{"id":"https://openalex.org/W4411086363","doi":"https://doi.org/10.1109/lra.2025.3577460","title":"LanCOPE: Language-Guided Category-Level Object Pose Estimation From a Single RGB Image","display_name":"LanCOPE: Language-Guided Category-Level Object Pose Estimation From a Single RGB Image","publication_year":2025,"publication_date":"2025-06-06","ids":{"openalex":"https://openalex.org/W4411086363","doi":"https://doi.org/10.1109/lra.2025.3577460"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3577460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3577460","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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":"https://openalex.org/A5112361483","display_name":"Hui Yang","orcid":"https://orcid.org/0009-0005-2648-9566"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yang","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0005-2648-9566","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637917","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-8644-2998"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8644-2998","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108049455","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0003-0604-8024"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0604-8024","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015511443","display_name":"Jin Zheng","orcid":"https://orcid.org/0000-0003-3353-1775"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zheng","raw_affiliation_strings":["School of Architecture and Art, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3353-1775","affiliations":[{"raw_affiliation_string":"School of Architecture and Art, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenqi Dai","orcid":"https://orcid.org/0009-0007-1379-083X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenqi Dai","raw_affiliation_strings":["National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-1379-083X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["Department of Computer Science and Software Engineering, University of Western Australia, Crawley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5206-3842","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.12276499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"7","first_page":"7555","last_page":"7562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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":0.9991999864578247,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9936000108718872,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7043820023536682},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6609936952590942},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.654589056968689},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5642424821853638},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5509756803512573},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5084737539291382},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5031308531761169},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4337954819202423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38875240087509155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3678637742996216},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05853530764579773}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7043820023536682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6609936952590942},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.654589056968689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5642424821853638},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5509756803512573},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5084737539291382},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5031308531761169},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4337954819202423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38875240087509155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3678637742996216},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05853530764579773},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2025.3577460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3577460","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/8861e4dc-0699-4582-9b2f-2ee18b3ccdd2","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/8861e4dc-0699-4582-9b2f-2ee18b3ccdd2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Yang, H, Sun, W, Liu, J, Zheng, J, Dai, Z & Mian, A 2025, 'LanCOPE : Language-Guided Category-Level Object Pose Estimation from a Single RGB Image', IEEE Robotics and Automation Letters, vol. 10, no. 7, pp. 7555-7562. https://doi.org/10.1109/LRA.2025.3577460","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1201409244","display_name":null,"funder_award_id":"62473141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2187632043","display_name":null,"funder_award_id":"2024JJ5098","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G3206439402","display_name":null,"funder_award_id":"FT210100268","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G3408348127","display_name":null,"funder_award_id":"U22A2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963892972","https://openalex.org/W2988766935","https://openalex.org/W3034986117","https://openalex.org/W3093644825","https://openalex.org/W3107992529","https://openalex.org/W3164543136","https://openalex.org/W3196328566","https://openalex.org/W3202459445","https://openalex.org/W3206934897","https://openalex.org/W4205105995","https://openalex.org/W4220980185","https://openalex.org/W4285221346","https://openalex.org/W4285233964","https://openalex.org/W4312801317","https://openalex.org/W4312933868","https://openalex.org/W4321033239","https://openalex.org/W4323065906","https://openalex.org/W4366148220","https://openalex.org/W4366208220","https://openalex.org/W4383108425","https://openalex.org/W4383108836","https://openalex.org/W4383109669","https://openalex.org/W4386075656","https://openalex.org/W4390872210","https://openalex.org/W4390873470","https://openalex.org/W4391855168","https://openalex.org/W4392223601","https://openalex.org/W4392979363","https://openalex.org/W4394671432","https://openalex.org/W4396753489","https://openalex.org/W4396914081","https://openalex.org/W4401415110","https://openalex.org/W4401416926","https://openalex.org/W4402753839","https://openalex.org/W4403779064","https://openalex.org/W4405785669","https://openalex.org/W4408564950"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4387967917","https://openalex.org/W4387968151","https://openalex.org/W4386925306","https://openalex.org/W3132124459","https://openalex.org/W2946083937","https://openalex.org/W3101088080","https://openalex.org/W2894986065","https://openalex.org/W4299867837"],"abstract_inverted_index":{"Monocular":[0],"RGB-based":[1],"category-level":[2,50],"object":[3,34,51,184],"pose":[4,52,185],"estimation":[5,53],"is":[6,202],"more":[7,44],"practical":[8],"and":[9,23,75,98,108,146,162,191],"cost-effective":[10],"for":[11,91],"robotics.":[12],"However,":[13],"existing":[14],"methods":[15],"do":[16],"not":[17],"fully":[18],"exploit":[19],"the":[20,38,83,92,104,156,160,166,177,183],"rich":[21],"semantic":[22,144,157],"contextual":[24],"information":[25,138,158],"in":[26,40,111],"multimodal":[27,126],"data":[28],"(e.g.":[29],"language)":[30],"that":[31,195],"provides":[32],"additional":[33],"attributes":[35],"to":[36,67,81,101,124,135,154,181],"guide":[37,103],"model":[39],"extracting":[41],"category":[42,113],"features":[43],"reliably.":[45],"We":[46,86,115],"propose":[47],"a":[48,57,71,117,131,151,172],"language-guided":[49],"method":[54,64],"(LanCOPE),":[55],"taking":[56],"single":[58,72],"RGB":[59,73,93],"image":[60,74,109],"as":[61],"input.":[62],"Our":[63,200],"uses":[65,150],"DINOv2":[66],"recover":[68,182],"depth":[69],"from":[70],"converts":[76],"it":[77,149],"into":[78],"point":[79,96,105],"cloud":[80,97,106],"perceive":[82],"object's":[84],"geometry.":[85],"then":[87],"introduce":[88],"language":[89,161],"descriptions":[90],"image,":[94],"estimated":[95],"overall":[99,167],"scene":[100],"better":[102],"encoder":[107,110],"learning":[112],"features.":[114,127],"develop":[116],"cross-modal":[118],"differential":[119,132],"perception":[120,133],"feature":[121],"fusion":[122,179],"network":[123,129,174],"fuse":[125,155],"This":[128],"employs":[130],"module":[134],"eliminate":[136],"redundant":[137],"across":[139],"different":[140],"modalities,":[141],"highlighting":[142],"signifcant":[143],"differences":[145],"similarities.":[147],"Furthermore,":[148],"cross-attention":[152],"mechanism":[153],"of":[159],"vision":[163],"features,":[164],"improving":[165],"perception.":[168],"Finally,":[169],"we":[170],"design":[171],"denoising":[173],"based":[175],"on":[176,189],"skip":[178],"transformer":[180],"accurately.":[186],"Extensive":[187],"experiments":[188],"REAL275":[190],"Wild6D":[192],"datasets":[193],"show":[194],"LanCOPE":[196],"achieves":[197],"state-of-the-art":[198],"performance.":[199],"code":[201],"available":[203],"at":[204],"LanCOPE.":[205]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}