{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T20:05:27Z","timestamp":1784318727984,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62071127"],"award-info":[{"award-number":["62071127"]}],"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":["62101137"],"award-info":[{"award-number":["62101137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022ZD0160100"],"award-info":[{"award-number":["2022ZD0160100"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668488","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"5809-5820","source":"Crossref","is-referenced-by-count":0,"title":["Rendered 2D Semantic and Generative Priors Guided 3D Multi-Object Grounding"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9848-2272","authenticated-orcid":false,"given":"Peng","family":"Guo","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5177-8320","authenticated-orcid":false,"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology, and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hancheng","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-1619","authenticated-orcid":false,"given":"Fukun","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00952"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00226"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3379888"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3228492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3081260"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00515"},{"key":"ref23","article-title":"ECNet: Effective controllable text-to-image diffusion models","author":"Li","year":"2024"},{"key":"ref24","article-title":"SAD: Segment any RGBD","author":"Cen","year":"2023"},{"key":"ref25","article-title":"SAM3D: Segment anything in 3D scenes","author":"Yang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02671"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00098"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340892"},{"key":"ref31","first-page":"487","article-title":"D3Net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in RGB-D scans","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Chen","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3455898"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543050"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128195"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3584895"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680758"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611902"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3620"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref54","article-title":"Fixing weight decay regularization in Adam","author":"Loshchilov","year":"2017"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11415711.pdf?arnumber=11415711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T19:45:40Z","timestamp":1784317540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11415711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668488","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}