{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T21:25:08Z","timestamp":1762205108289,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3728482.3757394","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T21:21:35Z","timestamp":1762204895000},"page":"1-3","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4169-1595","authenticated-orcid":false,"given":"Tingyu","family":"Wang","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6028-9051","authenticated-orcid":false,"given":"Yujiao","family":"Shi","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4511-4223","authenticated-orcid":false,"given":"Fabian","family":"Deuser","sequence":"additional","affiliation":[{"name":"University of the Bundeswehr Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8996-9907","authenticated-orcid":false,"given":"Shaofei","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9448-9892","authenticated-orcid":false,"given":"Guosheng","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2434-9050","authenticated-orcid":false,"given":"Zhedong","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7410-2590","authenticated-orcid":false,"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"YuanQiang Cai Dawei Du Libo Zhang Longyin Wen Weiqiang Wang Yanjun Wu and Siwei Lyu. 2020. Guided attention network for object detection and counting on drones. In ACM Multimedia.","DOI":"10.1145\/3394171.3413816"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Meng Chu Zhedong Zheng Wei Ji Tingyu Wang and Tat-Seng Chua. 2024. Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatially Relation Matching. In ECCV.","DOI":"10.1007\/978-3-031-73247-8_13"},{"key":"e_1_3_2_1_3_1","volume-title":"Path-Analysis-Based Reinforcement Learning Algorithm for Imitation Filming. TMM","author":"Dang Yuanjie","year":"2022","unstructured":"Yuanjie Dang, Chong Huang, Peng Chen, Ronghua Liang, Xin Yang, and Kwang- Ting Cheng. 2022. Path-Analysis-Based Reinforcement Learning Algorithm for Imitation Filming. TMM (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Awantha Jayasiri, and George KI Mann.","author":"Dissanayaka Didula","year":"2023","unstructured":"Didula Dissanayaka, Thumeera R Wanasinghe, Oscar De Silva, Awantha Jayasiri, and George KI Mann. 2023. Review of Navigation Methods for UAV-Based Parcel Delivery. TASE (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Tzu-Yi Fan Fangqi Liu Jia-Wei Fang Nalini Venkatasubramanian and Cheng-Hsin Hsu. 2022. Enhancing situational awareness with adaptive firefighting drones: leveraging diverse media types and classifiers. In ACM Multimedia.","DOI":"10.1145\/3524273.3532910"},{"key":"e_1_3_2_1_6_1","volume-title":"Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark. arXiv:2212.09381","author":"Fang Jianwu","year":"2022","unstructured":"Jianwu Fang, Lei-Lei Li, Kuan Yang, Zhedong Zheng, Jianru Xue, and Tat-Seng Chua. 2022. Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark. arXiv:2212.09381 (2022)."},{"key":"e_1_3_2_1_7_1","volume-title":"Ana Claudia Arias, and Tarek Zohdi","author":"Goodrich Payton","year":"2023","unstructured":"Payton Goodrich, Omar Betancourt, Ana Claudia Arias, and Tarek Zohdi. 2023. Placement and drone flight path mapping of agricultural soil sensors using machine learning. Computers and Electronics in Agriculture (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Anomaly Detection in Aerial Videos With Transformers. TGRS","author":"Jin Pu","year":"2022","unstructured":"Pu Jin, Lichao Mou, Gui-Song Xia, and Xiao Xiang Zhu. 2022. Anomaly Detection in Aerial Videos With Transformers. TGRS (2022)."},{"key":"e_1_3_2_1_9_1","unstructured":"Hao Ju Shaofei Huang Si Liu and Zhedong Zheng. 2024. Video2bev: Transforming drone videos to bevs for video-based geo-localization. In ICCV."},{"key":"e_1_3_2_1_10_1","volume-title":"Uav-human: A large benchmark for human behavior understanding with unmanned aerial vehicles. In CVPR.","author":"Li Tianjiao","year":"2021","unstructured":"Tianjiao Li, Jun Liu, Wei Zhang, Yun Ni, Wenqian Wang, and Zhiheng Li. 2021. Uav-human: A large benchmark for human behavior understanding with unmanned aerial vehicles. In CVPR."},{"key":"e_1_3_2_1_11_1","volume-title":"Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization. TIP","author":"Lin Jinliang","year":"2022","unstructured":"Jinliang Lin, Zhedong Zheng, Zhun Zhong, Zhiming Luo, Shaozi Li, Yi Yang, and Nicu Sebe. 2022. Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization. TIP (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Liu Liu and Hongdong Li. 2019. Lending orientation to neural networks for cross-view geo-localization. In CVPR.","DOI":"10.1109\/CVPR.2019.00577"},{"key":"e_1_3_2_1_13_1","volume-title":"Guanlin Chen, Yu Wang, Qinghua Hu, and Pengfei Zhu.","author":"Liu Zhihao","year":"2023","unstructured":"Zhihao Liu, Yuanyuan Shang, Timing Li, Guanlin Chen, Yu Wang, Qinghua Hu, and Pengfei Zhu. 2023. Robust Multi-Drone Multi-Target Tracking to Resolve Target Occlusion: A Benchmark. TMM (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Ioannis Pitas and Ioannis Mademlis. 2022. Autonomous UAV Cinematography. In ACM Multimedia.","DOI":"10.1145\/3503161.3546970"},{"key":"e_1_3_2_1_15_1","volume-title":"Fundamental research on unmanned aerial vehicles to support precision agriculture in oil palm plantations. Agricultural Robots-Fundamentals and Application","author":"Shamshiri Redmond Ramin","year":"2018","unstructured":"Redmond Ramin Shamshiri, Ibrahim A Hameed, Siva K Balasundram, Desa Ahmad, Cornelia Weltzien, and Muhammad Yamin. 2018. Fundamental research on unmanned aerial vehicles to support precision agriculture in oil palm plantations. Agricultural Robots-Fundamentals and Application (2018)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3188913"},{"key":"e_1_3_2_1_17_1","volume-title":"Xin Yu, and Hongdong Li.","author":"Shi Yujiao","year":"2022","unstructured":"Yujiao Shi, Dylan John Campbell, Xin Yu, and Hongdong Li. 2022. Geometryguided street-view panorama synthesis from satellite imagery. TPAMI (2022)."},{"key":"e_1_3_2_1_18_1","unstructured":"Yujiao Shi and Hongdong Li. 2022. Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image. In CVPR."},{"key":"e_1_3_2_1_19_1","unstructured":"Yujiao Shi Liu Liu Xin Yu and Hongdong Li. 2019. Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization. In NeurIPS."},{"key":"e_1_3_2_1_20_1","unstructured":"Yujiao Shi FeiWu Akhil Perincherry Ankit Vora and Hongdong Li. 2023. Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry- Guided Cross-View Transformer. In ICCV."},{"key":"e_1_3_2_1_21_1","unstructured":"Yujiao Shi Xin Yu Dylan Campbell and Hongdong Li. 2020. Where am I looking at? joint location and orientation estimation by cross-view matching. In CVPR."},{"key":"e_1_3_2_1_22_1","volume-title":"Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching. TPAMI","author":"Shi Yujiao","year":"2022","unstructured":"Yujiao Shi, Xin Yu, Liu Liu, Dylan Campbell, Piotr Koniusz, and Hongdong Li. 2022. Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching. TPAMI (2022)."},{"key":"e_1_3_2_1_23_1","unstructured":"Yujiao Shi Xin Yu Liu Liu Tong Zhang and Hongdong Li. 2020. Optimal feature transport for cross-view image geo-localization. In AAAI."},{"key":"e_1_3_2_1_24_1","unstructured":"Yujiao Shi Xin Yu ShanWang and Hongdong Li. 2022. CVLNet: Cross-View Feature Correspondence Learning for Video-based Camera Localization. In ACCV."},{"key":"e_1_3_2_1_25_1","unstructured":"Zhenbo Song Xianghui Ze Jianfeng Lu and Yujiao Shi. 2023. Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization. In NIPS."},{"key":"e_1_3_2_1_26_1","volume-title":"How the Wind Can Be Leveraged for Saving Energy in a Truck-Drone Delivery System. TITS","author":"Sorbelli Francesco Betti","year":"2023","unstructured":"Francesco Betti Sorbelli, Federico Cor\u00f2, Lorenzo Palazzetti, Cristina M Pinotti, and Giulio Rigoni. 2023. How the Wind Can Be Leveraged for Saving Energy in a Truck-Drone Delivery System. TITS (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Dualpyramidal image inpainting with dynamic normalization. TCSVT","author":"Wang Chao","year":"2022","unstructured":"Chao Wang, Mingwen Shao, Deyu Meng, and Wangmeng Zuo. 2022. Dualpyramidal image inpainting with dynamic normalization. TCSVT (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"ChaoWang Zhedong Zheng Ruijie Quan Yifan Sun and Yi Yang. 2023. Context-Aware Pretraining for Efficient Blind Image Decomposition. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01744"},{"key":"e_1_3_2_1_29_1","volume-title":"Multiple-environment Self-adaptive Network for Aerial-view Geo-localization. Pattern Recognition","author":"Wang Tingyu","year":"2024","unstructured":"Tingyu Wang, Zhedong Zheng, Yaoqi Sun, Tat-Seng Chua, Yi Yang, and Chenggang Yan. 2024. Multiple-environment Self-adaptive Network for Aerial-view Geo-localization. Pattern Recognition (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Each part matters: Local patterns facilitate cross-view geo-localization. TCSVT","author":"Wang Tingyu","year":"2022","unstructured":"Tingyu Wang, Zhedong Zheng, Chenggang Yan, Jiyong Zhang, Yaoqi Sun, Bolun Zheng, and Yi Yang. 2022. Each part matters: Local patterns facilitate cross-view geo-localization. TCSVT (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization. TGRS","author":"Wang Tingyu","year":"2024","unstructured":"Tingyu Wang, Zhedong Zheng, Zunjie Zhu, Yaoqi Sun, Yi Yang, and Chenggang Yan. 2024. Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization. TGRS (2024)."},{"key":"e_1_3_2_1_32_1","unstructured":"Longyin Wen Dawei Du Pengfei Zhu Qinghua Hu Qilong Wang Liefeng Bo and Siwei Lyu. 2021. Detection tracking and counting meets drones in crowds: A benchmark. In CVPR."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Haotian Zhang Gaoang Wang Zhichao Lei and Jenq-Neng Hwang. 2019. Eye in the sky: Drone-based object tracking and 3d localization. In ACM Multimedia.","DOI":"10.1145\/3343031.3350933"},{"key":"e_1_3_2_1_34_1","volume-title":"MS-YOLOv7: YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography. Drones","author":"Zhao LiangLiang","year":"2023","unstructured":"LiangLiang Zhao and MinLing Zhu. 2023. MS-YOLOv7: YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography. Drones (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety Oriented Research and Digital Twins. arXiv:2208.11036","author":"Zheng Ou","year":"2022","unstructured":"Ou Zheng, Mohamed Abdel-Aty, Lishengsa Yue, Amr Abdelraouf, Zijin Wang, and Nada Mahmoud. 2022. CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety Oriented Research and Digital Twins. arXiv:2208.11036 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"The 2nd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective. In Proceedings of the 32nd ACM International Conference on Multimedia Workshop.","author":"Zheng Zhedong","year":"2024","unstructured":"Zhedong Zheng, Yujiao Shi, TingyuWang, Chen Chen, Pengfei Zhu, and Richard Hartley. 2024. The 2nd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective. In Proceedings of the 32nd ACM International Conference on Multimedia Workshop."},{"key":"e_1_3_2_1_37_1","volume-title":"UAVM'23: 2023 Workshop on UAVs in Multimedia: Capturing the World from a New Perspective. In Proceedings of the 31st ACM International Conference on Multimedia. 9715--9717","author":"Zheng Zhedong","year":"2023","unstructured":"Zhedong Zheng, Yujiao Shi, Tingyu Wang, Jun Liu, Jianwu Fang, Yunchao Wei, and Tat-seng Chua. 2023. UAVM'23: 2023 Workshop on UAVs in Multimedia: Capturing the World from a New Perspective. In Proceedings of the 31st ACM International Conference on Multimedia. 9715--9717."},{"key":"e_1_3_2_1_38_1","unstructured":"Zhedong Zheng Yunchao Wei and Yi Yang. 2020. University-1652: A multi-view multi-source benchmark for drone-based geo-localization. In ACM Multimedia."},{"key":"e_1_3_2_1_39_1","volume-title":"Unsupervised scene adaptation with memory regularization in vivo. IJCAI","author":"Zheng Zhedong","year":"2019","unstructured":"Zhedong Zheng and Yi Yang. 2019. Unsupervised scene adaptation with memory regularization in vivo. IJCAI (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195642"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 3rd International Workshop on UAVs in Multimedia: Capturing the World from a New Perspective"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3728482.3757394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T21:21:58Z","timestamp":1762204918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728482.3757394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":40,"alternative-id":["10.1145\/3728482.3757394","10.1145\/3728482"],"URL":"https:\/\/doi.org\/10.1145\/3728482.3757394","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-11-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}