{"id":"https://openalex.org/W4405785541","doi":"https://doi.org/10.1109/iros58592.2024.10802366","title":"VIHE: Virtual In-Hand Eye Transformer for 3D Robotic Manipulation","display_name":"VIHE: Virtual In-Hand Eye Transformer for 3D Robotic Manipulation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785541","doi":"https://doi.org/10.1109/iros58592.2024.10802366"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802366","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/A5029113819","display_name":"Weiyao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyao Wang","raw_affiliation_strings":["Johns Hopkins University,Department of Computer Science,Baltimore,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Computer Science,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404175","display_name":"Yutian Lei","orcid":"https://orcid.org/0009-0006-5793-2513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutian Lei","raw_affiliation_strings":["Baidu Research, Robotics and Autonomous Driving Lab (RAL),Sunnyvale,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Robotics and Autonomous Driving Lab (RAL),Sunnyvale,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050808028","display_name":"Shiyu Jin","orcid":"https://orcid.org/0000-0002-6475-5942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Jin","raw_affiliation_strings":["Baidu Research, Robotics and Autonomous Driving Lab (RAL),Sunnyvale,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Robotics and Autonomous Driving Lab (RAL),Sunnyvale,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041383246","display_name":"Gregory D. Hager","orcid":"https://orcid.org/0000-0002-6662-9763"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory D. Hager","raw_affiliation_strings":["Johns Hopkins University,Department of Computer Science,Baltimore,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Computer Science,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843626","display_name":"Liangjun Zhang","orcid":"https://orcid.org/0000-0001-5737-2540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangjun Zhang","raw_affiliation_strings":["Baidu Research, Robotics and Autonomous Driving Lab (RAL),Sunnyvale,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Robotics and Autonomous Driving Lab (RAL),Sunnyvale,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"403","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9607999920845032,"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"}},"topics":[{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9607999920845032,"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/computer-science","display_name":"Computer science","score":0.6662020683288574},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5625327825546265},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4684208631515503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4609544575214386},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3952331244945526},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33011552691459656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19743934273719788},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1396554410457611},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05706644058227539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662020683288574},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5625327825546265},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4684208631515503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609544575214386},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3952331244945526},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33011552691459656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19743934273719788},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1396554410457611},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05706644058227539}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802366","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1564897360","https://openalex.org/W1971086298","https://openalex.org/W1975550062","https://openalex.org/W1986014385","https://openalex.org/W2082511574","https://openalex.org/W2164474021","https://openalex.org/W2194775991","https://openalex.org/W2919115771","https://openalex.org/W2962894046","https://openalex.org/W2962949934","https://openalex.org/W2966271811","https://openalex.org/W3007769740","https://openalex.org/W3037767967","https://openalex.org/W3045988483","https://openalex.org/W3119523940","https://openalex.org/W3174849255","https://openalex.org/W3183526037","https://openalex.org/W3214952050","https://openalex.org/W4200150166","https://openalex.org/W4205172069","https://openalex.org/W4206944021","https://openalex.org/W4306955484","https://openalex.org/W4307234290","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4402354127","https://openalex.org/W6685322675","https://openalex.org/W6762287338","https://openalex.org/W6764969207","https://openalex.org/W6782380515","https://openalex.org/W6784953566","https://openalex.org/W6791353385","https://openalex.org/W6793987055","https://openalex.org/W6799838802","https://openalex.org/W6801810553","https://openalex.org/W6802366246","https://openalex.org/W6809509765","https://openalex.org/W6810123038","https://openalex.org/W6810640255","https://openalex.org/W6838557027","https://openalex.org/W6843759960","https://openalex.org/W6850503672","https://openalex.org/W6852297048","https://openalex.org/W6854108904","https://openalex.org/W6854738657","https://openalex.org/W6855562989","https://openalex.org/W6861392586","https://openalex.org/W6871625546"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,104],"this":[1],"work,":[2],"we":[3],"introduce":[4],"the":[5,41,56,60,95],"Virtual":[6],"In-Hand":[7],"Eye":[8],"Transformer":[9],"(VIHE),":[10],"a":[11,49,81,85,114],"novel":[12],"method":[13],"designed":[14],"to":[15,92],"enhance":[16],"3D":[17],"manipulation":[18,73,110],"capabilities":[19],"through":[20],"action-aware":[21],"view":[22],"rendering.":[23],"VIHE":[24,79,107],"autoregressively":[25],"refines":[26],"actions":[27],"in":[28,40,75],"multiple":[29],"stages":[30],"by":[31],"conditioning":[32],"on":[33],"rendered":[34],"views":[35,47],"posed":[36],"from":[37,90],"action":[38],"predictions":[39],"earlier":[42],"stages.":[43],"These":[44],"virtual":[45],"in-hand":[46],"provide":[48],"strong":[50],"inductive":[51],"bias":[52],"for":[53,59,63],"effectively":[54],"recognizing":[55],"correct":[57],"pose":[58],"hand,":[61],"especially":[62],"challenging":[64],"high-precision":[65],"tasks":[66,74,111],"such":[67],"as":[68],"peg":[69],"insertion.":[70],"On":[71],"18":[72],"RLBench":[76],"simulated":[77],"environments,":[78],"achieves":[80],"new":[82],"state-of-the-art,":[83],"with":[84,112],"12%":[86],"absolute":[87],"improvement,":[88],"increasing":[89],"65%":[91],"77%":[93],"over":[94],"existing":[96],"state-of-the-art":[97],"model":[98],"using":[99],"100":[100],"demonstrations":[101],"per":[102],"task.":[103],"real-world":[105],"scenarios,":[106],"can":[108,126],"learn":[109],"just":[113],"handful":[115],"of":[116],"demonstrations,":[117],"highlighting":[118],"its":[119],"practical":[120],"utility.":[121],"Videos":[122],"and":[123],"code":[124],"implementation":[125],"be":[127],"found":[128],"at":[129],"our":[130],"project":[131],"site:":[132],"https://vihe-3d.github.io.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}