{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:23Z","timestamp":1766061683733,"version":"3.48.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247415","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7576-7583","source":"Crossref","is-referenced-by-count":0,"title":["Refer and Grasp: Vision-Language Guided Continuous Dexterous Grasping"],"prefix":"10.1109","author":[{"given":"Yayu","family":"Huang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Qi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daheng","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongkang","family":"Luo","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","volume-title":"7th Annual Conference on Robot Learning","author":"Tziafas","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802654"},{"article-title":"Grasp what you want: Embodied dexterous grasping system driven by your voice","year":"2024","author":"Li","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref6","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref10","first-page":"19 652","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","year":"2024","author":"Zhang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.419"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793917"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561398"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129138"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160314"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140424"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3322086"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3420722"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09907-y"},{"key":"ref30","article-title":"Learning score-based grasping primitive for human-assisting dexterous grasping","volume":"36","author":"Wu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aao4900"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.105133"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04901"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981838"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231193710"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00236"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"article-title":"Lisa++: An improved baseline for reasoning segmentation with large language model","year":"2023","author":"Yang","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3527278"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247415.pdf?arnumber=11247415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:38:17Z","timestamp":1766061497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247415","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}