{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:07:44Z","timestamp":1778080064586,"version":"3.51.4"},"reference-count":64,"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"}],"funder":[{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341379","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"976-983","source":"Crossref","is-referenced-by-count":36,"title":["VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes"],"prefix":"10.1109","author":[{"given":"Yuhao","family":"Lu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beixing","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangfu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561994"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.3023541"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981077"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PLANS.2016.7479745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2023.3281153"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"issue":"8","key":"ref17","article-title":"Gqa: a new dataset for compositional question answering over real-world images","volume":"3","author":"Hudson","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Dex-nerf: Using a neural radiance field to grasp transparent objects","author":"Ichnowski","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref22","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794435"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197566"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561473"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811961"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00236"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref35","first-page":"1174","article-title":"Generating expressions that refer to visible objects","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Mitchell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197318"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.03.003"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.264"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref41","article-title":"Pointnet ++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-020-01202-3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385661"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.028"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897133"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"ar Xiv preprint"},{"key":"ref49","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"key":"ref52","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.419"},{"key":"ref55","first-page":"1369","article-title":"The best of both modes: Separately leveraging rgb and depth for unseen object instance segmentation","volume-title":"Conference on robot learning","author":"Xie"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746336"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogr.2022.03.002"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00142"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref64","article-title":"Regnet: Region-based grasp network for end-to-end grasp detection in point clouds","author":"Zhao","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"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\/10341379.pdf?arnumber=10341379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:27:48Z","timestamp":1705022868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341379","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}