{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:29:34Z","timestamp":1774538974426,"version":"3.50.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246950","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"3201-3208","source":"Crossref","is-referenced-by-count":3,"title":["VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation"],"prefix":"10.1109","author":[{"given":"Zhengnan","family":"Sun","sequence":"first","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaotai","family":"Shi","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayin","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingtao","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cui","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"04","article-title":"Shadow hand","volume-title":"Journal of Advance Research in Applied Science (ISSN: 2208-2352)","volume":"1","author":"Sharma","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.089"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref5","article-title":"Learning generalizable dexterous manipulation from human grasp affordance","author":"Wu","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610933"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref10","first-page":"5842","article-title":"The","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Goyal"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref13","first-page":"23 301","article-title":"Liv: Language-image representations and rewards for robotic control","volume-title":"International Conference on Machine Learning","author":"Ma"},{"key":"ref14","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref16","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022"},{"key":"ref17","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref19","first-page":"2026","article-title":"Visuotactile transformers for manipulation","volume-title":"Conference on Robot Learning","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611305"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981802"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197124"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196104"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref28","article-title":"Solving rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342334"},{"key":"ref30","first-page":"594","article-title":"Dexpoint: Generalizable point cloud reinforcement learning for sim-to-real dexterous manipulation","volume-title":"Conference on Robot Learning","author":"Qin"},{"key":"ref31","first-page":"1722","article-title":"In-hand object rotation via rapid motor adaptation","volume-title":"Conference on Robot Learning","author":"Qi"},{"key":"ref32","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning","author":"Matas"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref34","article-title":"Visual dexterity: In-hand dexterous manipulation from depth","volume-title":"Icml workshop on new frontiers in learning, control, and dynamical systems","author":"Chen"},{"key":"ref35","article-title":"Sequential dexterity: Chaining dexterous policies for long-horizon manipulation","author":"Chen","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.036"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160756"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160739"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295991"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref42","first-page":"1887","article-title":"Dynamic handover: Throw and catch with bimanual hands","volume-title":"Conference on Robot Learning","author":"Huang"},{"key":"ref43","article-title":"Robopianist: Dexterous piano playing with deep reinforcement learning","volume-title":"Conference on Robot Learning. Conference on Robot Learning","author":"Zakka"},{"key":"ref44","article-title":"Twisting lids off with two hands","volume-title":"8th Annual Conference on Robot Learning","author":"Lin"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196976"},{"key":"ref46","first-page":"1596","article-title":"Visuotactile affordances for cloth manipulation with local control","volume-title":"Conference on Robot Learning","author":"Sunil"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610532"},{"key":"ref48","first-page":"2549","article-title":"General in-hand object rotation with vision and touch","volume-title":"Conference on Robot Learning","author":"Qi"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611407"},{"key":"ref50","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref51","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246950.pdf?arnumber=11246950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:14:11Z","timestamp":1765520051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246950","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}