{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:37:11Z","timestamp":1782833831117,"version":"3.54.5"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["JCYJ20220818103006012"],"award-info":[{"award-number":["JCYJ20220818103006012"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["ZDSYS20211021111415025"],"award-info":[{"award-number":["ZDSYS20211021111415025"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3352808","type":"journal-article","created":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T18:39:46Z","timestamp":1705603186000},"page":"897-909","source":"Crossref","is-referenced-by-count":6,"title":["Divide and Conquer: Improving Multi-Camera 3D Perception With 2D Semantic-Depth Priors and Input-Dependent Queries"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5362-4103","authenticated-orcid":false,"given":"Qi","family":"Song","sequence":"first","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0337-9207","authenticated-orcid":false,"given":"Qingyong","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4735-3972","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2493-6033","authenticated-orcid":false,"given":"Yongquan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7950-1662","authenticated-orcid":false,"given":"Rui","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3274479"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245337"},{"key":"ref7","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref8","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_48"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093519"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01649"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00447"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref16","article-title":"BEVerse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022","journal-title":"arXiv:2205.09743"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref21","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref22","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Vaswani"},{"key":"ref23","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","article-title":"BEVFormer v2: Adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision","author":"Yang","year":"2022","journal-title":"arXiv:2211.10439"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128311"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3144036"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s120404431"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00504"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01370-7_53"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891028"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142418"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01892"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref47","article-title":"BEVStereo: Enhancing depth estimation in multi-view 3D object detection with dynamic temporal stereo","author":"Li","year":"2022","journal-title":"arXiv:2209.10248"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref50","first-page":"6985","article-title":"Bird\u2019s eye view segmentation using lifted 2D semantic features","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Dwivedi"},{"key":"ref51","article-title":"DA-BEV: Depth aware BEV transformer for 3D object detection","author":"Zhang","year":"2023","journal-title":"arXiv:2302.13002"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref54","article-title":"M2BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022","journal-title":"arXiv:2204.05088"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25460"},{"key":"ref56","article-title":"Priors are powerful: Improving a transformer for multi-camera 3D detection with 2D priors","author":"Feng","year":"2023","journal-title":"arXiv:2301.13592"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref58","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref60","volume-title":"Lyft Level 5 AV Dataset 2019","author":"Kesten","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref63","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref64","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref66","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547859"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref69","article-title":"FISHING Net: Future inference of semantic heatmaps in grids","author":"Hendy","year":"2020","journal-title":"arXiv:2006.09917"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref71","first-page":"1","article-title":"Orthographic feature transform for monocular 3D object detection","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Roddick"},{"key":"ref72","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Fifty"},{"key":"ref73","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020","journal-title":"arXiv:2009.09796"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10407035.pdf?arnumber=10407035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:48:26Z","timestamp":1706759306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10407035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3352808","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}