{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:38:49Z","timestamp":1772041129545,"version":"3.50.1"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3594805","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T18:14:32Z","timestamp":1754072072000},"page":"10295-10310","source":"Crossref","is-referenced-by-count":1,"title":["Advancing 3D Object Detection With Depth-Aware Spatial Knowledge Distillation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2169-8271","authenticated-orcid":false,"given":"Zizhang","family":"Wu","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1960-9501","authenticated-orcid":false,"given":"Fan","family":"Song","sequence":"additional","affiliation":[{"name":"Megvii Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6222-0442","authenticated-orcid":false,"given":"Yuanzhu","family":"Gan","sequence":"additional","affiliation":[{"name":"ZongmuTech, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunzhe","family":"Wu","sequence":"additional","affiliation":[{"name":"ZongmuTech, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7483-3940","authenticated-orcid":false,"given":"Tianhao","family":"Xu","sequence":"additional","affiliation":[{"name":"ZongmuTech, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2573-0994","authenticated-orcid":false,"given":"Xiaoquan","family":"Wang","sequence":"additional","affiliation":[{"name":"ZongmuTech, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Tang","sequence":"additional","affiliation":[{"name":"ZongmuTech, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0892-1213","authenticated-orcid":false,"given":"Jian","family":"Pu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161329"},{"key":"ref4","first-page":"19182","article-title":"Point primitive transformer for long-range 3D point cloud completion","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Bai","year":"2023"},{"key":"ref5","first-page":"15916","article-title":"Vista: Boosting 3D object detection via dual cross-view spatial attention","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zhang","year":"2023"},{"key":"ref6","first-page":"15906","article-title":"BEVDepth: Acquisition of reliable depth for multi-view 3D object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Ma","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref8","first-page":"14072","article-title":"BEVFormer V2: Adapting modern image backbones to Bird\u2019s-Eye view recognition via perspective supervision","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li","year":"2023"},{"key":"ref9","first-page":"15886","article-title":"PETRV2: A unified framework for 3D perception from multi-camera images","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Wang","year":"2023"},{"key":"ref10","first-page":"15876","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Liu","year":"2023"},{"key":"ref11","first-page":"14082","article-title":"MonoNeRF: Learning scene representations for monocular 3D object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Guo","year":"2023"},{"key":"ref12","first-page":"1","article-title":"MonoDistill: Learning spatial features for monocular 3D object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chong","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00096"},{"key":"ref14","first-page":"87","article-title":"Cross-modality knowledge distillation network for monocular 3D object detection","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Yu","year":"2022"},{"key":"ref15","first-page":"8396","article-title":"MonodTR: Monocular 3D object detection with depth-aware transformer","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Sun","year":"2022"},{"key":"ref16","first-page":"3352","article-title":"SOAP: Cross-sensor domain adaptation for 3D object detection","volume-title":"Proc. IEEE Winter Conf. Appl. Comput. Vis.","author":"Huang","year":"2024"},{"key":"ref17","first-page":"14112","article-title":"Geometry-aware guided refinement of pseudo-LiDAR for monocular 3D object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Wang","year":"2023"},{"key":"ref18","first-page":"10555","article-title":"Implicit feature alignment: Learn to convert text recognizer to text spotter","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qian","year":"2022"},{"key":"ref19","first-page":"19192","article-title":"Point-BEV: A 3D scene representation for understanding point clouds","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Xie","year":"2023"},{"key":"ref20","first-page":"12715","article-title":"Cylinder3D: An effective 3D framework for driving-scenario understanding from point cloud","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li","year":"2022"},{"key":"ref21","first-page":"4262","article-title":"Stereo matching with cost volume fusion","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Xu","year":"2023"},{"key":"ref22","first-page":"4282","article-title":"Learning dynamic warping for scene flow estimation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Yang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref26","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25391"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref29","article-title":"DETR4D: Direct multi-view 3D object detection with sparse attention","author":"Luo","year":"2022"},{"key":"ref30","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_19"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3218594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref42","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00114"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref53","first-page":"12753","article-title":"End-to-end multi-view fusion for 3D object detection in lidar point clouds","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zhou","year":"2020"},{"key":"ref54","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","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref57","first-page":"206","article-title":"PolarFormer: Multi-camera 3D object detection with polar transformer","volume-title":"Eur. Conf. Comput. Vis.","author":"Jiang","year":"2022"},{"key":"ref58","first-page":"684","article-title":"Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhang","year":"2022"},{"key":"ref59","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref60","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Romero","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00298"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01524"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40283-8_3"},{"key":"ref69","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref81","first-page":"1","article-title":"BEVDistill: Cross-modal BEV distillation for multi-view 3D object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00052"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00627"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"ref85","first-page":"80165","article-title":"Depth-discriminative metric learning for monocular 3D object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Choi","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28436"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref89","first-page":"3354","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Geiger","year":"2012"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref91","first-page":"424","article-title":"3D object proposals for accurate object class detection","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2015"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00321"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11106759.pdf?arnumber=11106759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:52Z","timestamp":1759772212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11106759\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":93,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3594805","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}