":[102],"emphasis":[104],"balance":[105],"between":[106],"hard":[107],"noise":[109],"samples":[110],"monitoring":[112],"model's":[114],"at":[117],"batch":[119],"level":[120],"provide":[122],"optimization-oriented":[123],"feedback,":[124],"enabling":[125],"direct":[126],"on":[128],"noisy":[129,165,177],"without":[131],"requirement":[133],"pre-training.":[135],"Extensive":[136],"experiments":[137],"validate":[138],"that":[139],"our":[140,204],"proposed":[141,205],"RobustFace":[142,167],"achieves":[143],"competitive":[144],"in":[146],"comparison":[147],"existing":[150,171,189],"SoTA":[151],"trained":[154,159],"datasets.":[157],"When":[158],"both":[161,182],"real-world":[162],"synthetic":[164,176],"datasets,":[166],"significantly":[168],"outperforms":[169],"especially":[173],"are":[179],"close-set":[183],"open-set":[185],"baseline":[190],"an":[194],"average":[195],"performance":[196],"drop":[197],"around":[199],"40%,":[200],"circumstances,":[203],"still":[206],"delivers":[207],"accuracy":[208],"rates":[209],"more":[211],"than":[212],"90%.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}