{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:23:49Z","timestamp":1786119829184,"version":"build-2736575974"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":"crossref","award":["62495094"],"award-info":[{"award-number":["62495094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["25ZR1401356"],"award-info":[{"award-number":["25ZR1401356"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Chongqing Municipality","award":["CSTB2023NSCQ-MSX0063"],"award-info":[{"award-number":["CSTB2023NSCQ-MSX0063"]}]},{"name":"Shanghai Municipal Science and Shanghai Automotive Industry Science and Technology Development Foundation","award":["2407"],"award-info":[{"award-number":["2407"]}]},{"name":"National Key Research and Development Program of China","award":["2024YFE0115400"],"award-info":[{"award-number":["2024YFE0115400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsvt.2026.3679483","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:54:00Z","timestamp":1774986840000},"page":"11561-11575","source":"Crossref","is-referenced-by-count":0,"title":["AMTFusion: Boosting 3D Object Detection by Adaptive Multi-Modal Temporal Fusion and Augmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5085-7219","authenticated-orcid":false,"given":"Wei","family":"Tian","sequence":"first","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8234-1739","authenticated-orcid":false,"given":"Zhenglin","family":"Du","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiankun","family":"Yu","sequence":"additional","affiliation":[{"name":"SAIC Intelligent Technology (Shanghai) Company Ltd","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3713070"},{"key":"ref3","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref4","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial\u2013temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv:2211.10581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref6","article-title":"Sparse4D v3: Advancing end-to-end 3D detection and tracking","author":"Lin","year":"2023","journal-title":"arXiv:2311.11722"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3435045"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref12","article-title":"EA-LSS: Edge-aware lift-splat-shot framework for 3D BEV object detection","author":"Hu","year":"2023","journal-title":"arXiv:2303.17895"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202810"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103625"},{"key":"ref17","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","author":"Park","year":"2022","journal-title":"arXiv:2210.02443"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref19","article-title":"Sparse4D v2: Recurrent temporal fusion with sparse model","author":"Lin","year":"2023","journal-title":"arXiv:2305.14018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00625"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref28","article-title":"FusionFormer: A multi-sensory fusion in bird\u2019s-eye-view and temporal consistent transformer for 3D object detection","author":"Hu","year":"2023","journal-title":"arXiv:2309.05257"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3366664"},{"key":"ref31","article-title":"Exploring data augmentation for multi-modality 3D object detection","author":"Zhang","year":"2020","journal-title":"arXiv:2012.12741"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref37","first-page":"1","article-title":"Mixup: Beyond empirical risk management","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00771"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref43","first-page":"1992","article-title":"DeepInteraction: 3D object detection via modality interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01211"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"ref46","article-title":"BEVFusion4D: Learning LiDAR-camera fusion under bird\u2019s-eye-view via cross-modality guidance and temporal aggregation","author":"Cai","year":"2023","journal-title":"arXiv:2303.17099"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_25"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref50","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25056-9_43"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801741"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341778"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285651"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11458867.pdf?arnumber=11458867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:07:06Z","timestamp":1786043226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11458867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":55,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3679483","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}