{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:37:06Z","timestamp":1791391026693,"version":"4.3.3"},"reference-count":64,"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\/icra57147.2024.10610288","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"6904-6911","source":"Crossref","is-referenced-by-count":22,"title":["Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans"],"prefix":"10.1109","author":[{"given":"Homanga","family":"Bharadhwaj","sequence":"first","affiliation":[{"name":"Carnegie Mellon University and FAIR, AI at Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikash","family":"Kumar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubham","family":"Tulsiani","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref3","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","author":"Majumdar","year":"2023"},{"key":"ref4","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00329"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref10","article-title":"Videodex: Learning dexterity from internet videos","volume-title":"6th Annual Conference on Robot Learning","author":"Shaw"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref13","article-title":"Guide to the carnegie mellon university multimodal activity (cmu-mmac) database","author":"De la Torre","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref16","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Damen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref19","article-title":"Hand pose estimation via latent 2.5 d heatmap regression","author":"Iqbal","year":"2018","journal-title":"ECCV"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00116"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"ref27","article-title":"Frankmocap: Fast monocular 3d hand and body motion capture by regression and integration","author":"Rong","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00350"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967960"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref37","article-title":"Egodistill: Egocentric head motion distillation for efficient video understanding","author":"Tan","year":"2023"},{"key":"ref38","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Conference on robot learning","author":"Finn"},{"key":"ref39","article-title":"Visual imitation made easy","volume-title":"Conference on Robot Learning (CoRL)","author":"Young"},{"key":"ref40","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref41","article-title":"The unsurprising effectiveness of pre-trained vision models for control","author":"Parisi","year":"2022"},{"key":"ref42","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022"},{"key":"ref43","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref45","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref48","article-title":"Zero-shot robot manipulation from passive human videos","author":"Bharadhwaj","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","article-title":"Masked conditional video diffusion for prediction, generation, and interpolation","author":"Voleti","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02153"},{"key":"ref53","first-page":"13 745","article-title":"Epic-kitchens visor benchmark: Video segmentations and object relations","volume":"35","author":"Darkhalil","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363441"},{"key":"ref56","article-title":"Open-world object manipulation using pre-trained vision-language models","author":"Stone","year":"2023"},{"key":"ref57","article-title":"Cacti: A framework for scalable multi-task multi-scene visual imitation learning","author":"Mandi","year":"2022"},{"key":"ref58","first-page":"32","article-title":"Watch and match: Super-charging imitation with regularized optimal transport","volume-title":"Conference on Robot Learning","author":"Haldar"},{"key":"ref59","article-title":"From play to policy: Conditional behavior generation from uncurated robot data","author":"Cui","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"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\/10610288.pdf?arnumber=10610288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:14:59Z","timestamp":1723266899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610288","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}