{"id":"https://openalex.org/W7152419437","doi":"https://doi.org/10.1109/tase.2026.3682387","title":"Pre-Defined Keypoints Worth It: Multi-Modal Learning for Category-Level Articulated Objects Pose Estimation","display_name":"Pre-Defined Keypoints Worth It: Multi-Modal Learning for Category-Level Articulated Objects Pose Estimation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7152419437","doi":"https://doi.org/10.1109/tase.2026.3682387"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3682387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3682387","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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":"Li Zhang","orcid":"https://orcid.org/0000-0003-1610-6056"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1610-6056","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103454227","display_name":"W. B. Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Liu","orcid":"https://orcid.org/0000-0003-4218-8008"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4218-8008","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133243572","display_name":"Haonan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Jiang","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rujing Wang","orcid":"https://orcid.org/0000-0001-9534-3425"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujing Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Intelligent Machines and Hefei Institute of Physical Science, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9534-3425","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Intelligent Machines and Hefei Institute of Physical Science, Hefei, China","institution_ids":["https://openalex.org/I4210099079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133315175","display_name":"Xue Wang","orcid":"https://orcid.org/0000-0002-4086-0932"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Intelligent Machines and Hefei Institute of Physical Science, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4086-0932","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Intelligent Machines and Hefei Institute of Physical Science, Hefei, China","institution_ids":["https://openalex.org/I4210099079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101454332","display_name":"Yan Zhong","orcid":"https://orcid.org/0000-0003-0005-2620"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhong","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0005-2620","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38281022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"8248","last_page":"8262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8610000014305115,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8610000014305115,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.017400000244379044,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.01489999983459711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.8181999921798706},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.5708000063896179},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5702999830245972},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.37040001153945923},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.33719998598098755},{"id":"https://openalex.org/keywords/robot-vision","display_name":"Robot vision","score":0.3346000015735626},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3305000066757202}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8181999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.734499990940094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7214000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6431999802589417},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.5708000063896179},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5702999830245972},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C2983761899","wikidata":"https://www.wikidata.org/wiki/Q604674","display_name":"Robot vision","level":4,"score":0.3346000015735626},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29910001158714294},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.27090001106262207},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3682387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3682387","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1235217363","display_name":null,"funder_award_id":"62302143","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Articulated":[0],"objects":[1],"play":[2],"a":[3,31,63,66,75,104],"vital":[4],"role":[5],"in":[6,176],"daily":[7],"interactions,":[8],"but":[9],"traditional":[10],"RGB-based":[11],"pose":[12,39,144],"estimation":[13,40,79],"methods":[14],"often":[15],"face":[16],"challenges":[17],"such":[18],"as":[19],"lighting":[20],"variations":[21],"and":[22,59,85,99,127,164,180,184],"shadows.":[23],"To":[24,70],"address":[25],"these":[26],"limitations,":[27],"we":[28,73,102],"introduce":[29],"PAGE,":[30],"novel":[32],"Pre-defined":[33],"keypoint-based":[34],"framework":[35,138],"for":[36,123,174],"category-level":[37],"articulation":[38],"via":[41],"multi-modal":[42],"AliGnmEnt.":[43],"Our":[44],"approach":[45],"is":[46,117],"motivated":[47],"by":[48,119],"the":[49,52,83,113,121,141,146,162,189],"observation":[50],"that":[51,81,108],"distance":[53],"distribution":[54],"between":[55,96],"heuristically":[56],"generated":[57],"keypoints":[58],"visible":[60,125],"points":[61],"exhibits":[62],"divergent":[64],"pattern,":[65],"phenomenon":[67],"previously":[68],"overlooked.":[69],"tackle":[71],"this,":[72],"propose":[74],"customized":[76],"unsupervised":[77],"keypoint":[78],"method":[80],"enhances":[82],"stability":[84],"robustness":[86,163],"of":[87,145,167],"model":[88],"predictions.":[89],"Furthermore,":[90],"to":[91,134,158],"minimize":[92],"mutual":[93],"information":[94],"redundancy":[95],"point":[97,126],"clouds":[98],"RGB":[100],"images,":[101],"design":[103],"geometry-color":[105],"alignment":[106],"module":[107],"fuses":[109],"features":[110],"after":[111],"aligning":[112],"two":[114],"modalities.":[115],"This":[116,169],"followed":[118],"decoding":[120],"radius":[122],"each":[124],"applying":[128],"our":[129],"proposal":[130],"integration":[131],"scoring":[132],"strategy":[133],"predict":[135],"keypoints.":[136],"The":[137],"ultimately":[139],"outputs":[140],"per-part":[142],"6D":[143],"articulated":[147],"object.We":[148],"conduct":[149],"extensive":[150],"experiments":[151],"across":[152],"diverse":[153],"datasets,":[154],"ranging":[155],"from":[156],"synthetic":[157],"real-world":[159],"scenarios,":[160],"demonstrating":[161],"superior":[165],"performance":[166],"PAGE.":[168],"work":[170],"holds":[171],"significant":[172],"promise":[173],"applications":[175],"robotics,":[177],"embodied":[178],"intelligence,":[179],"augmented":[181],"reality.":[182],"Codes":[183],"datasets":[185],"are":[186],"available":[187],"at":[188],"website:":[190],"https://sites.google.com/view/pageforart.":[191]},"counts_by_year":[],"updated_date":"2026-04-23T06:14:38.165362","created_date":"2026-04-10T00:00:00"}