{"id":"https://openalex.org/W7124418642","doi":"https://doi.org/10.1007/s11263-025-02671-5","title":"Exploiting Class-agnostic Visual Prior for Few-shot Keypoint Detection","display_name":"Exploiting Class-agnostic Visual Prior for Few-shot Keypoint Detection","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7124418642","doi":"https://doi.org/10.1007/s11263-025-02671-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02671-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02671-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02671-5.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02671-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009755877","display_name":"Changsheng Lu","orcid":"https://orcid.org/0000-0002-1894-286X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I146617529","display_name":"Applied Science and Technology Research Institute","ror":"https://ror.org/03xmkea05","country_code":"CN","type":"facility","lineage":["https://openalex.org/I146617529"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["AU","CN","HK"],"is_corresponding":false,"raw_author_name":"Changsheng Lu","raw_affiliation_strings":["School of Computing, The Australian National University, Canberra, Australia","Von Neumann Institute, Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-1894-286X","affiliations":[{"raw_affiliation_string":"School of Computing, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Von Neumann Institute, Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I146617529","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101324723","display_name":"Hao Zhu","orcid":"https://orcid.org/0000-0002-1885-8051"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hao Zhu","raw_affiliation_strings":["Data61/CSIRO, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61/CSIRO, Canberra, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002212263","display_name":"Piotr Koniusz","orcid":"https://orcid.org/0000-0002-6340-5289"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Piotr Koniusz","raw_affiliation_strings":["Data61/CSIRO, Canberra, Australia","School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61/CSIRO, Canberra, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]},{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002212263"],"corresponding_institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I31746571","https://openalex.org/I42894916"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06158847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3269999921321869,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3269999921321869,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18359999358654022,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.08969999849796295,"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/inference","display_name":"Inference","score":0.5644000172615051},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4717000126838684},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46560001373291016},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42500001192092896},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3853999972343445},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.3702000081539154},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.34220001101493835},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.3398999869823456}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7788000106811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170000076293945},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42500001192092896},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02671-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02671-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02671-5.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02671-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02671-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02671-5.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124418642.pdf","grobid_xml":"https://content.openalex.org/works/W7124418642.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W1518641734","https://openalex.org/W1954152232","https://openalex.org/W1993277309","https://openalex.org/W2013640163","https://openalex.org/W2047670868","https://openalex.org/W2081293863","https://openalex.org/W2108598243","https://openalex.org/W2113325037","https://openalex.org/W2151103935","https://openalex.org/W2164943005","https://openalex.org/W2177274842","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2798836702","https://openalex.org/W2916798096","https://openalex.org/W2962697512","https://openalex.org/W2962730651","https://openalex.org/W2962887041","https://openalex.org/W2963150697","https://openalex.org/W2963350370","https://openalex.org/W2963474899","https://openalex.org/W2963781481","https://openalex.org/W2964105864","https://openalex.org/W2964352379","https://openalex.org/W2965729941","https://openalex.org/W2967819436","https://openalex.org/W2981413347","https://openalex.org/W2983156430","https://openalex.org/W2983454547","https://openalex.org/W2987701848","https://openalex.org/W2998508940","https://openalex.org/W3034399482","https://openalex.org/W3034453930","https://openalex.org/W3034942609","https://openalex.org/W3034974675","https://openalex.org/W3093326439","https://openalex.org/W3096609285","https://openalex.org/W3121137185","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3159481202","https://openalex.org/W3175577495","https://openalex.org/W3176065502","https://openalex.org/W3178774897","https://openalex.org/W4200082795","https://openalex.org/W4205398292","https://openalex.org/W4214508443","https://openalex.org/W4312233286","https://openalex.org/W4312383858","https://openalex.org/W4312804044","https://openalex.org/W4312815172","https://openalex.org/W4312960790","https://openalex.org/W4313036259","https://openalex.org/W4313058403","https://openalex.org/W4313156423","https://openalex.org/W4383198493","https://openalex.org/W4386071511","https://openalex.org/W4386076411"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"learning":[2,106],"based":[3,188],"keypoint":[4,20,24,53,123,199],"detectors":[5],"can":[6],"localize":[7],"specific":[8],"object":[9,108],"(or":[10],"body)":[11],"parts":[12],"well,":[13],"but":[14],"still":[15],"fall":[16],"short":[17],"of":[18,34,99,151,156,183],"general":[19,32],"detection.":[21],"Instead,":[22],"few-shot":[23],"detection":[25],"(FSKD)":[26],"is":[27,55],"an":[28,65],"underexplored":[29],"yet":[30],"more":[31],"task":[33],"localizing":[35],"either":[36],"base":[37],"or":[38,91],"novel":[39,129],"keypoints,":[40],"depending":[41],"on":[42,77,189],"the":[43,56,87,97,117,159,169,180,230],"prompted":[44],"support":[45,184],"samples.":[46],"In":[47],"FSKD,":[48],"how":[49],"to":[50,58,95,122,147,167,171,197,212],"build":[51],"robust":[52,174],"representations":[54,200],"key":[57],"success.":[59],"To":[60],"this":[61],"end,":[62],"we":[63,79,103,126,191],"propose":[64,127],"FSKD":[66,175,196,206],"approach":[67],"that":[68,217],"models":[69],"relations":[70],"between":[71,107],"keypoints.":[72],"As":[73,173],"keypoints":[74],"are":[75,140,240],"located":[76],"objects,":[78],"exploit":[80],"a":[81,128,143,164],"class-agnostic":[82,111],"visual":[83,112,137],"prior,":[84],"i.e":[85],".,":[86],"unsupervised":[88],"saliency":[89],"map":[90,94,162],"DINO":[92],"attentiveness":[93],"obtain":[96],"region":[98],"focus":[100],"within":[101],"which":[102],"perform":[104],"relation":[105],"patches.":[109],"The":[110,136,153],"prior":[113,138,161],"also":[114,177,227],"helps":[115],"suppress":[116],"background":[118],"noise":[119],"largely":[120],"irrelevant":[121],"locations.":[124],"Then,":[125],"Visual":[130],"Prior":[131],"guided":[132],"Vision":[133],"Transformer":[134],"(VPViT).":[135],"maps":[139],"refined":[141],"by":[142],"bespoke":[144],"morphology":[145],"learner":[146],"include":[148],"relevant":[149],"context":[150],"objects.":[152],"masked":[154],"self-attention":[155,170],"VPViT":[157],"takes":[158],"adapted":[160],"as":[163],"soft":[165],"mask":[166],"constrain":[168],"foregrounds.":[172],"must":[176],"deal":[178],"with":[179,201,207],"low":[181],"number":[182],"samples":[185],"and":[186,204,209,226,235],"occlusions,":[187],"VPViT,":[190],"further":[192],"investigate":[193],"i)":[194],"transductive":[195,233],"enhance":[198],"unlabeled":[202],"data":[203],"ii)":[205],"masking":[208],"alignment":[210],"(MAA)":[211],"improve":[213],"robustness.":[214],"We":[215],"show":[216],"our":[218],"model":[219],"performs":[220],"well":[221],"in":[222,232],"seven":[223],"public":[224],"datasets,":[225],"significantly":[228],"improves":[229],"accuracy":[231],"inference":[234],"under":[236],"occlusions.":[237],"Source":[238],"codes":[239],"available":[241],"at":[242],"https://github.com/AlanLuSun/VPViT":[243],".":[244]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-17T00:00:00"}