{"id":"https://openalex.org/W4405785307","doi":"https://doi.org/10.1109/iros58592.2024.10802654","title":"OVGNet: A Unified Visual-Linguistic Framework for Open-Vocabulary Robotic Grasping","display_name":"OVGNet: A Unified Visual-Linguistic Framework for Open-Vocabulary Robotic Grasping","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785307","doi":"https://doi.org/10.1109/iros58592.2024.10802654"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5008131938","display_name":"Meng Li","orcid":"https://orcid.org/0000-0002-7095-0170"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["Beihang University,Department of Electronic and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Department of Electronic and Information Engineering","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722127","display_name":"Qi Zhao","orcid":"https://orcid.org/0000-0002-3508-027X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhao","raw_affiliation_strings":["Beihang University,Department of Electronic and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Department of Electronic and Information Engineering","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029244560","display_name":"Shuchang Lyu","orcid":"https://orcid.org/0000-0001-9769-7083"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuchang Lyu","raw_affiliation_strings":["Beihang University,Department of Electronic and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Department of Electronic and Information Engineering","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710371","display_name":"Chunlei Wang","orcid":"https://orcid.org/0000-0002-8955-9964"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Wang","raw_affiliation_strings":["Beihang University,Department of Electronic and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Department of Electronic and Information Engineering","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443244","display_name":"Yuguang Ma","orcid":"https://orcid.org/0000-0003-0373-5873"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Ma","raw_affiliation_strings":["SenseTime,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime,Beijing,China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115599767","display_name":"Guangliang Cheng","orcid":"https://orcid.org/0000-0001-8686-9513"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangliang Cheng","raw_affiliation_strings":["University of Liverpool,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101501801","display_name":"Chenguang Yang","orcid":"https://orcid.org/0000-0002-3145-385X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenguang Yang","raw_affiliation_strings":["University of Liverpool,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7507","last_page":"7513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.988099992275238,"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":0.988099992275238,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9750000238418579,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9465000033378601,"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/computer-science","display_name":"Computer science","score":0.7328010201454163},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6732017397880554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5662127137184143},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5370496511459351},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4832642674446106},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3584445118904114},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0651528537273407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328010201454163},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6732017397880554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662127137184143},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5370496511459351},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4832642674446106},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3584445118904114},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0651528537273407}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"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":40,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W2948672349","https://openalex.org/W2952122856","https://openalex.org/W2983943451","https://openalex.org/W3026627579","https://openalex.org/W3035198432","https://openalex.org/W3105916048","https://openalex.org/W3107113572","https://openalex.org/W3131251978","https://openalex.org/W3159481202","https://openalex.org/W4205569741","https://openalex.org/W4221167790","https://openalex.org/W4226225308","https://openalex.org/W4283359318","https://openalex.org/W4312747482","https://openalex.org/W4312920279","https://openalex.org/W4383097652","https://openalex.org/W4383108836","https://openalex.org/W4383108845","https://openalex.org/W4383109008","https://openalex.org/W4383109253","https://openalex.org/W4383109368","https://openalex.org/W4386075561","https://openalex.org/W4386075819","https://openalex.org/W4386113267","https://openalex.org/W4387092545","https://openalex.org/W4389666604","https://openalex.org/W4389667112","https://openalex.org/W4389667691","https://openalex.org/W4390871915","https://openalex.org/W4390873107","https://openalex.org/W4390873343","https://openalex.org/W4395080758","https://openalex.org/W4404612908","https://openalex.org/W6755207826","https://openalex.org/W6791353385","https://openalex.org/W6797397777","https://openalex.org/W6839701648","https://openalex.org/W6843243982","https://openalex.org/W6846385215"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recognizing":[0],"and":[1,96,120,134,138,148],"grasping":[2,75,93,113],"novel-category":[3],"objects":[4],"remains":[5],"a":[6,33,63,80,87],"crucial":[7],"yet":[8],"challenging":[9],"problem":[10],"in":[11,23,91,110,141],"real-world":[12],"robotic":[13,44,112],"applications.":[14],"Despite":[15],"its":[16],"significance,":[17],"limited":[18],"research":[19],"has":[20],"been":[21],"conducted":[22],"this":[24],"specific":[25],"domain.":[26],"To":[27],"address":[28],"this,":[29],"we":[30,61,78,100],"seamlessly":[31],"propose":[32,79],"novel":[34,54,97,139],"framework":[35,83,127],"that":[36,84],"integrates":[37],"open-vocabulary":[38,74],"learning":[39],"into":[40],"the":[41,49,71,111,118],"domain":[42],"of":[43,73,122,132],"grasping,":[45],"empowering":[46],"robots":[47,90],"with":[48],"capability":[50],"to":[51,106],"adeptly":[52],"handle":[53],"objects.":[55,98],"Our":[56,146],"contributions":[57],"are":[58,150],"threefold.":[59],"Firstly,":[60],"present":[62],"large-scale":[64],"benchmark":[65],"dataset":[66,149],"specifically":[67],"tailored":[68],"for":[69,89],"evaluating":[70],"performance":[72],"tasks.":[76],"Secondly,":[77],"unified":[81],"visual-linguistic":[82,108],"serves":[85],"as":[86],"guide":[88],"successfully":[92],"both":[94],"base":[95,137],"Thirdly,":[99],"introduce":[101],"two":[102],"alignment":[103],"modules":[104],"designed":[105],"enhance":[107],"perception":[109],"process.":[114],"Extensive":[115],"experiments":[116],"validate":[117],"efficacy":[119],"utility":[121],"our":[123,126,142],"approach.":[124],"Notably,":[125],"achieves":[128],"an":[129],"average":[130],"accuracy":[131],"71.2%":[133],"64.4%":[135],"on":[136],"categories":[140],"new":[143],"dataset,":[144],"respectively.":[145],"code":[147],"available":[151],"at":[152],"https://github.com/cv516Buaa/OVGNet.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}