{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:33:44Z","timestamp":1772120024860,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610218","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"17515-17521","source":"Crossref","is-referenced-by-count":1,"title":["What Do We Learn from a Large-Scale Study of Pre-Trained Visual Representations in Sim and Real Environments?"],"prefix":"10.1109","author":[{"given":"Sneha","family":"Silwal","sequence":"first","affiliation":[{"name":"Meta AI"}]},{"given":"Karmesh","family":"Yadav","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Tingfan","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Jay","family":"Vakil","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Arjun","family":"Majumdar","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Sergio","family":"Arnaud","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Claire","family":"Chen","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Vincent-Pierre","family":"Berges","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Aravind","family":"Rajeswaran","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Mrinal","family":"Kalakrishnan","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Franziska","family":"Meier","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Oleksandr","family":"Maksymets","sequence":"additional","affiliation":[{"name":"Meta AI"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref2","article-title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","author":"Pa\u0433isi","year":"2022","journal-title":"ICML"},{"key":"ref3","article-title":"Offline visual representation learning for embodied navigation","author":"Yadav","year":"2022"},{"key":"ref4","article-title":"R3M: A Universal Visual Representation for Robot Manipulation","author":"Nair","year":"2022","journal-title":"CoRL"},{"key":"ref5","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref6","article-title":"Real-world robot learning with masked visual pre-training","author":"Radosavovic","year":"2022","journal-title":"CoRL"},{"key":"ref7","article-title":"Ovrl-v2: A simple state-of-art baseline for imagenav and objectnav","author":"Yadav","year":"2023"},{"key":"ref8","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","author":"Majumdar","year":"2023"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref11","article-title":"The unsurprising effectiveness of pre-trained vision models for control","author":"Parisi","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341260"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01117"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561157"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.058"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01002"},{"key":"ref20","article-title":"The role of pretrained representations for the ood generalization of reinforcement learning agents","author":"Dittadi","year":"2021"},{"key":"ref21","article-title":"Trifinger: An open-source robot for learning dexterity","author":"W\u00fcthrich","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref23","article-title":"Robohive: A unified framework for robot learning","author":"Kumar","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref26","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Ramakrishnan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01652"},{"key":"ref28","first-page":"2016","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610218.pdf?arnumber=10610218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:18:26Z","timestamp":1723267106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610218","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}