{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:41Z","timestamp":1777889681832,"version":"3.51.4"},"reference-count":58,"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\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"publisher","award":["AISG3-GV-2023-011"],"award-info":[{"award-number":["AISG3-GV-2023-011"]}],"id":[{"id":"10.13039\/501100001381","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\/iccv51701.2025.00907","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11-11","source":"Crossref","is-referenced-by-count":0,"title":["ViewSRD: 3D Visual Grounding Via Structured Multi-View Decomposition"],"prefix":"10.1109","author":[{"given":"Ronggang","family":"Huang","sequence":"first","affiliation":[{"name":"South China University of Technology"}]},{"given":"Haoxin","family":"Yang","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Yan","family":"Cai","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Xuemiao","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Huaidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology"}]},{"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","article-title":"Cot3dref: Chain-of-thoughts data-efficient 3d visual grounding","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations (ICLR)","author":"Bakr"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01340"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11210024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611485"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3426286"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01508"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1484088"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680833"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3555552"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00609"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0957"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3563229"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4473"},{"key":"ref28","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535230"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"50898","article-title":"Mmscan: A multi-modal 3d scene dataset with hierarchical grounded language annotations","volume":"37","author":"Lyu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3576839"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3332098"},{"key":"ref35","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":"ref36","first-page":"1046","article-title":"Languagerefer: Spatial-language model for 3d visual grounding","volume-title":"Conf. Robot Learn. (CoRL)","author":"Roh"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01333"},{"key":"ref38","article-title":"Multi-agent collaboration: Harnessing the power of intelligent llm agents","author":"Talebirad","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"Openchat: Advancing open-source language models with mixed-quality data","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01320"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3174656"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01633"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01923"},{"key":"ref46","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3449104"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref49","article-title":"Appagent: Multimodal agents as smartphone users","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01971"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01949"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01241"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00292"},{"key":"ref55","article-title":"Recdreamer: Consistent text-to-3d generation via uniform score distillation","volume-title":"Proc. Thirteenth Int. Conf. Learn. Representations (ICLR)","author":"Zheng","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3364162"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443387.pdf?arnumber=11443387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:49Z","timestamp":1777612489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00907","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}