{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:46:01Z","timestamp":1772041561979,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812279","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"675-682","source":"Crossref","is-referenced-by-count":7,"title":["Visually Grounding Language Instruction for History-Dependent Manipulation"],"prefix":"10.1109","author":[{"given":"Hyemin","family":"Ahn","sequence":"first","affiliation":[{"name":"Institute of Robotics and Mechatronics, German Aerospace Center (DLR),Wessling,Germany"}]},{"given":"Obin","family":"Kwon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Enginnering and ASRI,Seoul,Korea"}]},{"given":"Kyungdo","family":"Kim","sequence":"additional","affiliation":[{"name":"Transdisciplinary Institute of Medicine &#x0026; Advanced Technology, Seoul National University Hopital,Seoul,Korea"}]},{"given":"Jaeyeon","family":"Jeong","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Enginnering and ASRI,Seoul,Korea"}]},{"given":"Howoong","family":"Jun","sequence":"additional","affiliation":[{"name":"Graduate School of Artificial Intelligence (GSAI) and ASRI, Seoul National University,Seoul,Korea"}]},{"given":"Hongjung","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate School of Artificial Intelligence (GSAI) and ASRI, Seoul National University,Seoul,Korea"}]},{"given":"Dongheui","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Mechatronics, German Aerospace Center (DLR),Wessling,Germany"}]},{"given":"Songhwai","family":"Oh","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Enginnering and ASRI,Seoul,Korea"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.232"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1089"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.047"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.028"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/629"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915602060"},{"key":"ref28","article-title":"Interactively Picking Real-World Objects with Un-constrained Spoken Language Instructions","author":"hatori","year":"2018","journal-title":"Proc Int Conf Robotics and Automation (ICRA)"},{"key":"ref27","article-title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","author":"stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12026"},{"key":"ref2","article-title":"Interactive Grounded Language Ac-quisition and Generalization in a 2D World","author":"yu","year":"2018","journal-title":"Proc of International Conf on Learning Representations (ICLR)"},{"key":"ref1","article-title":"Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents","author":"yu","year":"2019","journal-title":"Proc Int Conf Robotics and Automation (ICRA)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5627"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1218"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1287"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794441"},{"key":"ref25","article-title":"The RobotSlang Bench-mark: Dialog-guided Robot Localization and Navigation","author":"banerjee","year":"2020","journal-title":"Proc of the Conf on Robot Learning (CoRL)"},{"key":"ref50","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref51","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1286"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6849"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.348"},{"key":"ref18","article-title":"Vision-and-Dialog Navigation","author":"thomason","year":"2019","journal-title":"Proc of the Conf on Robot Learning (CoRL)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01074"},{"key":"ref4","article-title":"Embodied Question Answering","author":"das","year":"2018","journal-title":"Proc of the IEEE Conf on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref8","article-title":"Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction","author":"blukis","year":"0","journal-title":"Proc of the Conf on Robot Learning (CoRL)"},{"key":"ref7","article-title":"Learning to Map Natural Language Instructions to Physical Quad-copter Control using Simulated Flight","author":"blukis","year":"2020","journal-title":"Proc of the Conf on Robot Learning (CoRL)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.066"},{"key":"ref46","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"European Conf on Computer Vision (ECCV)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852786"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968603"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918760992"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812279.pdf?arnumber=9812279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:45Z","timestamp":1667516745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812279","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}