{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:33:01Z","timestamp":1778257981786,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"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"}],"funder":[{"name":"National Natural Science Foundation of China Grant","award":["12071478, 61972404"],"award-info":[{"award-number":["12071478, 61972404"]}]},{"name":"China Scholarship Council award"},{"name":"Public Computing Cloud and the Blockchain Lab, School of Information, Renmin University of China"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680559","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"7833-7842","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["RoCo: Robust Cooperative Perception By Iterative Object Matching and Pose Adjustment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7656-1298","authenticated-orcid":false,"given":"Zhe","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-1646","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4197-2258","authenticated-orcid":false,"given":"Yongcai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0092-7020","authenticated-orcid":false,"given":"Wanting","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7748-5427","authenticated-orcid":false,"given":"Deying","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0961-0441","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Wollongong, Wollongong, NSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Eduardo Arnold Omar Y Al-Jarrah Mehrdad Dianati Saber Fallah David Oxtoby and Alexandros Mouzakitis. 2021. Data for Cooperative object classification for driving applications. (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915596589"},{"key":"e_1_3_2_1_3_1","volume-title":"The SLAM problem: a survey. Artificial Intelligence Research and Development","author":"Aulinas Josep","year":"2008","unstructured":"Josep Aulinas, Yvan Petillot, Joaquim Salvi, and Xavier Llad\u00f3. 2008. The SLAM problem: a survey. Artificial Intelligence Research and Development (2008), 363--371."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-022-01306-w"},{"key":"e_1_3_2_1_5_1","first-page":"3255","article-title":"Multiple hypothesis semantic mapping for robust data association","volume":"4","author":"Bernreiter Lukas","year":"2019","unstructured":"Lukas Bernreiter, Abel Gawel, Hannes Sommer, Juan Nieto, Roland Siegwart, and Cesar Cadena Lerma. 2019. Multiple hypothesis semantic mapping for robust data association. IEEE Robotics and Automation Letters, Vol. 4, 4 (2019), 3255--3262.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"e_1_3_2_1_8_1","volume-title":"VOLoc: Visual Place Recognition by Querying Compressed Lidar Map. arXiv preprint arXiv:2402.15961","author":"Cai Xudong","year":"2024","unstructured":"Xudong Cai, Yongcai Wang, Zhe Huang, Yu Shao, and Deying Li. 2024. VOLoc: Visual Place Recognition by Querying Compressed Lidar Map. arXiv preprint arXiv:2402.15961 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363300"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2984780"},{"key":"e_1_3_2_1_11_1","volume-title":"Conference on robot learning. PMLR, 1--16","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Conference on robot learning. PMLR, 1--16."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636761"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636761"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611880"},{"key":"e_1_3_2_1_15_1","series-title":"SIAM Journal on computing","volume-title":"An n^5\/2 algorithm for maximum matchings in bipartite graphs","author":"Hopcroft John E","year":"1973","unstructured":"John E Hopcroft and Richard M Karp. 1973. An n^5\/2 algorithm for maximum matchings in bipartite graphs. SIAM Journal on computing, Vol. 2, 4 (1973), 225--231."},{"key":"e_1_3_2_1_16_1","volume-title":"Where2comm: Communication-efficient collaborative perception via spatial confidence maps. Advances in neural information processing systems","author":"Hu Yue","year":"2022","unstructured":"Yue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong, and Siheng Chen. 2022. Where2comm: Communication-efficient collaborative perception via spatial confidence maps. Advances in neural information processing systems, Vol. 35 (2022), 4874--4886."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3245421"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191728"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.101971"},{"key":"e_1_3_2_1_20_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 (2014)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611948"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_1_23_1","volume-title":"A method for the solution of certain non-linear problems in least squares. Quarterly of applied mathematics","author":"Levenberg Kenneth","year":"1944","unstructured":"Kenneth Levenberg. 1944. A method for the solution of certain non-linear problems in least squares. Quarterly of applied mathematics, Vol. 2, 2 (1944), 164--168."},{"key":"e_1_3_2_1_24_1","volume-title":"Among us: Adversarially robust collaborative perception by consensus. arXiv preprint arXiv:2303.09495","author":"Li Yiming","year":"2023","unstructured":"Yiming Li, Qi Fang, Jiamu Bai, Siheng Chen, Felix Juefei-Xu, and Chen Feng. 2023. Among us: Adversarially robust collaborative perception by consensus. arXiv preprint arXiv:2303.09495 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192802"},{"key":"e_1_3_2_1_26_1","volume-title":"Conference on Robot Learning. PMLR","author":"Li Yiming","year":"2023","unstructured":"Yiming Li, Juexiao Zhang, Dekun Ma, Yue Wang, and Chen Feng. 2023. Multi-robot scene completion: Towards task-agnostic collaborative perception. In Conference on Robot Learning. PMLR, 2062--2072."