{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:21:14Z","timestamp":1783700474546,"version":"3.55.0"},"reference-count":82,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010190","name":"GENCI","doi-asserted-by":"publisher","award":["AD011013147"],"award-info":[{"award-number":["AD011013147"]}],"id":[{"id":"10.13039\/501100010190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-23-IACL-0008"],"award-info":[{"award-number":["ANR-23-IACL-0008"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127358","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"3336-3343","source":"Crossref","is-referenced-by-count":9,"title":["ViViDex: Learning Vision-Based Dexterous Manipulation from Human Videos"],"prefix":"10.1109","author":[{"given":"Zerui","family":"Chen","sequence":"first","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Etienne","family":"Arlaud","sequence":"additional","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref2","article-title":"Instruction-driven history-aware policies for robotic manipulations","volume-title":"CoRL","author":"Guhur","year":"2023"},{"key":"ref3","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"ICML","author":"Driess","year":"2023"},{"key":"ref4","article-title":"PolarNet: 3D point clouds for language-guided robotic manipulation","volume-title":"CoRL","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-104848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref9","article-title":"In-hand object rotation via rapid motor adaptation","volume-title":"CoRL","author":"Qi","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.036"},{"key":"ref11","article-title":"General in-hand object rotation with vision and touch","volume-title":"CoRL","author":"Qi","year":"2023"},{"key":"ref12","author":"Akkaya","year":"2019","journal-title":"Solving rubik\u2019s cube with a robot hand"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981221"},{"key":"ref14","article-title":"RoboPianist: Dexterous piano playing with deep reinforcement learning","volume-title":"CoRL","author":"Zakka","year":"2023"},{"key":"ref15","author":"Merel","year":"2017","journal-title":"Learning human behaviors from motion capture by adversarial imitation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160547"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref21","article-title":"ACE: A cross-platfrom visual-exoskeletons for low-cost dexterous teleoperation","volume-title":"CoRL","author":"Yang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref25","article-title":"DexVIP: Learning dexterous grasping with human hand pose priors from video","volume-title":"CoRL","author":"Mandikal","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342334"},{"key":"ref27","article-title":"VideoDex: Learning dexterity from internet videos","volume-title":"CoRL","author":"Shaw","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161147"},{"key":"ref29","article-title":"Learning generalizable dexterous manipulation from human grasp affordance","volume-title":"CoRL","author":"Wu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1998.677060"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066268"},{"key":"ref33","article-title":"Contact-invariant optimization for hand manipulation","volume-title":"SIGGRAPH","author":"Mordatch","year":"2012"},{"key":"ref34","author":"Wu","year":"2022","journal-title":"Learning diverse and physically feasible dexterous grasps with generative model and bilevel optimization"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3548503"},{"key":"ref36","article-title":"Diff-LfD: Contact-aware model-based learning from visual demonstration for robotic manipulation via differentiable physicsbased simulation and rendering","volume-title":"CoRL","author":"Zhu","year":"2023"},{"key":"ref37","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"CoRL","author":"Nair","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00459"},{"key":"ref39","article-title":"A system for general in-hand object re-orientation","volume-title":"CoRL","author":"Chen","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"ref41","author":"Lin","year":"2024","journal-title":"Learning visuotactile skills with two multifingered hands"},{"key":"ref42","article-title":"On the utility of koopman operator theory in learning dexterous manipulation skills","volume-title":"CoRL","author":"Han","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01700"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610532"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc9244"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref47","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"CoRL","author":"Nagabandi","year":"2020"},{"key":"ref48","article-title":"MoDem: Accelerating visual modelbased reinforcement learning with demonstrations","volume-title":"ICLR","author":"Hansen","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_14"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.024"},{"key":"ref57","article-title":"XIRL: Cross-embodiment inverse reinforcement learning","volume-title":"CoRL","author":"Zakka","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"ref59","article-title":"Reinforcement learning with videos: Combining offline observations with interaction","volume-title":"CoRL","author":"Schmeckpeper","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.082"},{"key":"ref61","author":"Xiao","year":"2022","journal-title":"Masked visual pre-training for motor control"},{"key":"ref62","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"CoRL","author":"Radosavovic","year":"2023"},{"key":"ref63","article-title":"HInDex:visual reinforcement learning with hand-informed representations for dexterous manipulation","volume-title":"NeurIPS","author":"Ze","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161336"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161178"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561802"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197124"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_19"},{"key":"ref73","author":"Steven","year":"2019","journal-title":"The nlopt nonlinear-optimization package"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref75","article-title":"Frame Mining: a free lunch for learning robotic manipulation from 3D point clouds","volume-title":"CoRL","author":"Liu","year":"2022"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref80","article-title":"Trust region policy optimization","volume-title":"ICML","author":"Schulman","year":"2015"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636557"},{"key":"ref82","article-title":"Policy optimization with demonstrations","volume-title":"ICML","author":"Kang","year":"2018"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127358.pdf?arnumber=11127358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:04:33Z","timestamp":1756879473000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127358","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}