{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:13:58Z","timestamp":1785420838487,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":40,"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\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100017582","name":"Beijing National Research Center For Information Science And Technology","doi-asserted-by":"publisher","award":["BNR2023RC01003, BNR2023TD03006"],"award-info":[{"award-number":["BNR2023RC01003, BNR2023TD03006"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0106300"],"award-info":[{"award-number":["2020AAA0106300"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222209, 62250008, 62102222"],"award-info":[{"award-number":["62222209, 62250008, 62102222"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M751688"],"award-info":[{"award-number":["2024M751688"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20240827"],"award-info":[{"award-number":["GZC20240827"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681151","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"7600-7608","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["U2UData: A Large-scale Cooperative Perception Dataset for Swarm UAVs Autonomous Flight"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4734-5607","authenticated-orcid":false,"given":"Tongtong","family":"Feng","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7463-2252","authenticated-orcid":false,"given":"Feilin","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Film and Television Technology, Beijing Film Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1769-6335","authenticated-orcid":false,"given":"Leping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Film and Television Technology, Beijing Film Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612156"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00058"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612465"},{"key":"e_1_3_2_1_4_1","unstructured":"DigitalOcean. [n. d.]. FlightGear. https:\/\/www.flightgear.org\/."},{"key":"e_1_3_2_1_5_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_6_1","unstructured":"FEISILAB. [n. d.]. RflySim. https:\/\/rflysim.com\/doc\/zh\/."},{"key":"e_1_3_2_1_7_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_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00892"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613812"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304562"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192802"},{"key":"e_1_3_2_1_12_1","first-page":"29541","article-title":"Learning distilled collaboration graph for multi-agent perception","volume":"34","author":"Li Yiming","year":"2021","unstructured":"Yiming Li, Shunli Ren, Pengxiang Wu, Siheng Chen, Chen Feng, and Wenjun Zhang. 2021. Learning distilled collaboration graph for multi-agent perception. Advances in Neural Information Processing Systems, Vol. 34 (2021), 29541--29552.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"Beom Jin Kim, and et al","author":"Liao Fuyou","year":"2022","unstructured":"Fuyou Liao, Zheng Zhou, Beom Jin Kim, and et al. 2022. Bioinspired in-sensor visual adaptation for accurate perception. In Nature Electronics. 84--91."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612425"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611831"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00416"},{"key":"e_1_3_2_1_17_1","volume-title":"An Extensible Framework for Open Heterogeneous Collaborative Perception. The Twelfth International Conference on Learning Representations","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. The Twelfth International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_18_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_19_1","unstructured":"NVIDIA. [n. d.]. Isaac Sim. https:\/\/developer.nvidia.com\/isaac-sim."},{"key":"e_1_3_2_1_20_1","unstructured":"PX4. [n. d.]. Jmavsim. https:\/\/docs.px4.io\/main\/en\/sim_jmavsim\/."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569832"},{"key":"e_1_3_2_1_22_1","unstructured":"Laminar Research. [n. d.]. XPlan. https:\/\/www.x-plane.com\/."},{"key":"e_1_3_2_1_23_1","unstructured":"Open Robotics. [n. d.]. Gazebo. https:\/\/gazebosim.org\/home."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"e_1_3_2_1_25_1","volume-title":"UAV-Ground Visual Tracking: A Unified Dataset and Collaborative Learning Approach","author":"Sun Dengdi","year":"2023","unstructured":"Dengdi Sun, Leilei Cheng, Song Chen, Chenglong Li, Yun Xiao, and Bin Luo. 2023. UAV-Ground Visual Tracking: A Unified Dataset and Collaborative Learning Approach. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_26_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. 605--621."},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wei Sizhe","year":"2024","unstructured":"Sizhe Wei, Yuxi Wei, Yue Hu, Yifan Lu, Yiqi Zhong, Siheng Chen, and Ya Zhang. 2024. Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"e_1_3_2_1_29_1","volume-title":"UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization. arXiv preprint arXiv:2401.05971","author":"Wu Rouwan","year":"2024","unstructured":"Rouwan Wu, Xiaoya Cheng, Juelin Zhu, Xuxiang Liu, Maojun Zhang, and Shen Yan. 2024. UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization. arXiv preprint arXiv:2401.05971 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564825"},{"key":"e_1_3_2_1_31_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_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611843"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00531"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811956"},{"key":"e_1_3_2_1_39_1","volume-title":"BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities. arXiv preprint arXiv:2310.14702","author":"Zhao Binyu","year":"2023","unstructured":"Binyu Zhao, Wei Zhang, and Zhaonian Zou. 2023. BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities. arXiv preprint arXiv:2310.14702 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612346"}],"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\/3664647.3681151","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3664647.3681151","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681151","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"}}]}}