},{"key":"e_1_3_2_1_27_1","volume-title":"An Extensible Framework for Open Heterogeneous Collaborative Perception. arXiv preprint arXiv:2401.13964","author":"Lu Yifan","year":"2024","unstructured":"Yifan Lu, Yue Hu, Yiqi Zhong, Dequan Wang, Siheng Chen, and Yanfeng Wang. 2024. An Extensible Framework for Open Heterogeneous Collaborative Perception. arXiv preprint arXiv:2401.13964 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160546"},{"key":"e_1_3_2_1_29_1","volume-title":"CoBEVFusion: Cooperative Perception with LiDAR-Camera Bird's-Eye View Fusion. arXiv preprint arXiv:2310.06008","author":"Qiao Donghao","year":"2023","unstructured":"Donghao Qiao and Farhana Zulkernine. 2023. CoBEVFusion: Cooperative Perception with LiDAR-Camera Bird's-Eye View Fusion. arXiv preprint arXiv:2310.06008 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"SyncNet: Using Causal Convolutions and Correlating Objective for Time Delay Estimation in Audio Signals. arXiv preprint arXiv:2203.14639","author":"Raina Akshay","year":"2022","unstructured":"Akshay Raina and Vipul Arora. 2022. SyncNet: Using Causal Convolutions and Correlating Objective for Time Delay Estimation in Audio Signals. arXiv preprint arXiv:2203.14639 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0926-5805(00)00106-0"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177853"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1186\/s41074-017-0027-2"},{"key":"e_1_3_2_1_34_1","volume-title":"DL-SLOT: Dynamic LiDAR SLAM and object tracking based on collaborative graph optimization. arXiv preprint arXiv:2212.02077","author":"Tian Xuebo","year":"2022","unstructured":"Xuebo Tian, Zhongyang Zhu, Junqiao Zhao, Gengxuan Tian, and Chen Ye. 2022. DL-SLOT: Dynamic LiDAR SLAM and object tracking based on collaborative graph optimization. arXiv preprint arXiv:2212.02077 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Conference on Robot Learning. PMLR, 1195--1210","author":"Vadivelu Nicholas","year":"2021","unstructured":"Nicholas Vadivelu, Mengye Ren, James Tu, Jingkang Wang, and Raquel Urtasun. 2021. Learning to communicate and correct pose errors. In Conference on Robot Learning. PMLR, 1195--1210."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00143"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242708"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23052399"},{"key":"e_1_3_2_1_39_1","volume-title":"UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework. arXiv preprint arXiv:2303.12400","author":"Wang Tianhang","year":"2023","unstructured":"Tianhang Wang, Guang Chen, Kai Chen, Zhengfa Liu, Bo Zhang, Alois Knoll, and Changjun Jiang. 2023. UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework. arXiv preprint arXiv:2303.12400 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings, Part II 16","author":"Wang Tsun-Hsuan","year":"2020","unstructured":"Tsun-Hsuan Wang, Sivabalan Manivasagam, Ming Liang, Bin Yang, Wenyuan Zeng, and Raquel Urtasun. 2020. V2vnet: Vehicle-to-vehicle communication for joint perception and prediction. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part II 16. Springer, 605--621."},{"key":"e_1_3_2_1_41_1","volume-title":"Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow. arXiv e-prints","author":"Wei Sizhe","year":"2023","unstructured":"Sizhe Wei, Yuxi Wei, Yue Hu, Yifan Lu, Yiqi Zhong, Siheng Chen, and Ya Zhang. 2023. Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow. arXiv e-prints (2023), arXiv--2309."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161384"},{"key":"e_1_3_2_1_43_1","volume-title":"DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection. arXiv preprint arXiv:2312.15742","author":"Xiang Li","year":"2023","unstructured":"Li Xiang, Junbo Yin, Wei Li, Cheng-Zhong Xu, Ruigang Yang, and Jianbing Shen. 2023. DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection. arXiv preprint arXiv:2312.15742 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"CoBEVT: Cooperative bird's eye view semantic segmentation with sparse transformers. arXiv preprint arXiv:2207.02202","author":"Xu Runsheng","year":"2022","unstructured":"Runsheng Xu, Zhengzhong Tu, Hao Xiang, Wei Shao, Bolei Zhou, and Jiaqi Ma. 2022. CoBEVT: Cooperative bird's eye view semantic segmentation with sparse transformers. arXiv preprint arXiv:2207.02202 (2022)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611699"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143299"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143299"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982280"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2011.2170414"},{"key":"e_1_3_2_1_54_1","volume-title":"LIMOT: A Tightly-Coupled System for LiDAR-Inertial Odometry and Multi-Object Tracking. arXiv preprint arXiv:2305.00406","author":"Zhu Zhongyang","year":"2023","unstructured":"Zhongyang Zhu, Junqiao Zhao, Xuebo Tian, Kai Huang, and Chen Ye. 2023. LIMOT: A Tightly-Coupled System for LiDAR-Inertial Odometry and Multi-Object Tracking. arXiv preprint arXiv:2305.00406 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2019.09.002"}],"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\/3664647.3680559","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:45Z","timestamp":1750291425000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680559"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":55,"alternative-id":["10.1145\/3664647.3680559","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680559","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"}}]}}