{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:20:26Z","timestamp":1765520426721,"version":"3.48.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247216","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2539-2546","source":"Crossref","is-referenced-by-count":0,"title":["Consistent Feature Alignment for Cross-Modal Knowledge Distillation in Monocular 3D Object Detection"],"prefix":"10.1109","author":[{"given":"Fan","family":"Li","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Ding","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00352"},{"article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","year":"2021","author":"Huang","key":"ref4"},{"article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"The Conference on Robot Learning (CoRL)","author":"Wang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"article-title":"Monodistill: Learning spatial features for monocular 3d object detection","year":"2022","author":"Chong","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3405992"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230555"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref25"},{"key":"ref26","article-title":"Learning efficient object detection models with knowledge distillation","volume":"30","author":"Chen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612162"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00090"},{"article-title":"Graph-based knowledge distillation by multi-head attention network","year":"2019","author":"Lee","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25391"},{"article-title":"Bevdistill: Cross-modal bev distillation for multi-view 3d object detection","year":"2022","author":"Chen","key":"ref31"},{"article-title":"Tig-bev: Multi-view bev 3d object detection via target inner-geometry learning","year":"2022","author":"Huang","key":"ref32"},{"key":"ref33","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Ross","year":"2017","journal-title":"proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"ref34","first-page":"12084","article-title":"Improved feature distillation via projector ensemble","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3475583"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00979"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2706685"},{"key":"ref40","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247216.pdf?arnumber=11247216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:32Z","timestamp":1765520132000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247216","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}