{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T06:52:29Z","timestamp":1793083949427,"version":"4.5.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JC STEM Lab of Machine Learning and Computer Vision"},{"name":"Hong Kong Jockey Club Charities Trust","id":[{"id":"https:\/\/ror.org\/02z8pdw35","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3581780","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:29:00Z","timestamp":1750426140000},"page":"6235-6247","source":"Crossref","is-referenced-by-count":6,"title":["3DGeoDet: General-Purpose Geometry-Aware Image-Based 3D Object Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8242-1581","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8659-4724","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9337-687X","authenticated-orcid":false,"given":"Yawen","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4932-0593","authenticated-orcid":false,"given":"Lap-Pui","family":"Chau","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3480691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3410308"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/trit.2019.0034"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222632"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3245359"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275366"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304054"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02131"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref26","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref27","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_35"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_29"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270638"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189778"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref37","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055632"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"ref43","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Conf. Robot Learn.","author":"Wang","year":"2022"},{"key":"ref44","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161451"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref51","first-page":"64318","article-title":"OCC3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tian","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_25"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00543"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01578"},{"key":"ref57","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00627"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3560240"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_5"},{"key":"ref62","first-page":"11703","article-title":"Monouni: A unified vehicle and infrastructure-side monocular 3D object detection network with sufficient depth clues","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Jia","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00088"},{"key":"ref64","article-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11045444.pdf?arnumber=11045444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:59:55Z","timestamp":1759237195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3581780","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}