{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T14:10:31Z","timestamp":1771683031196,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372155"],"award-info":[{"award-number":["62372155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Qinglan Project of Jiangsu Province"},{"name":"Changzhou Science and Technology Bureau Project","award":["20231313"],"award-info":[{"award-number":["20231313"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758220","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12792-12798","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["UEMM-Air: Enable UAVs to Undertake More Multi-modal Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4588-3658","authenticated-orcid":false,"given":"Liang","family":"Yao","sequence":"first","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8746-9845","authenticated-orcid":false,"given":"Fan","family":"Liu","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4964-8406","authenticated-orcid":false,"given":"Shengxiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8724-5796","authenticated-orcid":false,"given":"Chuanyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7394-0082","authenticated-orcid":false,"given":"Shimin","family":"Di","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7059-2317","authenticated-orcid":false,"given":"Xing","family":"Ma","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4053-6227","authenticated-orcid":false,"given":"Jianyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3031-0848","authenticated-orcid":false,"given":"Zequan","family":"Wang","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5822-8233","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Griffith University, Nathan, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.31893\/multirev.2024118"},{"key":"e_1_3_2_1_2_1","volume-title":"Au-air: A multi-modal unmanned aerial vehicle dataset for low altitude traffic surveillance. In ICRA.","author":"Bozcan Ilker","year":"2020","unstructured":"Ilker Bozcan and Erdal Kayacan. 2020. Au-air: A multi-modal unmanned aerial vehicle dataset for low altitude traffic surveillance. In ICRA."},{"key":"e_1_3_2_1_3_1","volume-title":"Multi-Temporal Earth Observation Imagery. In ICLR Workshop on Machine Learning for Remote Sensing (ML4RS).","author":"Brown Christopher","year":"2024","unstructured":"Christopher Brown, Michal Kazmierski, William Rucklidge, Valerie Pasquarella, and Evan Shelhamer. 2024. Learned Embedding Fields for Multi-Source, Multi-Temporal Earth Observation Imagery. In ICLR Workshop on Machine Learning for Remote Sensing (ML4RS)."},{"key":"e_1_3_2_1_4_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_5_1","first-page":"370","article-title":"The unmanned aerial vehicle benchmark: Object detection and tracking","author":"Du Dawei","year":"2018","unstructured":"Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, and Qi Tian. 2018. The unmanned aerial vehicle benchmark: Object detection and tracking. In ECCV. 370-386.","journal-title":"ECCV."},{"key":"e_1_3_2_1_6_1","first-page":"213","article-title":"VisDrone-DET2019: The vision meets drone object detection in image challenge results","author":"Du Dawei","year":"2019","unstructured":"Dawei Du, Pengfei Zhu, Longyin Wen, Xiao Bian, Haibin Lin, Qinghua Hu, Tao Peng, Jiayu Zheng, Xinyao Wang, Yue Zhang, et al., 2019. VisDrone-DET2019: The vision meets drone object detection in image challenge results. In ICCVW. 213-226.","journal-title":"ICCVW."},{"key":"e_1_3_2_1_7_1","unstructured":"Epic Games. 2024. Unreal Engine."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104856"},{"key":"e_1_3_2_1_9_1","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou Qibin","year":"2021","unstructured":"Qibin Hou, Daquan Zhou, and Jiashi Feng. 2021. Coordinate attention for efficient mobile network design. In CVPR. 13713-13722.","journal-title":"CVPR."},{"key":"e_1_3_2_1_10_1","volume-title":"A novel weighted ensemble transferred U-net based model (WETUM) for post-earthquake building damage assessment from UAV data: A comparison of deep learning-and machine learning-based approaches. TGRS","author":"Khankeshizadeh Ehsan","year":"2024","unstructured":"Ehsan Khankeshizadeh, Ali Mohammadzadeh, Hossein Arefi, Amin Mohsenifar, Saied Pirasteh, En Fan, Huxiong Li, and Jonathan Li. 2024. A novel weighted ensemble transferred U-net based model (WETUM) for post-earthquake building damage assessment from UAV data: A comparison of deep learning-and machine learning-based approaches. TGRS (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Sahil Khose Anisha Pal Aayushi Agarwal Judy Hoffman Prithvijit Chattopadhyay et al. 2023. SkyScenes: A Synthetic Dataset for Aerial Scene Understanding. arXiv preprint arXiv:2312.06719 (2023).","DOI":"10.1007\/978-3-031-72986-7_2"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436-444."