{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:49Z","timestamp":1777655809733,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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","award":["62173045"],"award-info":[{"award-number":["62173045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673192"],"award-info":[{"award-number":["61673192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2020XD-A04-3"],"award-info":[{"award-number":["2020XD-A04-3"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["622RC675"],"award-info":[{"award-number":["622RC675"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/lra.2024.3426286","type":"journal-article","created":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T17:40:23Z","timestamp":1720633223000},"page":"7469-7476","source":"Crossref","is-referenced-by-count":7,"title":["ViewInfer3D: 3D Visual Grounding Based on Embodied Viewpoint Inference"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6618-4338","authenticated-orcid":false,"given":"Liang","family":"Geng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1595-2499","authenticated-orcid":false,"given":"Jianqin","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aax8177"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44223-0_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.10.008"},{"key":"ref6","article-title":"LLM-grounder: Open-vocabulary 3D visual grounding with large language model as an agent","author":"Yang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00257"},{"key":"ref16","first-page":"20623","article-title":"Visual programming for zero-shot open-vocabulary 3D visual grounding","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yuan","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189785"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3399997"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1146"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157567"},{"key":"ref26","first-page":"23","article-title":"Sayplan: Grounding large language models using 3D scene graphs for scalable task planning","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","volume":"229","author":"Rana","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2023.3332242"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref30","first-page":"5105","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi","year":"2017"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84996-023-6","volume-title":"Mathematics for Computer Graphics","volume":"5","author":"Vince","year":"2010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref36","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Madaan","year":"2024"},{"key":"ref37","article-title":"Empowering language models with active inquiry for deeper understanding","author":"Pang","year":"2024"},{"key":"ref38","first-page":"7","article-title":"Ask me anything: A simple strategy for prompting language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Arora","year":"2022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10601335\/10592798.pdf?arnumber=10592798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T04:42:33Z","timestamp":1721450553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10592798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":38,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3426286","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}