{"id":"https://openalex.org/W4401415315","doi":"https://doi.org/10.1109/icra57147.2024.10610601","title":"AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViT","display_name":"AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViT","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415315","doi":"https://doi.org/10.1109/icra57147.2024.10610601"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610601","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5003819876","display_name":"Fangbo Qin","orcid":"https://orcid.org/0000-0002-4085-0857"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangbo Qin","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003369387","display_name":"Taogang Hou","orcid":"https://orcid.org/0000-0002-6992-5269"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taogang Hou","raw_affiliation_strings":["Beijing Jiaotong University,School of Electronic and Information Engineering,Beijing,China,100044"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Electronic and Information Engineering,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101857094","display_name":"Shan Lin","orcid":"https://orcid.org/0000-0002-3254-1923"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Lin","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,San Diego, La Jolla,CA,USA,92093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,San Diego, La Jolla,CA,USA,92093","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018389432","display_name":"Kaiyuan Wang","orcid":"https://orcid.org/0000-0002-0029-0656"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiyuan Wang","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,San Diego, La Jolla,CA,USA,92093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,San Diego, La Jolla,CA,USA,92093","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054598974","display_name":"Michael C. Yip","orcid":"https://orcid.org/0000-0001-9689-0172"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael C. Yip","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,San Diego, La Jolla,CA,USA,92093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,San Diego, La Jolla,CA,USA,92093","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107848501","display_name":"Shan Yu","orcid":"https://orcid.org/0009-0000-5650-4505"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"12397","last_page":"12403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9962000250816345,"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":0.9958000183105469,"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/shot","display_name":"Shot (pellet)","score":0.7323021292686462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715570330619812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6920455694198608},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5962152481079102},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5626254677772522},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5576759576797485},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5382146239280701},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48587721586227417},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4757116436958313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4215034544467926},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08096113801002502}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7323021292686462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715570330619812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6920455694198608},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5962152481079102},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5626254677772522},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5576759576797485},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5382146239280701},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48587721586227417},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4757116436958313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4215034544467926},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08096113801002502},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610601","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2302255633","https://openalex.org/W2926550000","https://openalex.org/W2979458572","https://openalex.org/W3034275286","https://openalex.org/W3043075211","https://openalex.org/W3088321106","https://openalex.org/W3089045049","https://openalex.org/W3090952442","https://openalex.org/W3091470805","https://openalex.org/W3104724231","https://openalex.org/W3107939686","https://openalex.org/W3130857053","https://openalex.org/W3135359526","https://openalex.org/W3149079890","https://openalex.org/W3159481202","https://openalex.org/W3166285241","https://openalex.org/W3199947443","https://openalex.org/W3200540310","https://openalex.org/W3203518786","https://openalex.org/W3205504840","https://openalex.org/W4221162134","https://openalex.org/W4225569978","https://openalex.org/W4284898803","https://openalex.org/W4289665802","https://openalex.org/W4321319299","https://openalex.org/W4327663536","https://openalex.org/W4366208220","https://openalex.org/W4383108397","https://openalex.org/W4390874575","https://openalex.org/W6739901393","https://openalex.org/W6752823625","https://openalex.org/W6784333009","https://openalex.org/W6795475546","https://openalex.org/W6800217721","https://openalex.org/W6811470611","https://openalex.org/W6843515625","https://openalex.org/W6845226490","https://openalex.org/W6851800889"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Towards":[0],"flexible":[1],"object-centric":[2],"visual":[3],"perception,":[4],"we":[5],"propose":[6],"a":[7,41,127,130,134],"one-shot":[8],"instance-aware":[9],"object":[10,33,113,120],"keypoint":[11],"(OKP)":[12],"extraction":[13],"approach,":[14],"AnyOKP,":[15],"which":[16,57,137],"leverages":[17],"the":[18,86,101,105,124,141],"powerful":[19],"representation":[20],"ability":[21],"of":[22,35,126],"pretrained":[23],"vision":[24],"transformer":[25],"(ViT),":[26],"and":[27,53,73,133,144,155],"can":[28],"obtain":[29],"keypoints":[30,92],"on":[31,77,104,118],"multiple":[32],"instances":[34],"arbitrary":[36],"category":[37],"after":[38],"learning":[39],"from":[40],"support":[42,72],"image.":[43],"An":[44],"off-the-shelf":[45],"petrained":[46],"ViT":[47],"is":[48,58,116],"directly":[49],"deployed":[50],"for":[51,70],"generalizable":[52],"transferable":[54],"feature":[55,62,102],"extraction,":[56],"followed":[59],"by":[60],"training-free":[61],"enhancement.":[63],"The":[64],"best-prototype":[65],"pairs":[66],"(BPPs)":[67],"are":[68,95],"searched":[69],"in":[71],"query":[74],"images":[75,121],"based":[76],"appearance":[78],"similarity,":[79],"to":[80,100,152],"yield":[81],"instance-unaware":[82],"candidate":[83,91],"keypoints.":[84],"Then,":[85],"entire":[87],"graph":[88,106],"with":[89,123],"all":[90],"as":[93],"vertices":[94],"divided":[96],"into":[97],"sub-graphs":[98],"according":[99],"distributions":[103],"edges.":[107],"Finally,":[108],"each":[109],"sub-graph":[110],"represents":[111],"an":[112],"instance.":[114],"AnyOKP":[115],"evaluated":[117],"real":[119],"collected":[122],"cameras":[125],"robot":[128],"arm,":[129],"mobile":[131],"robot,":[132,136],"surgical":[135],"not":[138],"only":[139],"demonstrates":[140],"cross-category":[142],"flexibility":[143],"instance":[145],"awareness,":[146],"but":[147],"also":[148],"show":[149],"remarkable":[150],"robustness":[151],"domain":[153],"shift":[154],"viewpoint":[156],"change.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}