{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T09:52:59Z","timestamp":1777110779718,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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"}]},{"name":"2023 \u201cDouble First-Class\u201d Discipline Construction Interdisciplinary Team Project of Beijing University of Posts and Telecommunications","award":["2023SYLTD02"],"award-info":[{"award-number":["2023SYLTD02"]}]},{"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 Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3547855","type":"journal-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T13:54:00Z","timestamp":1741096440000},"page":"8031-8044","source":"Crossref","is-referenced-by-count":3,"title":["Pseudo-EV: Enhancing 3D Visual Grounding With Pseudo Embodied Viewpoint"],"prefix":"10.1109","volume":"35","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, Haidian, 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, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Modern Post, Beijing University of Posts and Telecommunications, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxuan","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Modern Post, Beijing University of Posts and Telecommunications, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318220"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407785"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3413074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2021.3127015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374045"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00445"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.10.008"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3502621"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452418"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3365249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref26","first-page":"1046","article-title":"LanguageRefer: Spatial-language model for 3D visual grounding","volume-title":"Proc. Conf. Robot Learn.","author":"Roh"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00033"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref37","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01661"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680690"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref44","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":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"issue":"2","key":"ref46","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Kenton"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref48","first-page":"20522","article-title":"Language conditioned spatial relation reasoning for 3D object grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02051"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_19"},{"key":"ref54","article-title":"ML-mamba: Efficient multi-modal large language model utilizing mamba-2","author":"Huang","year":"2024","journal-title":"arXiv:2407.19832"},{"key":"ref55","article-title":"MambaVision: A hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2024","journal-title":"arXiv:2407.08083"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28186"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10909465.pdf?arnumber=10909465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:02:19Z","timestamp":1754503339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10909465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3547855","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}