{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T05:47:33Z","timestamp":1779169653177,"version":"3.51.4"},"reference-count":54,"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":"NSFC","doi-asserted-by":"publisher","award":["62402427,U24B20154"],"award-info":[{"award-number":["62402427,U24B20154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","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\/iccv51701.2025.00655","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6970-6980","source":"Crossref","is-referenced-by-count":1,"title":["EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds"],"prefix":"10.1109","author":[{"given":"Lu","family":"Chen","sequence":"first","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shixiang","family":"Tang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianhong","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231688"},{"key":"ref6","article-title":"MC-JEPA: A joint-embedding predictive architecture for self-supervised learning of motion and content features","author":"Bardes","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Revisiting feature prediction for learning visual representations from video","author":"Bardes","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.59.103006.093639"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"ref12","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00655"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","article-title":"Learning and leveraging world models in visual representation learning","author":"Garrido","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00479"},{"key":"ref22","article-title":"Recurrent world models facilitate policy evolution","volume":"31","author":"Ha","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"World models","volume-title":"Thirtysecond Annual Conference on Neural Information Processing Systems","author":"Ha","year":"2018"},{"key":"ref24","first-page":"17572","article-title":"Data-efficient large vision models through sequential autoregression","volume-title":"International Conference on Machine Learning","author":"Hao","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","article-title":"GAIA-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"ref30","first-page":"1","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022\u201306-27","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Review"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16321"},{"key":"ref32","article-title":"VIP: Towards universal visual reward and representation via valueimplicit pre-training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ma","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00632"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00798"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"ref38","first-page":"892","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning","author":"Nair","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/713752551"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.4324\/9780203850664"},{"key":"ref41","volume-title":"InternLM: A multilingual language model with progressively enhanced capabilities","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2524.001.0001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X01003910"},{"key":"ref44","article-title":"Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video","volume-title":"The Twelfth International Conference on Learning Representations","author":"Venkataramanan","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089380"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00897"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref48","first-page":"1871","article-title":"TriFinger: An open-source robot for learning dexterity","volume-title":"Proceedings of Machine Learning Research","volume":"155","author":"W\u00fcthrich","year":"2020"},{"key":"ref49","article-title":"Pandora: Towards general world model with natural language actions and video states","author":"Xiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00170"},{"key":"ref51","article-title":"UniSim: Learning interactive real-world simulators","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00605"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_39"}],"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\/11444620.pdf?arnumber=11444620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:24Z","timestamp":1777612104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444620\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00655","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}