{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:30:29Z","timestamp":1772908229891,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681038","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"4283-4291","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LaneCMKT: Boosting Monocular 3D Lane Detection with Cross-Modal Knowledge Transfer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4494-8894","authenticated-orcid":false,"given":"Runkai","family":"Zhao","sequence":"first","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5473-5751","authenticated-orcid":false,"given":"Heng","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3706-8896","authenticated-orcid":false,"given":"Weidong","family":"Cai","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161160"},{"key":"e_1_3_2_1_2_1","volume-title":"CurveFormer: 3D lane detection by curve propagation with temporal curve queries and attention. arXiv preprint arXiv:2402.06423","author":"Bai Yifeng","year":"2024","unstructured":"Yifeng Bai, Zhirong Chen, Pengpeng Liang, and Erkang Cheng. 2024. CurveFormer: 3D lane detection by curve propagation with temporal curve queries and attention. arXiv preprint arXiv:2402.06423 (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19143166"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_32"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Chen Zehui","year":"2022","unstructured":"Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, and Feng Zhao. 2022. BEVDistill: Cross-modal bev distillation for multi-view 3D object detection. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_7_1","volume-title":"Monodistill: Learning spatial features for monocular 3D object detection. arXiv preprint arXiv:2201.10830.","author":"Chong Zhiyu","year":"2022","unstructured":"Zhiyu Chong, Xinzhu Ma, Hong Zhang, Yuxin Yue, Haojie Li, Zhihui Wang, and Wanli Ouyang. 2022. Monodistill: Learning spatial features for monocular 3D object detection. arXiv preprint arXiv:2201.10830."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00301"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_40"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01674"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612006"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3609703.3609707"},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612389"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00483"},{"key":"e_1_3_2_1_19_1","unstructured":"Tianyu Li Li Chen Huijie Wang Yang Li Jiazhi Yang Xiangwei Geng Shengyin Jiang Yuting Wang Hang Xu Chunjing Xu Junchi Yan Ping Luo and Hongyang Li. 2023. Graph-based topology reasoning for driving scenes. arXiv preprint arXiv:2304.05277."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Li Tianyu","year":"2023","unstructured":"Tianyu Li, Peijin Jia, Bangjun Wang, Li Chen, Kun Jiang, Junchi Yan, and Hongyang Li. 2023. LaneSegNet: Map learning with lane segment perception for autonomous driving. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"e_1_3_2_1_22_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983.","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983."},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Luo Yueru","year":"2023","unstructured":"Yueru Luo, Shuguang Cui, and Zhen Li. 2023. DV-3DLane: End-to-end multi-modal 3D lane detection with dual-view representation. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_24_1","unstructured":"Yueru Luo Xu Yan Chaoda Zheng Chao Zheng Shuqi Mei Tang Kun Shuguang Cui and Zhen Li. 2022. M2--3DLaneNet: Exploring Multi-Modal 3D Lane Detection. arXiv preprint arXiv:2209.05996."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00730"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00491"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00144"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning (ICML). PMLR, 8748--8763."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00309"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01662"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00103"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00502"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612107"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612013"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_39"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00768"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610087"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612454"},{"key":"e_1_3_2_1_46_1","unstructured":"Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681038","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:37Z","timestamp":1750295857000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681038","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681038","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}