},{"key":"e_1_3_2_1_13_1","volume-title":"Remoteclip: A vision language foundation model for remote sensing. TGRS","author":"Liu Fan","year":"2024","unstructured":"Fan Liu, Delong Chen, Zhangqingyun Guan, Xiaocong Zhou, Jiale Zhu, Qiaolin Ye, Liyong Fu, and Jun Zhou. 2024a. Remoteclip: A vision language foundation model for remote sensing. TGRS (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3564261"},{"key":"e_1_3_2_1_15_1","first-page":"26658","article-title":"Rotated multi-scale interaction network for referring remote sensing image segmentation","author":"Liu Sihan","year":"2024","unstructured":"Sihan Liu, Yiwei Ma, Xiaoqing Zhang, Haowei Wang, Jiayi Ji, Xiaoshuai Sun, and Rongrong Ji. 2024b. Rotated multi-scale interaction network for referring remote sensing image segmentation. In CVPR. 26658-26668.","journal-title":"CVPR."},{"key":"e_1_3_2_1_16_1","volume-title":"DETRs beat YOLOs on real-time object detection. arXiv preprint arXiv:2304.08069","author":"Lv Wenyu","year":"2023","unstructured":"Wenyu Lv, Shangliang Xu, Yian Zhao, Guanzhong Wang, Jinman Wei, Cheng Cui, Yuning Du, Qingqing Dang, and Yi Liu. 2023. DETRs beat YOLOs on real-time object detection. arXiv preprint arXiv:2304.08069 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"UAVid: A semantic segmentation dataset for UAV imagery. ISPRS journal of photogrammetry and remote sensing","author":"Lyu Ye","year":"2020","unstructured":"Ye Lyu, George Vosselman, Gui-Song Xia, Alper Yilmaz, and Michael Ying Yang. 2020. UAVid: A semantic segmentation dataset for UAV imagery. ISPRS journal of photogrammetry and remote sensing, Vol. 165 (2020), 108-119."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104046"},{"key":"e_1_3_2_1_19_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2021.102456"},{"key":"e_1_3_2_1_21_1","volume-title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement. arXiv preprint arXiv:2410.13842","author":"Peng Yansong","year":"2024","unstructured":"Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, and Feng Wu. 2024. D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement. arXiv preprint arXiv:2410.13842 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Cheng Qian Huanxing Wu Qirui Zhang Lvshun Yang and Qi Jiang. 2022. Design and Implementation of UAV Formation Cooperative System. In ICAUS.","DOI":"10.1007\/978-981-99-0479-2_133"},{"key":"e_1_3_2_1_23_1","first-page":"4426","volume-title":"TMM","volume":"23","author":"Qiao Yanyuan","year":"2020","unstructured":"Yanyuan Qiao, Chaorui Deng, and Qi Wu. 2020. Referring expression comprehension: A survey of methods and datasets. TMM, Vol. 23 (2020), 4426-4440."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_25_1","volume-title":"RescueNet: a high resolution UAV semantic segmentation dataset for natural disaster damage assessment. Scientific data","author":"Rahnemoonfar Maryam","year":"2023","unstructured":"Maryam Rahnemoonfar, Tashnim Chowdhury, and Robin Murphy. 2023. RescueNet: a high resolution UAV semantic segmentation dataset for natural disaster damage assessment. Scientific data, Vol. 10, 1 (2023), 913."},{"key":"e_1_3_2_1_26_1","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks. NeurIPS","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. NeurIPS (2015)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Giulia Rizzoli Francesco Barbato Matteo Caligiuri and Pietro Zanuttigh. 2023a. SynDrone-Multi-Modal UAV Dataset for Urban Scenarios. In ICCV.","DOI":"10.1109\/ICCVW60793.2023.00235"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"G. Rizzoli F. Barbato M. Caligiuri and P. Zanuttigh. 2023b. SynDrone - Multi-modal UAV Dataset for Urban Scenarios. In ICCVW.","DOI":"10.1109\/ICCVW60793.2023.00235"},{"key":"e_1_3_2_1_29_1","unstructured":"Shital Shah Debadeepta Dey Chris Lovett and Ashish Kapoor. 2017. AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles. In Field and Service Robotics. showeprintarXiv:1705.05065 https:\/\/arxiv.org\/abs\/1705.05065"},{"key":"e_1_3_2_1_30_1","first-page":"8135","volume-title":"TNNLS","volume":"34","author":"Song Hwanjun","year":"2022","unstructured":"Hwanjun Song, Minseok Kim, Dongmin Park, Yooju Shin, and Jae-Gil Lee. 2022. Learning from noisy labels with deep neural networks: A survey. TNNLS, Vol. 34, 11 (2022), 8135-8153."