{"id":"https://openalex.org/W4280533594","doi":"https://doi.org/10.1109/icra46639.2022.9811367","title":"Learning 6-DoF Object Poses to Grasp Category-Level Objects by Language Instructions","display_name":"Learning 6-DoF Object Poses to Grasp Category-Level Objects by Language Instructions","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4280533594","doi":"https://doi.org/10.1109/icra46639.2022.9811367"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811367","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5071789313","display_name":"Chilam Cheang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chilam Cheang","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039653330","display_name":"Haitao Lin","orcid":"https://orcid.org/0000-0003-2767-127X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Lin","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University,School of Data Science","School of Data Science, Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Data Science","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Data Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071789313"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.1386,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85156139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8476","last_page":"8482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940000176429749,"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/grasp","display_name":"GRASP","score":0.8105108737945557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966412305831909},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7221576571464539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7089868783950806},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6300089359283447},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5671185255050659},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5322040915489197},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4974713623523712},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4679286479949951},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4658205509185791},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4624521732330322},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.451910138130188},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.4402104914188385},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4369279742240906},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39538973569869995},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1047908365726471},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0825640857219696}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8105108737945557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966412305831909},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7221576571464539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7089868783950806},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6300089359283447},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5671185255050659},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5322040915489197},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4974713623523712},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4679286479949951},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4658205509185791},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4624521732330322},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.451910138130188},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4402104914188385},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4369279742240906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39538973569869995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1047908365726471},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0825640857219696},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811367","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G3894836115","display_name":null,"funder_award_id":"19511120700,2O2lSHZDZXOlO3","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5077234039","display_name":null,"funder_award_id":"62076067","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1526868886","https://openalex.org/W1825604117","https://openalex.org/W1999156278","https://openalex.org/W2251512949","https://openalex.org/W2416144529","https://openalex.org/W2962716343","https://openalex.org/W2963121255","https://openalex.org/W2963150697","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963244312","https://openalex.org/W2963756608","https://openalex.org/W2963892972","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2980088508","https://openalex.org/W2984121207","https://openalex.org/W2988715931","https://openalex.org/W2998012869","https://openalex.org/W3004284873","https://openalex.org/W3034597466","https://openalex.org/W3035268124","https://openalex.org/W3035398346","https://openalex.org/W3035605030","https://openalex.org/W3035662013","https://openalex.org/W3037369911","https://openalex.org/W3037533539","https://openalex.org/W3090584485","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3107992529","https://openalex.org/W3140398265","https://openalex.org/W3163945288","https://openalex.org/W3175234951","https://openalex.org/W3175572814","https://openalex.org/W3179868941","https://openalex.org/W3205420310","https://openalex.org/W3205613184","https://openalex.org/W4293584584","https://openalex.org/W6631711059","https://openalex.org/W6716462739","https://openalex.org/W6739778489","https://openalex.org/W6750227808","https://openalex.org/W6775517382","https://openalex.org/W6780515072","https://openalex.org/W6797336786"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W4387804363","https://openalex.org/W2019547100","https://openalex.org/W2477150073","https://openalex.org/W2515493494"],"abstract_inverted_index":{"This":[0,17,88],"paper":[1],"studies":[2],"the":[3,10,20,46,52,62,69,79,85,126,130,133,156,162,177,186,202,214,230,241,244],"task":[4,18],"of":[5,54,65,81,139,145,190,232,247],"any":[6],"objects":[7,55,67],"grasping":[8,111],"from":[9,56,68,155],"known":[11,70],"categories":[12],"by":[13,112,180],"free-form":[14],"language":[15,26,137],"instructions.":[16],"demands":[19],"technique":[21],"in":[22,50,93,132,235],"computer":[23],"vision,":[24],"natural":[25],"processing,":[27],"and":[28,59,142,151,160,184],"robotics.":[29],"We":[30],"bring":[31],"these":[32],"disciplines":[33],"together":[34],"on":[35,77,224],"this":[36,97,117],"open":[37],"challenge,":[38],"which":[39,196],"is":[40,197,211],"essential":[41],"to":[42,108,228,240],"human-robot":[43],"interaction.":[44],"Critically,":[45],"key":[47],"challenge":[48],"lies":[49],"inferring":[51,78],"category":[53],"linguistic":[57],"instructions":[58],"accurately":[60],"estimating":[61],"6-DoF":[63,103,164,188],"information":[64],"unseen":[66,194],"classes.":[71],"In":[72,96],"contrast,":[73],"previous":[74],"works":[75],"focus":[76],"pose":[80,166,189],"object":[82,105,165,179],"candidates":[83],"at":[84,167],"instance":[86,195],"level.":[87],"significantly":[89],"limits":[90],"its":[91],"applications":[92],"real-world":[94,236],"scenarios.":[95],"paper,":[98],"we":[99,119,220],"propose":[100,120],"a":[101,121,171,191,225],"language-guided":[102],"category-level":[104],"localization":[106],"model":[107],"achieve":[109],"robotic":[110],"comprehending":[113],"human":[114,182],"intention.":[115],"To":[116],"end,":[118],"novel":[122],"two-stage":[123],"method.":[124,218],"Particularly,":[125],"first":[127],"stage":[128,149],"grounds":[129],"target":[131],"RGB":[134],"image":[135,159],"through":[136],"description":[138],"names,":[140],"attributes,":[141],"spatial":[143],"relations":[144],"objects.":[146],"The":[147],"second":[148],"extracts":[150],"segments":[152],"point":[153],"clouds":[154],"cropped":[157],"depth":[158],"estimates":[161],"full":[163,187],"category-level.":[168],"Under":[169],"such":[170],"manner,":[172],"our":[173,209,222,233,248],"approach":[174,223],"can":[175],"locate":[176],"specific":[178],"following":[181],"instructions,":[183],"estimate":[185],"category-known":[192],"but":[193],"not":[198],"utilized":[199],"for":[200,243],"training":[201],"model.":[203],"Extensive":[204],"experimental":[205],"results":[206],"show":[207],"that":[208],"method":[210],"competitive":[212],"with":[213],"state-of-the-art":[215],"language-conditioned":[216],"grasp":[217],"Importantly,":[219],"deploy":[221],"physical":[226],"robot":[227,249],"validate":[229],"usability":[231],"framework":[234],"applications.":[237],"Please":[238],"refer":[239],"supplementary":[242],"demo":[245],"videos":[246],"experiments.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}