{"id":"https://openalex.org/W4416749321","doi":"https://doi.org/10.1109/iros60139.2025.11247325","title":"MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning","display_name":"MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749321","doi":"https://doi.org/10.1109/iros60139.2025.11247325"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5120101363","display_name":"Yifan Yang","orcid":"https://orcid.org/0009-0009-7146-2599"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peili Song","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peili Song","raw_affiliation_strings":["Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112926965","display_name":"Enfan Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enfan Lan","raw_affiliation_strings":["Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407381","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0001-9100-2906"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030233306","display_name":"Jingtai Liu","orcid":"https://orcid.org/0000-0003-2645-5655"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtai Liu","raw_affiliation_strings":["Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and Also With TBI Center, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"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":null,"issue":null,"first_page":"4232","last_page":"4239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7555000185966492,"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":0.7555000185966492,"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":0.0632999986410141,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.03240000084042549,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6607999801635742},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6312999725341797},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6215999722480774},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6171000003814697},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5450000166893005},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5170000195503235},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7904999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166000008583069},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6607999801635742},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6288999915122986},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6215999722480774},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41029998660087585},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1526868886","https://openalex.org/W2161168419","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W3107730598","https://openalex.org/W3107992529","https://openalex.org/W3202459445","https://openalex.org/W3202538459","https://openalex.org/W4226321491","https://openalex.org/W4312296985","https://openalex.org/W4312604533","https://openalex.org/W4312818087","https://openalex.org/W4312982499","https://openalex.org/W4313027996","https://openalex.org/W4383503782","https://openalex.org/W4390830078","https://openalex.org/W4390872672","https://openalex.org/W4390873470","https://openalex.org/W4400111043","https://openalex.org/W4402716094","https://openalex.org/W4402716422","https://openalex.org/W4403779064","https://openalex.org/W4403941285","https://openalex.org/W4404005290","https://openalex.org/W4405785377","https://openalex.org/W4405785669"],"related_works":[],"abstract_inverted_index":{"Category-level":[0],"object":[1,42],"pose":[2,7],"estimation,":[3],"which":[4],"predicts":[5],"the":[6],"of":[8,17],"objects":[9],"within":[10],"a":[11,54,73,92],"known":[12],"category":[13],"without":[14,140],"prior":[15],"knowledge":[16],"individual":[18],"instances,":[19],"is":[20,97,108,116],"essential":[21],"in":[22,134],"applications":[23],"like":[24],"warehouse":[25],"automation":[26],"and":[27,44,49,66,87,104,112,115,137],"manufacturing.":[28],"Existing":[29],"methods":[30,133],"relying":[31],"on":[32,110,122],"RGB":[33,62],"images":[34],"or":[35],"point":[36,64],"cloud":[37],"data":[38],"often":[39],"struggle":[40],"with":[41,79],"occlusion":[43],"generalization":[45],"across":[46],"different":[47],"instances":[48],"categories.":[50],"This":[51],"paper":[52],"proposes":[53],"multimodal-based":[55],"keypoint":[56,75],"learning":[57],"framework":[58],"(MK-Pose)":[59],"that":[60,128],"integrates":[61],"images,":[63],"clouds,":[65],"category-level":[67],"textual":[68],"descriptions.":[69],"The":[70,125],"model":[71],"uses":[72],"self-supervised":[74],"detection":[76],"module":[77,96],"enhanced":[78],"attention-":[80],"based":[81],"query":[82],"generation,":[83],"soft":[84],"heatmap":[85],"matching":[86],"graph-based":[88],"relational":[89],"modeling.":[90],"Additionally,":[91],"graph-enhanced":[93],"feature":[94],"fusion":[95],"designed":[98],"to":[99],"integrate":[100],"local":[101],"geometric":[102],"information":[103],"global":[105],"context.":[106],"MK-Pose":[107,129],"evaluated":[109],"CAMERA25":[111],"REAL275":[113],"dataset,":[114],"further":[117],"tested":[118],"for":[119],"cross-dataset":[120],"capability":[121],"HouseCat6D":[123],"dataset.":[124],"results":[126],"demonstrate":[127],"outperforms":[130],"existing":[131],"state-of-the-art":[132],"both":[135],"IoU":[136],"average":[138],"precision":[139],"shape":[141],"priors.":[142],"Codes":[143],"will":[144],"be":[145],"released":[146],"at":[147],"https://github.com/yangyifanYYF/MK-Pose.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}