{"id":"https://openalex.org/W4417299960","doi":"https://doi.org/10.48550/arxiv.2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","display_name":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","publication_year":2025,"publication_date":"2025-05-16","ids":{"openalex":"https://openalex.org/W4417299960","doi":"https://doi.org/10.48550/arxiv.2505.11709"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.11709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11709","pdf_url":"https://arxiv.org/pdf/2505.11709","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.11709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049331220","display_name":"Ryan Hoque","orcid":"https://orcid.org/0000-0002-6457-2951"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hoque, Ryan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028058","display_name":"Peide Huang","orcid":"https://orcid.org/0000-0002-1048-8690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Peide","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027301346","display_name":"David J. Yoon","orcid":"https://orcid.org/0000-0002-4838-7422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, David J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505186","display_name":"Mouli Sivapurapu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sivapurapu, Mouli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409896","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-8511-8523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049331220"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7351999878883362,"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":0.7351999878883362,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.16990000009536743,"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":0.030300000682473183,"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/tying","display_name":"Tying","score":0.5825999975204468},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5095000267028809},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4650000035762787},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4580000042915344},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3894999921321869},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3813000023365021},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.3801000118255615},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.3643999993801117},{"id":"https://openalex.org/keywords/wired-glove","display_name":"Wired glove","score":0.35740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6419000029563904},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43380001187324524},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C107953548","wikidata":"https://www.wikidata.org/wiki/Q1172433","display_name":"Wired glove","level":3,"score":0.35740000009536743},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C15759828","wikidata":"https://www.wikidata.org/wiki/Q165074","display_name":"Parallax","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2505.11709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11709","pdf_url":"https://arxiv.org/pdf/2505.11709","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2505.11709","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2505.11709","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11709","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.11709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11709","pdf_url":"https://arxiv.org/pdf/2505.11709","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning":[1,158],"for":[2,24,160,171,201],"manipulation":[3,80,133],"has":[4,84],"a":[5,34,128],"well-known":[6],"data":[7,23,37,97],"scarcity":[8],"problem.":[9],"Unlike":[10],"natural":[11],"language":[12],"and":[13,53,73,94,108,154,169,194],"2D":[14],"computer":[15,192],"vision,":[16,193],"there":[17],"is":[18,30,198],"no":[19],"Internet-scale":[20],"corpus":[21],"of":[22,77,87,102,119,122,131,190],"dexterous":[25,78],"manipulation.":[26,59],"One":[27],"appealing":[28],"option":[29],"egocentric":[31,88],"human":[32,79],"video,":[33],"passively":[35],"scalable":[36],"source.":[38],"However,":[39],"existing":[40],"large-scale":[41,182],"datasets":[42],"such":[43],"as":[44],"Ego4D":[45],"do":[46,54],"not":[47,55],"have":[48],"native":[49],"hand":[50,93,161],"pose":[51,118],"annotations":[52],"focus":[56],"on":[57,164],"object":[58],"To":[60],"this":[61,175,181],"end,":[62],"we":[63,152,184],"use":[64],"Apple":[65],"Vision":[66],"Pro":[67],"to":[68,81,114,148,186],"collect":[69],"EgoDex:":[70],"the":[71,100,117,165,188],"largest":[72],"most":[74],"diverse":[75,132],"dataset":[76,126],"date.":[82],"EgoDex":[83,197],"829":[85],"hours":[86],"video":[89],"with":[90,135],"paired":[91],"3D":[92],"finger":[95],"tracking":[96],"collected":[98],"at":[99,203],"time":[101],"recording,":[103],"where":[104],"multiple":[105],"calibrated":[106],"cameras":[107],"on-device":[109],"SLAM":[110],"can":[111],"be":[112],"used":[113],"precisely":[115],"track":[116],"every":[120],"joint":[121],"each":[123],"hand.":[124],"The":[125],"covers":[127],"wide":[129],"range":[130],"behaviors":[134],"everyday":[136],"household":[137],"objects":[138],"in":[139,174],"194":[140],"different":[141],"tabletop":[142],"tasks":[143],"ranging":[144],"from":[145],"tying":[146],"shoelaces":[147],"folding":[149],"laundry.":[150],"Furthermore,":[151],"train":[153],"systematically":[155],"evaluate":[156],"imitation":[157],"policies":[159],"trajectory":[162],"prediction":[163],"dataset,":[166,183],"introducing":[167],"metrics":[168],"benchmarks":[170],"measuring":[172],"progress":[173],"increasingly":[176],"important":[177],"area.":[178],"By":[179],"releasing":[180],"hope":[185],"push":[187],"frontier":[189],"robotics,":[191],"foundation":[195],"models.":[196],"publicly":[199],"available":[200],"download":[202],"https://github.com/apple/ml-egodex.":[204]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}