{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T22:19:22Z","timestamp":1774736362135,"version":"3.50.1"},"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\/icra57147.2024.10610763","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"16850-16857","source":"Crossref","is-referenced-by-count":16,"title":["Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Jianfeng","family":"Gao","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology,Institute for Anthropomatics and Robotics,Karlsruhe,Germany"}]},{"given":"Xiaoshu","family":"Jin","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Institute for Anthropomatics and Robotics,Karlsruhe,Germany"}]},{"given":"Franziska","family":"Krebs","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Institute for Anthropomatics and Robotics,Karlsruhe,Germany"}]},{"given":"No\u00e9mie","family":"Jaquier","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Institute for Anthropomatics and Robotics,Karlsruhe,Germany"}]},{"given":"Tamim","family":"Asfour","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Institute for Anthropomatics and Robotics,Karlsruhe,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3286074"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5353894"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152439"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/00222895.1987.10735426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/dev.20428"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759806"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3153728"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.12.011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref11","author":"Patel","year":"2022","journal-title":"Learning to Imitate Object Interactions from Internet Videos"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197121"},{"key":"ref13","first-page":"373","article-title":"Dense Object Nets: Learning dense visual object descriptors by and for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Florence"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5220\/0008989304440451"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref16","first-page":"550","article-title":"One-Shot Transfer of Affordance Regions? AffCorrs!","volume-title":"Conference on Robot Learning (CoRL)","author":"Hadjivelichkov"},{"key":"ref17","article-title":"Deep ViT Features as Dense Visual Descriptors","author":"Amir","year":"2022","journal-title":"ECCVW What is Motion For?"},{"key":"ref18","first-page":"6990","article-title":"GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs","author":"Liu","year":"2019","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"ref21","first-page":"835","article-title":"SE(3)-Equivariant Relational Re-arrangement with Neural Descriptor Fields","volume-title":"Conference on Robot Learning (CoRL)","author":"Simeonov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160423"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160666"},{"key":"ref25","author":"Sundaresan","year":"2023","journal-title":"KITE: Keypoint-Conditioned Policies for Semantic Manipulation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341758"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907047"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2298\/TSCI151005037S"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918765952"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624916"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140053"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140049"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898330"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-23807-0_6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3295249"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152974"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555785"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref41","author":"Fu","year":"2024","journal-title":"Mobile ALOHA: learning bimanual mobile manipulation with low-cost whole-body teleoperation"},{"key":"ref42","first-page":"5150","article-title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","volume":"35","author":"Chen","year":"2022","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref43","author":"Kataoka","year":"2022","journal-title":"Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learning"},{"key":"ref44","first-page":"2327","article-title":"Deep Imitation Learning for Bimanual Robotic Manipulation","volume":"33","author":"Xie","year":"2020","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref45","author":"Kim","year":"2022","journal-title":"Robot peels banana with goal-conditioned dual-action deep imitation learning"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636301"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2949221"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12416"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968586"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref52","first-page":"526","article-title":"Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects","volume-title":"Conference on Robot Learning (CoRL)","volume":"164","author":"Ichnowski"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref55","author":"Cheng","year":"2023","journal-title":"Segment and Track Anything"},{"key":"ref56","author":"Liu","year":"2023","journal-title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"},{"key":"ref57","author":"Lugaresi","year":"2019","journal-title":"MediaPipe: A framework for building perception pipelines"},{"key":"ref58","author":"Jiang","year":"2023","journal-title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2019.2941246"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461202"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142903"}],"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\/10610763.pdf?arnumber=10610763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:54:52Z","timestamp":1723269292000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610763","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}