{"id":"https://openalex.org/W4416177752","doi":"https://doi.org/10.1109/tcsvt.2025.3632418","title":"CAMD: Context-Aware Masked Distillation for General Self-Supervised Facial Representation Pre-Training","display_name":"CAMD: Context-Aware Masked Distillation for General Self-Supervised Facial Representation Pre-Training","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416177752","doi":"https://doi.org/10.1109/tcsvt.2025.3632418"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3632418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3632418","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Sensen Wang","orcid":"https://orcid.org/0009-0004-6616-5892"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sensen Wang","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0004-6616-5892","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073464445","display_name":"Si Chen","orcid":"https://orcid.org/0000-0002-5631-7942"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Chen","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5631-7942","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032628425","display_name":"Da\u2010Han Wang","orcid":"https://orcid.org/0000-0002-5901-0778"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da-Han Wang","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5901-0778","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016123060","display_name":"Hua Yang","orcid":"https://orcid.org/0000-0001-5536-503X"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Hua","raw_affiliation_strings":["Institute of Electronics, Communications and Information Technology, Queen’s University Belfast, Belfast, U.K","Institute of Electronics, Communications and Information Technology, Queen’s University Belfast, Belfast, UK"],"raw_orcid":"https://orcid.org/0000-0001-5536-503X","affiliations":[{"raw_affiliation_string":"Institute of Electronics, Communications and Information Technology, Queen’s University Belfast, Belfast, U.K","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"Institute of Electronics, Communications and Information Technology, Queen’s University Belfast, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-3674-7160","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5615,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.702552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"4","first_page":"4663","last_page":"4677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9110999703407288,"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":0.9110999703407288,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.021400000900030136,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01679999940097332,"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/feature","display_name":"Feature (linguistics)","score":0.6126000285148621},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5867999792098999},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5654000043869019},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5284000039100647},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5278000235557556},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.46799999475479126},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43939998745918274},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43380001187324524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7283999919891357},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43939998745918274},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.4020000100135803},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3632418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3632418","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4031016800","display_name":null,"funder_award_id":"3502Z20241029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6920052985","display_name":null,"funder_award_id":"62571466","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8872334155","display_name":null,"funder_award_id":"3502Z20241027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"pre-training":[1,20,108],"has":[2],"been":[3],"shown":[4],"to":[5,28,43,63,86,127,152],"effectively":[6,64],"learn":[7,65,87,173],"transferable":[8],"representations":[9,68,115,122],"from":[10],"unlabeled":[11],"images":[12],"in":[13,35],"many":[14],"visual":[15],"tasks.":[16,49,73],"However,":[17],"existing":[18],"self-supervised":[19,102],"methods":[21],"lack":[22],"sufficient":[23],"context-awareness":[24],"and":[25,92,97,133,136,167,176,204,212,217],"are":[26],"difficult":[27],"obtain":[29],"fine-grained":[30,70,179],"facial":[31,47,67,71,180,190,198,201],"representations,":[32],"thus":[33],"resulting":[34],"the":[36,41,88,111,118,142,155,165,214],"weak":[37],"generalization":[38],"ability":[39],"of":[40,157,164],"model":[42],"deal":[44],"with":[45],"various":[46],"analysis":[48,72,191],"To":[50],"address":[51],"this":[52,105],"issue,":[53],"we":[54],"propose":[55],"a":[56],"Context-Aware":[57],"Masked":[58],"Distillation":[59],"method,":[60],"termed":[61],"CAMD,":[62],"general":[66],"for":[69],"The":[74,219],"CAMD":[75,143],"method":[76,144,184],"first":[77],"designs":[78],"an":[79,146],"innovative":[80],"local-to-global":[81],"masked":[82],"image":[83],"modeling":[84],"framework":[85],"contextual":[89,174],"spatial":[90,139],"structures":[91],"semantic":[93,129],"relationships":[94],"between":[95,160],"local":[96,120,132],"global":[98,113,134],"features,":[99],"enabling":[100],"effective":[101],"pre-training.":[103],"In":[104],"framework,":[106],"our":[107],"task":[109],"predicts":[110],"dense":[112],"feature":[114,121,181],"based":[116],"on":[117,187],"visible":[119],"after":[123],"masking,":[124],"so":[125],"as":[126],"achieve":[128],"alignment":[130],"across":[131],"views":[135],"significantly":[137],"enhance":[138],"sensitivity.":[140],"Moreover,":[141],"leverages":[145],"attention-driven":[147],"cross-view":[148],"hierarchical":[149],"distillation":[150],"module":[151,171],"fully":[153],"distill":[154],"features":[156],"related":[158],"regions":[159],"different":[161],"encoder":[162],"layers":[163],"online":[166],"target":[168],"encoders.":[169],"This":[170],"can":[172],"dependencies":[175],"capture":[177],"discriminative":[178],"representations.":[182],"Our":[183],"is":[185,221],"evaluated":[186],"multiple":[188],"downstream":[189],"tasks,":[192],"including":[193],"face":[194,196],"alignment,":[195],"parsing,":[197],"attribute":[199],"recognition,":[200,203],"expression":[202],"head":[205],"pose":[206],"estimation,":[207],"all":[208],"achieving":[209],"state-of-the-art":[210],"results":[211],"exhibiting":[213],"strong":[215],"generality":[216],"effectiveness.":[218],"code":[220],"available":[222],"at:":[223],"https://github.com/mumumu-wss/CAMD.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-11-13T00:00:00"}