{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:29:58Z","timestamp":1777656598547,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":60,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681360","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"2652-2661","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7928-3354","authenticated-orcid":false,"given":"Xiao","family":"Zhao","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2869-9434","authenticated-orcid":false,"given":"Xukun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-5671","authenticated-orcid":false,"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8217-6508","authenticated-orcid":false,"given":"Mingyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6244-6081","authenticated-orcid":false,"given":"Mingcheng","family":"Li","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3755-8724","authenticated-orcid":false,"given":"Shunli","family":"Wang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-4347","authenticated-orcid":false,"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University & Jilin Provincial Key Laboratory of Intelligence Science and Engineering, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/CVPR52688.2022.00116"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00330"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"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","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40, 4 (2017), 834--848."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00771"},{"key":"e_1_3_2_1_8_1","volume-title":"Autoalign: Pixel-instance feature aggregation for multi-modal 3d object detection. arXiv preprint arXiv:2201.06493","author":"Chen Zehui","year":"2022","unstructured":"Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinghong Jiang, Feng Zhao, Bolei Zhou, and Hang Zhao. 2022. Autoalign: Pixel-instance feature aggregation for multi-modal 3d object detection. arXiv preprint arXiv:2201.06493 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings, Part IV 14","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Identity mappings in deep residual networks. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part IV 14. Springer, 630--645."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"e_1_3_2_1_15_1","volume-title":"Bevdet4d: Exploit temporal cues in multicamera 3d object detection. arXiv preprint arXiv:2203.17054","author":"Huang Junjie","year":"2022","unstructured":"Junjie Huang and Guan Huang. 2022. Bevdet4d: Exploit temporal cues in multicamera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790","author":"Huang Junjie","year":"2021","unstructured":"Junjie Huang, Guan Huang, Zheng Zhu, Yun Ye, and Dalong Du. 2021. Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors. arXiv preprint arXiv:2403.06093","author":"Ji Haoxuanye","year":"2024","unstructured":"Haoxuanye Ji, Pengpeng Liang, and Erkang Cheng. 2024. Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors. arXiv preprint arXiv:2403.06093 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00641"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"e_1_3_2_1_26_1","first-page":"10421","article-title":"Bevfusion: A simple and robust lidar-camera fusion framework","volume":"35","author":"Liang Tingting","year":"2022","unstructured":"Tingting Liang, Hongwei Xie, Kaicheng Yu, Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Tao Tang, Bing Wang, and Zhi Tang. 2022. Bevfusion: A simple and robust lidar-camera fusion framework. Advances in Neural Information Processing Systems 35 (2022), 10421--10434.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_28_1","volume-title":"Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329","author":"Liu Shilong","year":"2022","unstructured":"Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, and Lei Zhang. 2022. Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"e_1_3_2_1_32_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 15216--15225","author":"Pan Chenbin","year":"2024","unstructured":"Chenbin Pan, Burhaneddin Yaman, Senem Velipasalar, and Liu Ren. 2024. Clipbevformer: Enhancing multi-view image-based bev detector with ground truth flow. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 15216--15225."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings, Part XIV 16","author":"Philion Jonah","year":"2020","unstructured":"Jonah Philion and Sanja Fidler. 2020. Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16. Springer, 194--210."},{"key":"e_1_3_2_1_37_1","volume-title":"Cyclical learning rates for training neural networks. In 2017 IEEE winter conference on applications of computer vision (WACV)","author":"Smith Leslie N","unstructured":"Leslie N Smith. 2017. Cyclical learning rates for training neural networks. In 2017 IEEE winter conference on applications of computer vision (WACV). IEEE, 464--472."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00625"},{"key":"e_1_3_2_1_41_1","volume-title":"Conference on Robot Learning. PMLR, 180--191","author":"Wang Yue","year":"2022","unstructured":"Yue Wang, Vitor Campagnolo Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, and Justin Solomon. 2022. Detr3d: 3d object detection from multi-view images via 3d-to-2d queries. In Conference on Robot Learning. PMLR, 180--191."},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation. arXiv preprint arXiv:2204.05088","author":"Xie Enze","year":"2022","unstructured":"Enze Xie, Zhiding Yu, Daquan Zhou, Jonah Philion, Anima Anandkumar, Sanja Fidler, Ping Luo, and Jose M Alvarez. 2022. M?2 BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation. arXiv preprint arXiv:2204.05088 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"e_1_3_2_1_45_1","first-page":"1992","article-title":"Deepinteraction: 3d object detection via modality interaction","volume":"35","author":"Yang Zeyu","year":"2022","unstructured":"Zeyu Yang, Jiaqi Chen, Zhenwei Miao, Wei Li, Xiatian Zhu, and Li Zhang. 2022. Deepinteraction: 3d object detection via modality interaction. Advances in Neural Information Processing Systems 35 (2022), 1992--2005.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_46_1","volume-title":"Is-fusion: Instance-scene collaborative fusion for multimodal 3d object detection. arXiv preprint arXiv:2403.15241","author":"Yin Junbo","year":"2024","unstructured":"Junbo Yin, Jianbing Shen, Runnan Chen, Wei Li, Ruigang Yang, Pascal Frossard, and Wenguan Wang. 2024. Is-fusion: Instance-scene collaborative fusion for multimodal 3d object detection. arXiv preprint arXiv:2403.15241 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"e_1_3_2_1_48_1","first-page":"16494","article-title":"Multimodal virtual point 3d detection","volume":"34","author":"Yin Tianwei","year":"2021","unstructured":"Tianwei Yin, Xingyi Zhou, and Philipp Kr\u00e4henb\u00fchl. 2021. Multimodal virtual point 3d detection. Advances in Neural Information Processing Systems 34 (2021), 16494--16507.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00321"},{"key":"e_1_3_2_1_50_1","volume-title":"SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection. arXiv preprint arXiv:2403.05817","author":"Zhang Gang","year":"2024","unstructured":"Gang Zhang, Junnan Chen, Guohuan Gao, Jianmin Li, Si Liu, and Xiaolin Hu. 2024. SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection. arXiv preprint arXiv:2403.05817 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"e_1_3_2_1_54_1","volume-title":"Beverse: Unified perception and prediction in birdseye- view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743","author":"Zhang Yunpeng","year":"2022","unstructured":"Yunpeng Zhang, Zheng Zhu, Wenzhao Zheng, Junjie Huang, Guan Huang, Jie Zhou, and Jiwen Lu. 2022. Beverse: Unified perception and prediction in birdseye- view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743 (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"e_1_3_2_1_56_1","volume-title":"Conference on Robot Learning. PMLR, 923--932","author":"Zhou Yin","year":"2020","unstructured":"Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, and Vijay Vasudevan. 2020. End-to-end multi-view fusion for 3d object detection in lidar point clouds. In Conference on Robot Learning. PMLR, 923--932."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12588--12597","author":"Zhou Zhizhuo","year":"2023","unstructured":"Zhizhuo Zhou and Shubham Tulsiani. 2023. Sparsefusion: Distilling viewconditioned diffusion for 3d reconstruction. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12588--12597."},{"key":"e_1_3_2_1_59_1","volume-title":"Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492","author":"Zhu Benjin","year":"2019","unstructured":"Benjin Zhu, Zhengkai Jiang, Xiangxin Zhou, Zeming Li, and Gang Yu. 2019. Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492 (2019)."},{"key":"e_1_3_2_1_60_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","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 (2020)."}],"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\/3664647.3681360","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:44Z","timestamp":1750295864000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":60,"alternative-id":["10.1145\/3664647.3681360","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681360","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"}}]}}