{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:21Z","timestamp":1774420101433,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888740","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["MFT: Modal Fusion Transformer for Cross-Modal Fusion in 3D Object Detection"],"prefix":"10.1109","author":[{"given":"Haojie","family":"Cai","sequence":"first","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}]},{"given":"Dongfu","family":"Yin","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}]},{"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}]},{"given":"Siting","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref3","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref6","article-title":"3d dual-fusion: Dual-domain dual-query camera-lidar fusion for 3d object detection","author":"Kim","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610230"},{"key":"ref9","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Conference on Robot Learning","author":"Wang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"ref11","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Li"},{"key":"ref12","article-title":"mmfusion: Multimodal fusion for 3d objects detection","author":"Ahmad","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160616"},{"key":"ref14","first-page":"16494","article-title":"Multimodal virtual point 3d detection","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Yin"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref17","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3d object detection","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref22","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref29","article-title":"Class-balanced grouping and sampling for point cloud 3d object detection","author":"Zhu","year":"2019"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref31","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888740.pdf?arnumber=10888740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:24Z","timestamp":1774416384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888740","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}