{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T16:09:34Z","timestamp":1773158974653,"version":"3.50.1"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":"publisher","award":["62461160260"],"award-info":[{"award-number":["62461160260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2023YFE0205800"],"award-info":[{"award-number":["2023YFE0205800"]}]},{"name":"Science and Technology Development Fund, Macau SAR","award":["0075\/2023\/AMJ"],"award-info":[{"award-number":["0075\/2023\/AMJ"]}]},{"name":"Science and Technology Development Fund, Macau SAR","award":["0092\/2024\/AFJ"],"award-info":[{"award-number":["0092\/2024\/AFJ"]}]},{"name":"Science and Technology Development Fund, Macau SAR","award":["0003\/2023\/RIB1"],"award-info":[{"award-number":["0003\/2023\/RIB1"]}]},{"name":"Science and Technology Development Fund, Macau SAR","award":["001\/2024\/SKL"],"award-info":[{"award-number":["001\/2024\/SKL"]}]},{"name":"Guangdong Department of Science and Technology","award":["2023A0505030003"],"award-info":[{"award-number":["2023A0505030003"]}]},{"DOI":"10.13039\/501100004733","name":"Universidade de Macau","doi-asserted-by":"publisher","award":["MYRG-GRG2023-00237-FST-UMDF"],"award-info":[{"award-number":["MYRG-GRG2023-00237-FST-UMDF"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004733","name":"Universidade de Macau","doi-asserted-by":"publisher","award":["MYRG-GRG2024-00299-FST"],"award-info":[{"award-number":["MYRG-GRG2024-00299-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcsvt.2025.3596322","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:02:03Z","timestamp":1754503323000},"page":"846-860","source":"Crossref","is-referenced-by-count":4,"title":["TiGDistill-BEV: Multi-View BEV 3D Object Detection via Target Inner-Geometry Learning Distillation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0274-6677","authenticated-orcid":false,"given":"Shaoqing","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, the Centre for Artificial Intelligence and Robotics, University of Macau, Macau, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3677-2577","authenticated-orcid":false,"given":"Fang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, the Centre for Artificial Intelligence and Robotics, University of Macau, Macau, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1420-9355","authenticated-orcid":false,"given":"Peixiang","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Engineering, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5539-2599","authenticated-orcid":false,"given":"Ziying","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9151-7758","authenticated-orcid":false,"given":"Zhi-Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electromechanical Engineering, State Key Laboratory of Internet of Things for Smart City, the Centre for Artificial Intelligence and Robotics, University of Macau, Macau, SAR, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/141"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025798"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3405992"},{"key":"ref6","article-title":"VoxelNextFusion: A simple, unified and effective voxel fusion framework for multi-modal 3D object detection","author":"Song","year":"2024","journal-title":"arXiv:2401.02702"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237579"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296583"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3310042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3387732"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3270728"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229526"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123438"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681565"},{"key":"ref19","article-title":"GaussianPretrain: A simple unified 3D Gaussian representation for visual pre-training in autonomous driving","author":"Xu","year":"2024","journal-title":"arXiv:2411.12452"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref21","article-title":"BEVDistill: Cross-modal BEV distillation for multi-view 3D object detection","author":"Chen","year":"2022","journal-title":"arXiv:2211.09386"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"ref23","article-title":"LiCROcc: Teach radar for accurate semantic occupancy prediction using LiDAR and camera","author":"Ma","year":"2024","journal-title":"arXiv:2407.16197"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref25","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref26","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref29","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref31","article-title":"PETRv2: A unified framework for 3D perception from multi-camera images","author":"Liu","year":"2022","journal-title":"arXiv:2206.01256"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref33","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial\u2013temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv:2211.10581"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref36","first-page":"1","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref39","article-title":"SurroundDepth: Entangling surrounding views for self-supervised multi-camera depth estimation","author":"Wei","year":"2022","journal-title":"arXiv:2204.03636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150884"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00845"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref46","article-title":"MonoDETR: Depth-guided transformer for monocular 3D object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.13310"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01361"},{"key":"ref50","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref51","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang","year":"2017","journal-title":"arXiv:1707.01219"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00816"},{"key":"ref53","first-page":"14338","article-title":"Knowledge augmented deep neural networks for joint facial expression and action unit recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cui"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref55","article-title":"Distillation with contrast is all you need for self-supervised point cloud representation learning","author":"Fu","year":"2022","journal-title":"arXiv:2202.04241"},{"key":"ref56","article-title":"Learning 3D representations from 2D pre-trained models via image-to-point masked autoencoders","author":"Zhang","year":"2022","journal-title":"arXiv:2212.06785"},{"key":"ref57","article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","author":"Liu","year":"2021","journal-title":"arXiv:2104.04687"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref60","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Chen"},{"key":"ref61","first-page":"5116","article-title":"UniDistill: A universal cross-modality knowledge distillation framework for 3D object detection in bird\u2019s-eye view","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhou"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00829"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_21"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01282"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28577"},{"key":"ref67","article-title":"Leveraging vision-centric multi-modal expertise for 3D object detection","author":"Huang","year":"2023","journal-title":"arXiv:2310.15670"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref73","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_39"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074363"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3515454"},{"key":"ref87","first-page":"1","article-title":"STXD: Structural and temporal cross-modal distillation for multi-view 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Jang"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11365019\/11115141.pdf?arnumber=11115141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:15Z","timestamp":1769634075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11115141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":87,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3596322","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}