{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:56:22Z","timestamp":1762325782966,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342201","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"11390-11395","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods"],"prefix":"10.1109","author":[{"given":"Ya","family":"Jing","sequence":"first","affiliation":[{"name":"ByteDance Research"}]},{"given":"Xuelin","family":"Zhu","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]},{"given":"Xingbin","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]},{"given":"Qie","family":"Sima","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]},{"given":"Taozheng","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]},{"given":"Yunhai","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]},{"given":"Tao","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_7"},{"key":"ref4","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov","key":"ref5"},{"article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"6th Annual Conference on Robot Learning","author":"Nair","key":"ref6"},{"article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2017.8202237"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897133"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.020"},{"key":"ref14","article-title":"Maskvit: Masked visual pre-training for video prediction","author":"Gupta","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref19","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning","author":"Yu","key":"ref20"},{"article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforce-ment learning","volume-title":"Conference on Robot Learning","author":"Gupta","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref24","article-title":"Vlmbench: A compositional benchmark for vision-and-language manipulation","author":"Zheng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"article-title":"Relay policy learning: Solving long-horizon tasks via imitation and rein-forcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Gupta","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"article-title":"A simple frame-work for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen","key":"ref30"},{"key":"ref31","article-title":"Behavioral cloning from obser-vation","author":"Torabi","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","key":"ref35"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342201.pdf?arnumber=10342201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:19:23Z","timestamp":1703031563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342201","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}