{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:39:03Z","timestamp":1757608743209,"version":"3.44.0"},"reference-count":35,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101,62233013"],"award-info":[{"award-number":["62088101,62233013"]}],"id":[{"id":"10.13039\/501100001809","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\/icra55743.2025.11127230","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"11838-11844","source":"Crossref","is-referenced-by-count":0,"title":["UpViTaL: Unpaired Visual-Tactile Self-Supervised Representation Learning for Dexterous Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Guwen","family":"Han","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingtao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cui","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anjun","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/117"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610408"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610870"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342334"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610933"},{"key":"ref6","article-title":"VTDexmanip: A dataset and benchmark for visual-tactile pretraining and dexterous manipulation with reinforcement learning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Liu","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd9461"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611407"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref10","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"3","key":"ref12","first-page":"6","article-title":"Vima: General robot manipulation with multimodal prompts","volume":"2","author":"Jiang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105694"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196976"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340881"},{"key":"ref16","first-page":"1488","article-title":"Efficient tactile simulation with differentiability for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Xu","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061308"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636259"},{"key":"ref19","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610356"},{"key":"ref21","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"23 301","article-title":"Liv: Language-image representations and rewards for robotic control","volume-title":"International Conference on Machine Learning","author":"Ma","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3296371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852779"},{"key":"ref26","first-page":"2549","article-title":"General in-hand object rotation with vision and touch","volume-title":"Conference on Robot Learning","author":"Qi","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3379803"},{"key":"ref28","article-title":"Visuo-tactile pretraining for cable plugging","author":"George","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3485748"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.53555\/nnas.v1i1.692"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11127230.pdf?arnumber=11127230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:40:18Z","timestamp":1756881618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127230","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}