{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T21:12:46Z","timestamp":1772226766950,"version":"3.50.1"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802583","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T14:17:39Z","timestamp":1735136259000},"page":"7391-7398","source":"Crossref","is-referenced-by-count":1,"title":["How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing"],"prefix":"10.1109","author":[{"given":"Shutong","family":"Jin","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"}]},{"given":"Ruiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"}]},{"given":"Muhammad","family":"Zahid","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"}]},{"given":"Florian T.","family":"Pokorny","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref7","first-page":"15 084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","first-page":"27 921","article-title":"Multi-game decision transformers","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"27 042","article-title":"Online decision transformer","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Zheng"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref11","first-page":"785","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Shridhar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref13","first-page":"12 493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Patrick","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref15","first-page":"2071","article-title":"Transformers for one-shot visual imitation","volume-title":"Proceedings of the 2020 Conference on Robot Learning","volume":"155","author":"Dasari"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161288"},{"key":"ref17","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5220\/0010241801010112"},{"key":"ref19","article-title":"Maskvit: Masked visual pre-training for video prediction","volume-title":"ICLR","author":"Gupta"},{"key":"ref20","article-title":"Transframer: Arbitrary frame prediction with generative models","author":"Nash","year":"2023","journal-title":"Trans. on Machine Learning Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150855"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00295"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611548"},{"key":"ref27","first-page":"785","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref28","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref30","article-title":"Scale efficiently: Insights from pre-training and fine-tuning transformers","author":"Tay","year":"2021"},{"issue":"1","key":"ref31","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume-title":"JMLR","volume":"23","author":"Fedus"},{"key":"ref32","article-title":"Scaling laws vs model architectures: How does inductive bias influence scaling?","author":"Tay","year":"2022"},{"key":"ref33","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342201"},{"key":"ref35","article-title":"Kitchenshift: Evaluating zero-shot generalization of imitation-based policy learning under domain shifts","volume-title":"NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications","author":"Xing"},{"key":"ref36","article-title":"Decomposing the generalization gap in imitation learning for visual robotic manipulation","author":"Xie","year":"2023"},{"key":"ref37","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"ICML","author":"Cobbe"},{"key":"ref38","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref40","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref42","first-page":"5842","article-title":"The","volume-title":"something something\" video database for learning and evaluating visual common sense,\" in Proceedings of the IEEE international conference on computer vision","author":"Goyal"},{"key":"ref43","first-page":"16 711","article-title":"Avid dataset: Anonymized videos from diverse countries","volume":"33","author":"Piergiovanni","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref45","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref47","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref48","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"5th Annual Conference on Robot Learning","author":"Mandlekar"},{"key":"ref49","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref50","first-page":"1367","article-title":"Error-aware imitation learning from teleoperation data for mobile manipulation","volume-title":"Conference on Robot Learning","author":"Wong"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref52","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3064065"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref56","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref57","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02186"},{"key":"ref59","first-page":"16 743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref61","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref63","volume-title":"Berzelius"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802583.pdf?arnumber=10802583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:45:59Z","timestamp":1772225159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802583","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}