{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:06:26Z","timestamp":1774541186189,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0121300"],"award-info":[{"award-number":["2023ZD0121300"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/lra.2024.3401172","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T17:42:32Z","timestamp":1715794952000},"page":"6544-6551","source":"Crossref","is-referenced-by-count":50,"title":["Exploring Recurrent Long-Term Temporal Fusion for Multi-View 3D Perception"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9725-280X","authenticated-orcid":false,"given":"Chunrui","family":"Han","sequence":"first","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0248-8041","authenticated-orcid":false,"given":"Jinrong","family":"Yang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1216-9626","authenticated-orcid":false,"given":"Jianjian","family":"Sun","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8630-8270","authenticated-orcid":false,"given":"Zheng","family":"Ge","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1104-7897","authenticated-orcid":false,"given":"Runpei","family":"Dong","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2098-5890","authenticated-orcid":false,"given":"Hongyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0444-1079","authenticated-orcid":false,"given":"Weixin","family":"Mao","sequence":"additional","affiliation":[{"name":"Waseda University, Fukuoka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1448-5489","authenticated-orcid":false,"given":"Yuang","family":"Peng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Ji'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2138-4608","authenticated-orcid":false,"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Megvii Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref2","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref4","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Park","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref9","article-title":"Fast-BEV: Towards real-time on-vehicle birds-eye view perception","volume-title":"Proc. Adv. Neural Inform. Process. Syst. Workshop","author":"Huang","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref13","first-page":"466","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref25","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636083"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/34.310690"},{"key":"ref31","article-title":"STS: Surround-view temporal stereo for multi-view 3D detection","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Wang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00785"},{"key":"ref35","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"ref37","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Annu. Conf. Robot. Learn.","author":"Wang","year":"2021"},{"key":"ref38","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Li","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref45","article-title":"M $^{2}$ BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01712"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/nq\/s8-vi.143.228j"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3168781"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00496"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"ref53","article-title":"Polar parametrization for vision-based surround-view 3D detection","author":"Chen","year":"2022"},{"key":"ref54","article-title":"SRCN3D: Sparse R-CNN 3D surround-view camera object detection and tracking for autonomous driving","author":"Shi","year":"2022"},{"key":"ref55","article-title":"CC-3DT: Panoramic 3D object tracking via cross-camera fusion","author":"Fischer","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01719"},{"key":"ref57","article-title":"Quality matters: Embracing quality clues for robust 3D multi-object tracking","author":"Yang","year":"2022"},{"key":"ref58","article-title":"Sparse4d: Multi-view 3D object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_36"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01669"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10534628\/10530939.pdf?arnumber=10530939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:01:33Z","timestamp":1719349293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":62,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3401172","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}