{"id":"https://openalex.org/W4413925209","doi":"https://doi.org/10.1109/icra55743.2025.11127358","title":"ViViDex: Learning Vision-Based Dexterous Manipulation from Human Videos","display_name":"ViViDex: Learning Vision-Based Dexterous Manipulation from Human Videos","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925209","doi":"https://doi.org/10.1109/icra55743.2025.11127358"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5077550932","display_name":"Zerui Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zerui Chen","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017554398","display_name":"Etienne Arlaud","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Etienne Arlaud","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ivan Laptev","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]}],"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3336","last_page":"3343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9736999869346619,"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":0.9736999869346619,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9542999863624573,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9415000081062317,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205768823623657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418466329574585},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5328764319419861},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41870689392089844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205768823623657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418466329574585},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5328764319419861},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41870689392089844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2439744834","display_name":"PR[AI]RIE-PSAI - Paris School of Artificial Intelligence","funder_award_id":"ANR-23-IACL-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3489392256","display_name":null,"funder_award_id":"AD011013147","funder_id":"https://openalex.org/F4320326256","funder_display_name":"Grand \u00c9quipement National De Calcul Intensif"},{"id":"https://openalex.org/G4842108258","display_name":"Predicting future video content","funder_award_id":"ANR-21-FAI1-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1577352482","https://openalex.org/W1820657498","https://openalex.org/W2021065900","https://openalex.org/W2106281046","https://openalex.org/W2107726111","https://openalex.org/W2560609797","https://openalex.org/W2768683308","https://openalex.org/W2789839425","https://openalex.org/W2894714230","https://openalex.org/W2919115771","https://openalex.org/W2951360122","https://openalex.org/W2963411833","https://openalex.org/W2968722025","https://openalex.org/W3007769740","https://openalex.org/W3035624836","https://openalex.org/W3038245394","https://openalex.org/W3038298277","https://openalex.org/W3091133300","https://openalex.org/W3122520957","https://openalex.org/W3175995235","https://openalex.org/W3180172155","https://openalex.org/W3189615635","https://openalex.org/W3202782837","https://openalex.org/W3204665606","https://openalex.org/W3205786327","https://openalex.org/W3207908209","https://openalex.org/W4206434057","https://openalex.org/W4214717370","https://openalex.org/W4221156515","https://openalex.org/W4312331262","https://openalex.org/W4312821980","https://openalex.org/W4313015918","https://openalex.org/W4313031313","https://openalex.org/W4362722144","https://openalex.org/W4383066442","https://openalex.org/W4383108491","https://openalex.org/W4383108784","https://openalex.org/W4383109144","https://openalex.org/W4385403811","https://openalex.org/W4385430564","https://openalex.org/W4385430618","https://openalex.org/W4386066654","https://openalex.org/W4386071465","https://openalex.org/W4386076519","https://openalex.org/W4388901983","https://openalex.org/W4389665571","https://openalex.org/W4390872441","https://openalex.org/W4401417123","https://openalex.org/W4402354045","https://openalex.org/W4402354112","https://openalex.org/W4402704543","https://openalex.org/W4408254224"],"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],"this":[1],"work,":[2],"we":[3,70],"aim":[4],"to":[5,15,76,93,134],"learn":[6],"a":[7,17,72,121],"unified":[8,122],"vision-based":[9,78],"policy":[10,35,79,124,148,152],"for":[11,34,97,149],"multi-fingered":[12],"robot":[13,162],"hands":[14],"manipulate":[16],"variety":[18],"of":[19,30],"objects":[20],"in":[21,45,63,156],"diverse":[22],"poses.":[23],"Though":[24],"prior":[25],"work":[26],"has":[27],"shown":[28],"benefits":[29],"using":[31,126],"human":[32,82],"videos":[33],"learning,":[36],"performance":[37],"gains":[38],"have":[39],"been":[40],"limited":[41],"by":[42],"the":[43,61,109,137,150,160],"noise":[44],"estimated":[46],"trajectories.":[47],"Moreover,":[48],"reliance":[49],"on":[50,159,169],"privileged":[51,128],"object":[52,57],"information":[53],"such":[54],"as":[55],"ground-truth":[56],"states":[58],"further":[59,135],"limits":[60],"applicability":[62],"realistic":[64],"scenarios.":[65],"To":[66],"address":[67],"these":[68],"limitations,":[69],"propose":[71,131],"new":[73],"framework":[74],"ViViDex":[75,165],"improve":[77],"learning":[80,88],"from":[81,108,116],"videos.":[83],"It":[84],"first":[85],"uses":[86],"reinforcement":[87],"with":[89],"trajectory":[90],"guided":[91],"rewards":[92],"train":[94,120],"state-based":[95,117],"policies":[96,118],"each":[98],"video,":[99],"obtaining":[100],"both":[101,155],"visually":[102],"natural":[103],"and":[104,119,142,146,158],"physically":[105],"plausible":[106],"trajectories":[107],"video.":[110],"We":[111,130],"then":[112],"rollout":[113],"successful":[114],"episodes":[115],"visual":[123,138,151],"without":[125],"any":[127],"information.":[129],"coordinate":[132],"transformation":[133],"enhance":[136],"point":[139],"cloud":[140],"representation,":[141],"compare":[143],"behavior":[144],"cloning":[145],"diffusion":[147],"training.":[153],"Experiments":[154],"simulation":[157],"real":[161],"demonstrate":[163],"that":[164],"outperforms":[166],"state-of-theart":[167],"approaches":[168],"three":[170],"dexterous":[171],"manipulation":[172],"tasks.":[173],"Project":[174],"website:":[175],"zerchen.github.io/projects/vividex.html.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}