{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T23:32:58Z","timestamp":1774481578635,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62273327"],"award-info":[{"award-number":["62273327"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62461160260"],"award-info":[{"award-number":["62461160260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2064"],"award-info":[{"award-number":["U22A2064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Fund of Macau SAR","award":["0092\/2024\/AFJ"],"award-info":[{"award-number":["0092\/2024\/AFJ"]}]},{"name":"Science and Technology Development Fund of Macau SAR","award":["0075\/2023\/AMJ"],"award-info":[{"award-number":["0075\/2023\/AMJ"]}]},{"name":"Science and Technology Development Fund of Macau SAR","award":["0003\/2023\/RIB1"],"award-info":[{"award-number":["0003\/2023\/RIB1"]}]},{"name":"Science and Technology Development Fund of Macau SAR","award":["001\/2024\/SKL"],"award-info":[{"award-number":["001\/2024\/SKL"]}]},{"DOI":"10.13039\/501100007162","name":"Guangdong Science and Technology Department","doi-asserted-by":"publisher","award":["2023A0505030003"],"award-info":[{"award-number":["2023A0505030003"]}],"id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007162","name":"Guangdong Science and Technology Department","doi-asserted-by":"publisher","award":["2020B1515130001"],"award-info":[{"award-number":["2020B1515130001"]}],"id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022B1515120010"],"award-info":[{"award-number":["2022B1515120010"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["KCXFZ20211020165003005"],"award-info":[{"award-number":["KCXFZ20211020165003005"]}]},{"DOI":"10.13039\/501100004733","name":"Universidade de Macau","doi-asserted-by":"publisher","award":["MYRG-GRG2023-00237-FST-UMDF"],"award-info":[{"award-number":["MYRG-GRG2023-00237-FST-UMDF"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004733","name":"Universidade de Macau","doi-asserted-by":"publisher","award":["MYRG-GRG2024-00299-FST"],"award-info":[{"award-number":["MYRG-GRG2024-00299-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tro.2025.3539193","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T14:22:54Z","timestamp":1738765374000},"page":"1553-1567","source":"Crossref","is-referenced-by-count":9,"title":["Fusion-Perception-to-Action Transformer: Enhancing Robotic Manipulation With 3-D Visual Fusion Attention and Proprioception"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8170-2463","authenticated-orcid":false,"given":"Yangjun","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City, Centre for Artificial Intelligence and Robotics, Department of Electromechanical Engineering, University of Macau, Macau, China"}]},{"given":"Sheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6780-8475","authenticated-orcid":false,"given":"Binghan","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9151-7758","authenticated-orcid":false,"given":"Zhi-Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City, Centre for Artificial Intelligence and Robotics, Department of Electromechanical Engineering, University of Macau, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5086-4152","authenticated-orcid":false,"given":"Sheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3217048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3184258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3121408"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3351548"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref13","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3248324"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919872545"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2785415"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3213730"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3299051"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3252578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3422054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3006716"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf7843"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144512"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref32","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2635479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197181"},{"key":"ref35","first-page":"694","article-title":"RVT: Robotic view transformer for 3D object manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Goyal","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3353075"},{"key":"ref37","first-page":"1761","article-title":"PolarNet: 3D point clouds for language-guided robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Chen","year":"2023"},{"issue":"PMLR","key":"ref38","first-page":"284","article-title":"GNFactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Proc. Conf. Robot Learn.","author":"Ze","year":"2023"},{"key":"ref39","first-page":"3949","article-title":"Act3D: 3D feature field transformers for multi-task robotic manipulation","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Gervet","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref42","first-page":"2022","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jaegle"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2942160"},{"key":"ref46","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You","year":"2020"},{"key":"ref47","first-page":"23192","article-title":"PointNext: Revisiting pointnet with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qian","year":"2022"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/10778592\/10874177.pdf?arnumber=10874177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T23:26:46Z","timestamp":1768951606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10874177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tro.2025.3539193","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}