{"id":"https://openalex.org/W4416748641","doi":"https://doi.org/10.1109/iros60139.2025.11247415","title":"Refer and Grasp: Vision-Language Guided Continuous Dexterous Grasping","display_name":"Refer and Grasp: Vision-Language Guided Continuous Dexterous Grasping","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748641","doi":"https://doi.org/10.1109/iros60139.2025.11247415"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247415","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":"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/A5115603585","display_name":"Yayu Huang","orcid":"https://orcid.org/0000-0002-3599-651X"},"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":"Yayu Huang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongxuan Fan","orcid":null},"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":"Dongxuan Fan","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642547","display_name":"Qi Wen","orcid":"https://orcid.org/0009-0009-5624-1050"},"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":"Wen Qi","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042097384","display_name":"Daheng Li","orcid":"https://orcid.org/0000-0002-6289-5423"},"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":"Daheng Li","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910951","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-1455-2001"},"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":"Yifan Yang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088762168","display_name":"Yongkang Luo","orcid":"https://orcid.org/0000-0003-0651-8794"},"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":"Yongkang Luo","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100889160","display_name":"Jia Sun","orcid":"https://orcid.org/0000-0002-8010-316X"},"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":"Jia Sun","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000419148","display_name":"Q.B. Liu","orcid":"https://orcid.org/0009-0002-8562-7189"},"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":"Qian Liu","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396004","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-2801-4012"},"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":"Peng Wang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"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":0.40094812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7576","last_page":"7583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5928999781608582,"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":0.5928999781608582,"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":0.3499999940395355,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.012000000104308128,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.7998999953269958},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5837000012397766},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.39010000228881836},{"id":"https://openalex.org/keywords/robotic-hand","display_name":"Robotic hand","score":0.38280001282691956},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3303999900817871},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32850000262260437}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7998999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607999801635742},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2988191880","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic hand","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3815999925136566},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247415","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2077069816","https://openalex.org/W2302548814","https://openalex.org/W2489434015","https://openalex.org/W2561715562","https://openalex.org/W2907143950","https://openalex.org/W2911549659","https://openalex.org/W2963109634","https://openalex.org/W2964199361","https://openalex.org/W2964345792","https://openalex.org/W2967153639","https://openalex.org/W2996325525","https://openalex.org/W3008273191","https://openalex.org/W3034952258","https://openalex.org/W3039599385","https://openalex.org/W3099587965","https://openalex.org/W3109929115","https://openalex.org/W3138516171","https://openalex.org/W3170390053","https://openalex.org/W3180172155","https://openalex.org/W3186077919","https://openalex.org/W3215810277","https://openalex.org/W4200631575","https://openalex.org/W4206247072","https://openalex.org/W4312443924","https://openalex.org/W4312876407","https://openalex.org/W4321377343","https://openalex.org/W4383108746","https://openalex.org/W4383108955","https://openalex.org/W4386001306","https://openalex.org/W4386075493","https://openalex.org/W4387350597","https://openalex.org/W4387734269","https://openalex.org/W4389667112","https://openalex.org/W4390874575","https://openalex.org/W4400111043","https://openalex.org/W4402754134","https://openalex.org/W4405785307","https://openalex.org/W4406158138"],"related_works":[],"abstract_inverted_index":{"Robotic":[0],"grasping":[1,97,106,136],"guided":[2],"by":[3],"natural":[4],"language":[5],"instructions":[6],"faces":[7],"challenges":[8],"due":[9],"to":[10,18,33],"ambiguities":[11],"in":[12,65],"object":[13,39],"descriptions":[14],"and":[15,91,133],"the":[16,84],"need":[17],"interpret":[19],"complex":[20],"spatial":[21],"context.":[22],"Existing":[23],"visual":[24,63],"grounding":[25,64],"methods":[26],"often":[27],"rely":[28],"on":[29],"datasets":[30],"that":[31],"fail":[32],"capture":[34],"these":[35,47],"complexities,":[36],"particularly":[37],"when":[38],"categories":[40],"are":[41],"vague":[42],"or":[43],"undefined.":[44],"To":[45],"address":[46],"challenges,":[48],"we":[49,55,82,100],"make":[50],"three":[51],"key":[52],"contributions.":[53],"First,":[54],"present":[56],"an":[57,134],"automated":[58],"dataset":[59,132],"generation":[60],"engine":[61],"for":[62,95,124,138],"tabletop":[66],"grasping,":[67],"combining":[68],"procedural":[69],"scene":[70],"synthesis":[71],"with":[72,108],"template-based":[73],"referring":[74],"expression":[75],"generation,":[76,111],"requiring":[77],"no":[78],"manual":[79],"labeling.":[80],"Second,":[81],"introduce":[83],"RefGrasp":[85],"dataset,":[86],"featuring":[87],"diverse":[88],"indoor":[89],"environments":[90],"linguistically":[92],"challenging":[93,131],"expressions":[94],"robotic":[96,116,126],"tasks.":[98],"Third,":[99],"propose":[101],"a":[102,121,130],"visually":[103],"grounded":[104],"dexterous":[105],"framework":[107,137],"continuous":[109],"grasp":[110],"validated":[112],"through":[113],"extensive":[114],"real-world":[115,139],"experiments.":[117],"Our":[118],"work":[119],"offers":[120],"novel":[122],"approach":[123],"language-guided":[125],"manipulation,":[127],"providing":[128],"both":[129],"effective":[135],"applications.":[140],"Project":[141],"website:":[142],"https://refer-and-grasp.github.io.":[143]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
