{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:53:09Z","timestamp":1767333189897,"version":"3.48.0"},"reference-count":35,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2025.3641506","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:43:50Z","timestamp":1765219430000},"page":"356-360","source":"Crossref","is-referenced-by-count":0,"title":["LVMF3D: Large Vision Model Boosting Multimodal Fusion for Indoor 3D Object Detection"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3208-1960","authenticated-orcid":false,"given":"Yichen","family":"Shi","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-1286","authenticated-orcid":false,"given":"Wenming","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5211-9472","authenticated-orcid":false,"given":"Nan","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Electronics Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2131-3044","authenticated-orcid":false,"given":"Guijin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronics Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_18"},{"key":"ref7","first-page":"29975","article-title":"CAGroup3D: Class-aware grouping for 3D object detection on point clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"article-title":"V-DETR: DETR with vertex relative position encoding for 3D object detection","year":"2023","author":"Shen","key":"ref11"},{"key":"ref12","first-page":"39876","article-title":"Uni3DETR: Unified 3D detection transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28616"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3449319"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681121"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02015"},{"key":"ref17","first-page":"132824","article-title":"MVSDet: Multi-view indoor 3D object detection via efficient plane sweeps","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","volume":"37","author":"Xu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3336569"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01180"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"article-title":"Boosting 3D object detection via object-focused image fusion","year":"2022","author":"Yang","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3309133"},{"key":"ref26","article-title":"Progressive multi-modal fusion for robust 3D object detection","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Mohan","year":"2024"},{"article-title":"mmFUSION: Multimodal fusion for 3D objects detection","year":"2023","author":"Ahmad","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","year":"2022","author":"Zhang","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref32","article-title":"Object detection with multimodal large vision-language models: An in-depth review","volume-title":"Inf. Fusion","volume":"126","author":"Sapkota","year":"2026"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33337"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3468090"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11282993.pdf?arnumber=11282993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:52:04Z","timestamp":1767333124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11282993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3641506","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2026]]}}}