{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:50Z","timestamp":1777865390176,"version":"3.51.4"},"reference-count":64,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476011"],"award-info":[{"award-number":["62476011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00791","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8451-8461","source":"Crossref","is-referenced-by-count":0,"title":["4D Visual Pre-Training for Robot Learning"],"prefix":"10.1109","author":[{"given":"Chengkai","family":"Hou","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjie","family":"Ze","sequence":"additional","affiliation":[{"name":"Shanghai Qizhi Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yankai","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Gao","sequence":"additional","affiliation":[{"name":"CASIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songbo","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhe","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Diffusion-based representation learning","author":"Abstreiter","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref2","volume-title":"Cobot magic: An open-source robotic system","author":"Robotics","year":"2025"},{"key":"ref3","volume-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref5","first-page":"1183","article-title":"An unbiased look at datasets for visuo-motor pre-training","volume-title":"Conference on Robot Learning","author":"Dasari","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_178781"},{"key":"ref8","article-title":"Mobile aloha: Learning bimanual mobile manipulation using low-cost whole-body teleoperation","volume-title":"8th Annual Conference on Robot Learning (CoRL)","author":"Fu","year":"2024"},{"key":"ref9","article-title":"Act3d: Infinite resolution action detection transformer for robotic manipulation","author":"Gervet","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref10","first-page":"694","article-title":"Rvt: Robotic view transformer for 3d object manipulation","volume-title":"Conference on Robot Learning","author":"Goyal","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02181"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.56.5018"},{"key":"ref17","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Pointvoxel cnn for efficient 3d deep learning","volume":"32","author":"Liu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","volume":"36","author":"Majumdar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","volume-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021"},{"key":"ref21","first-page":"1444","article-title":"Self-supervised point cloud prediction using 3d spatio-temporal convolutional networks","volume-title":"Conference on Robot Learning","author":"Mersch","year":"2022"},{"key":"ref22","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref23","volume-title":"Extracting reward functions from diffusion models","author":"Nuti","year":"2023"},{"key":"ref24","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref27","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.015"},{"key":"ref30","first-page":"683","article-title":"Robot learning with sensorimotor pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","year":"2023"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","volume-title":"On bringing robots home","author":"Muhammad","year":"2023"},{"key":"ref36","article-title":"Rrl: Resnet as representation for reinforcement learning","author":"Shah","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref37","first-page":"785","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar","year":"2023"},{"key":"ref38","volume-title":"Shelving, stacking, hanging: Relational pose diffusion for multi-modal rearrangement","author":"Simeonov","year":"2023"},{"key":"ref39","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref41","volume-title":"Memory-consistent neural networks for imitation learning","author":"Sridhar","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801678"},{"key":"ref45","article-title":"Equivariant diffusion policy","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.152"},{"key":"ref48","volume-title":"Tiangong","year":"2025"},{"key":"ref49","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247358"},{"key":"ref51","article-title":"Equibot: Sim (3)equivariant diffusion policy for generalizable and data efficient learning","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref53","first-page":"1094","article-title":"Metaworld: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3259681"},{"key":"ref55","first-page":"284","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on Robot Learning","author":"Ze","year":"2023"},{"key":"ref56","article-title":"Generalizable humanoid manipulation with improved 3d diffusion policies","author":"Ze","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1962"},{"key":"ref59","article-title":"Vlabench: A large-scale benchmark for language-conditioned robotics manipulation with longhorizon reasoning tasks","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01694"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02164"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444572.pdf?arnumber=11444572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:23Z","timestamp":1777530203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00791","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}