{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:57:13Z","timestamp":1786114633252,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"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":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547859","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"5999-6008","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["Graph-DETR3D"],"prefix":"10.1145","author":[{"given":"Zehui","family":"Chen","sequence":"first","affiliation":[{"name":"Univ. of Sci. and Tech. of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangji","family":"Fang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinhong","family":"Jiang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Univ. of Sci. and Tech. of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.963459"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(77)90070-9"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_2_5_1","volume-title":"ProxylessNAS: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332","author":"Cai Han","year":"2018","unstructured":"Han Cai , Ligeng Zhu , and Song Han . 2018. ProxylessNAS: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 ( 2018 ). Han Cai, Ligeng Zhu, and Song Han. 2018. ProxylessNAS: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-010-0660-6"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"e_1_3_2_2_10_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 ). 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_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_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 , and Dalong Du. 2021. BEVDet: High-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 ( 2021 ). Junjie Huang, Guan Huang, Zheng Zhu, 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_2_17_1","volume-title":"1st Place Solutions of Waymo Open Dataset Challenge 2020--2D Object Detection Track. arXiv preprint arXiv:2008.01365","author":"Huang Zehao","year":"2020","unstructured":"Zehao Huang , Zehui Chen , Qiaofei Li , Hongkai Zhang , and Naiyan Wang . 2020. 1st Place Solutions of Waymo Open Dataset Challenge 2020--2D Object Detection Track. arXiv preprint arXiv:2008.01365 ( 2020 ). Zehao Huang, Zehui Chen, Qiaofei Li, Hongkai Zhang, and Naiyan Wang. 2020. 1st Place Solutions of Waymo Open Dataset Challenge 2020--2D Object Detection Track. arXiv preprint arXiv:2008.01365 (2020)."},{"key":"e_1_3_2_2_18_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_2_19_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Kreuzer Devin","year":"2021","unstructured":"Devin Kreuzer , Dominique Beaini , Will Hamilton , Vincent L\u00e9tourneau , and Prudencio Tossou . 2021 . Rethinking graph transformers with spectral attention . Advances in Neural Information Processing Systems , Vol. 34 (2021). Devin Kreuzer, Dominique Beaini, Will Hamilton, Vincent L\u00e9tourneau, and Prudencio Tossou. 2021. Rethinking graph transformers with spectral attention. Advances in Neural Information Processing Systems , Vol. 34 (2021)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00111"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00115"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"e_1_3_2_2_28_1","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume":"33","author":"Luo Dongsheng","year":"2020","unstructured":"Dongsheng Luo , Wei Cheng , Dongkuan Xu , Wenchao Yu , Bo Zong , Haifeng Chen , and Xiang Zhang . 2020 . Parameterized explainer for graph neural network . Advances in Neural Information Processing Systems , Vol. 33 (2020), 19620 -- 19631 . Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. 2020. Parameterized explainer for graph neural network. Advances in Neural Information Processing Systems , Vol. 33 (2020), 19620--19631.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113538"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"e_1_3_2_2_34_1","volume-title":"Computational geometry: An introduction","author":"Preparata Franco P","unstructured":"Franco P Preparata and Michael I Shamos . 2012. Computational geometry: An introduction . Springer Science & Business Media . Franco P Preparata and Michael I Shamos. 2012. Computational geometry: An introduction. Springer Science & Business Media."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"e_1_3_2_2_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren , Kaiming He , Ross Girshick , and Jian Sun . 2015 . Faster R-CNN: Towards real-time object detection with region proposal networks . Advances in Neural Information Processing Systems , Vol. 28 (2015). Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems , Vol. 28 (2015)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00208"},{"key":"e_1_3_2_2_41_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Singh Bharat","year":"2018","unstructured":"Bharat Singh , Mahyar Najibi , and Larry S Davis . 