{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:15Z","timestamp":1766061675844,"version":"3.48.0"},"reference-count":36,"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\/iros60139.2025.11247201","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"3193-3200","source":"Crossref","is-referenced-by-count":0,"title":["Temporal-Spatial Representation Fusion for Dexterous Manipulation Learning with Unpaired Visual-Action Data"],"prefix":"10.1109","author":[{"given":"Guwen","family":"Han","sequence":"first","affiliation":[{"name":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China,310027"}]},{"given":"Zhengnan","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Qingtao","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Yu","family":"Cui","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Anjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Huajin","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Rong","family":"Xiong","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]},{"given":"Qi","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907864"},{"author":"Liu","key":"ref2","article-title":"Vtdexmanip: A dataset and benchmark for visual-tactile pretraining and dexterous manipulation with reinforcement learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342334"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610870"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25874-z"},{"key":"ref6","first-page":"689","article-title":"Multimodal deep learning","volume-title":"ICML","volume":"11","author":"Ngiam"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref7"},{"key":"ref8","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings","author":"Ross"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd9461"},{"article-title":"A universal semantic-geometric representation for robotic manipulation","year":"2023","author":"Zhang","key":"ref11"},{"key":"ref12","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610356"},{"article-title":"R3m: A universal visual representation for robot manipulation","year":"2022","author":"Nair","key":"ref14"},{"article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","year":"2022","author":"Ma","key":"ref15"},{"key":"ref16","first-page":"23301","article-title":"Liv: Language-image representations and rewards for robotic control","volume-title":"International Conference on Machine Learning","author":"Ma"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"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":"ref18"},{"article-title":"Dynamic handover: Throw and catch with bimanual hands","year":"2023","author":"Huang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160547"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref24","first-page":"651","article-title":"Dexvip: Learning dexterous grasping with human hand pose priors from video","volume-title":"Conference on Robot Learning","author":"Mandikal"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197124"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref30"},{"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","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.53555\/nnas.v1i1.692"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610933"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","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\/11247201.pdf?arnumber=11247201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:58Z","timestamp":1766061478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247201","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}