2018 . SNIPER: Efficient multi-scale training . Advances in Neural Information Processing Systems , Vol. 31 (2018). Bharat Singh, Mahyar Najibi, and Larry S Davis. 2018. SNIPER: Efficient multi-scale training. Advances in Neural Information Processing Systems , Vol. 31 (2018)."},{"key":"e_1_3_2_2_42_1","volume-title":"Graph structure learning with variational information bottleneck. arXiv preprint arXiv:2112.08903","author":"Sun Qingyun","year":"2021","unstructured":"Qingyun Sun , Jianxin Li , Hao Peng , Jia Wu , Xingcheng Fu , Cheng Ji , and Philip S Yu. 2021. Graph structure learning with variational information bottleneck. arXiv preprint arXiv:2112.08903 ( 2021 ). Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Xingcheng Fu, Cheng Ji, and Philip S Yu. 2021. Graph structure learning with variational information bottleneck. arXiv preprint arXiv:2112.08903 (2021)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00052"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 5th Conference on Robot Learning. PMLR, 1475--1485","author":"Wang Tai","year":"2022","unstructured":"Tai Wang , ZHU Xinge , Jiangmiao Pang , and Dahua Lin . 2022 b. Probabilistic and geometric depth: Detecting objects in perspective . In Proceedings of the 5th Conference on Robot Learning. PMLR, 1475--1485 . Tai Wang, ZHU Xinge, Jiangmiao Pang, and Dahua Lin. 2022b. Probabilistic and geometric depth: Detecting objects in perspective. In Proceedings of the 5th Conference on Robot Learning. PMLR, 1475--1485."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403177"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the 5th 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 a. DETR3D: 3D object detection from multi-view images via 3d-to-2d queries . In Proceedings of the 5th Conference on Robot Learning. PMLR, 180--191 . Yue Wang, Vitor Campagnolo Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, and Justin Solomon. 2022a. DETR3D: 3D object detection from multi-view images via 3d-to-2d queries. In Proceedings of the 5th Conference on Robot Learning. PMLR, 180--191."},{"key":"e_1_3_2_2_51_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Wang Yue","year":"2021","unstructured":"Yue Wang and Justin M Solomon . 2021 . Object DGCNN: 3D Object Detection using Dynamic Graphs . Advances in Neural Information Processing Systems , Vol. 34 (2021). Yue Wang and Justin M Solomon. 2021. Object DGCNN: 3D Object Detection using Dynamic Graphs. Advances in Neural Information Processing Systems , Vol. 34 (2021)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"e_1_3_2_2_53_1","volume-title":"Pseudo-LiDAR: Accurate depth for 3D object detection in autonomous driving. arXiv preprint arXiv:1906.06310","author":"You Yurong","year":"2019","unstructured":"Yurong You , Yan Wang , Wei-Lun Chao , Divyansh Garg , Geoff Pleiss , Bharath Hariharan , Mark Campbell , and Kilian Q Weinberger . 2019. Pseudo-LiDAR: Accurate depth for 3D object detection in autonomous driving. arXiv preprint arXiv:1906.06310 ( 2019 ). Yurong You, Yan Wang, Wei-Lun Chao, Divyansh Garg, Geoff Pleiss, Bharath Hariharan, Mark Campbell, and Kilian Q Weinberger. 2019. Pseudo-LiDAR: Accurate depth for 3D object detection in autonomous driving. arXiv preprint arXiv:1906.06310 (2019)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16600"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"e_1_3_2_2_56_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 ). 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)."},{"key":"e_1_3_2_2_57_1","volume-title":"Deep graph structure learning for robust representations: A survey. arXiv preprint arXiv:2103.03036","author":"Zhu Yanqiao","year":"2021","unstructured":"Yanqiao Zhu , Weizhi Xu , Jinghao Zhang , Qiang Liu , Shu Wu , and Liang Wang . 2021. Deep graph structure learning for robust representations: A survey. arXiv preprint arXiv:2103.03036 ( 2021 ).io Yanqiao Zhu, Weizhi Xu, Jinghao Zhang, Qiang Liu, Shu Wu, and Liang Wang. 2021. Deep graph structure learning for robust representations: A survey. arXiv preprint arXiv:2103.03036 (2021).io"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547859","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:35Z","timestamp":1750186955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547859"}},"subtitle":["Rethinking Overlapping Regions for Multi-View 3D Object Detection"],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":57,"alternative-id":["10.1145\/3503161.3547859","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547859","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}