},{"key":"e_1_3_2_1_31_1","volume-title":"Techniques, answers, and real-world UAV implementations for precision farming. WPC","author":"Srivastava Ashish","year":"2023","unstructured":"Ashish Srivastava and Jay Prakash. 2023. Techniques, answers, and real-world UAV implementations for precision farming. WPC (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"AI meets UAVs: A survey on AI empowered UAV perception systems for precision agriculture. Neurocomputing","author":"Su Jinya","year":"2023","unstructured":"Jinya Su, Xiaoyong Zhu, Shihua Li, and Wen-Hua Chen. 2023. AI meets UAVs: A survey on AI empowered UAV perception systems for precision agriculture. Neurocomputing (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"e_1_3_2_1_34_1","volume-title":"Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning. TCSVT","author":"Sun Yiming","year":"2022","unstructured":"Yiming Sun, Bing Cao, Pengfei Zhu, and Qinghua Hu. 2022b. Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning. TCSVT (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02066-6"},{"key":"e_1_3_2_1_36_1","unstructured":"Ultralytics. 2024. Ultralytics yolov11. In https:\/\/docs.ultralytics.com."},{"key":"e_1_3_2_1_37_1","unstructured":"Chien-Yao Wang Alexey Bochkovskiy and Hong-Yuan Mark Liao. 2023. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In CVPR."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3275068"},{"key":"e_1_3_2_1_39_1","volume-title":"Towards robust referring image segmentation. TIP","author":"Wu Jianzong","year":"2024","unstructured":"Jianzong Wu, Xiangtai Li, Xia Li, Henghui Ding, Yunhai Tong, and Dacheng Tao. 2024. Towards robust referring image segmentation. TIP (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Deep learning for unmanned aerial vehicle-based object detection and tracking: A survey","author":"Wu Xin","year":"2021","unstructured":"Xin Wu, Wei Li, Danfeng Hong, Ran Tao, and Qian Du. 2021. Deep learning for unmanned aerial vehicle-based object detection and tracking: A survey. IEEE GRSM (2021)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.3390\/app132011320"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220219"},{"key":"e_1_3_2_1_43_1","first-page":"18155","article-title":"Lavt: Language-aware vision transformer for referring image segmentation","author":"Yang Zhao","year":"2022","unstructured":"Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, and Philip HS Torr. 2022b. Lavt: Language-aware vision transformer for referring image segmentation. In CVPR. 18155-18165.","journal-title":"CVPR."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Liang Yao Fan Liu Delong Chen Chuanyi Zhang Yijun Wang Ziyun Chen Wei Xu Shimin Di and Yuhui Zheng. 2025. RemoteSAM: Towards Segment Anything for Earth Observation. arXiv:2505.18022 [cs.CV] https:\/\/arxiv.org\/abs\/2505.18022","DOI":"10.1145\/3746027.3754950"},{"key":"e_1_3_2_1_45_1","volume-title":"A survey on multimodal large language models. arXiv preprint arXiv:2306.13549","author":"Yin Shukang","year":"2023","unstructured":"Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2023. A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12020221"},{"key":"e_1_3_2_1_47_1","volume-title":"Empowering Physical Attacks with Jacobian Matrix Regularization against ViT-based Detectors in UAV Remote Sensing Images. TGRS","author":"Zhang Yu","year":"2024","unstructured":"Yu Zhang, Zhiqiang Gong, Wenlin Liu, Hao Wen, Pengcheng Wan, Jiahao Qi, Xikun Hu, and Ping Zhong. 2024. Empowering Physical Attacks with Jacobian Matrix Regularization against ViT-based Detectors in UAV Remote Sensing Images. TGRS (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Detrs beat yolos on real-time object detection. arXiv preprint arXiv:2304.08069","author":"Zhao Yian","year":"2023","unstructured":"Yian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei, Guanzhong Wang, Qingqing Dang, Yi Liu, and Jie Chen. 2023. Detrs beat yolos on real-time object detection. arXiv preprint arXiv:2304.08069 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"A review of UAV Visual Detection and Tracking Methods. arXiv preprint arXiv:2306.05089","author":"Zitar Raed Abu","year":"2023","unstructured":"Raed Abu Zitar, Mohammad Al-Betar, Mohamad Ryalat, and Sofian Kassaymehd. 2023. A review of UAV Visual Detection and Tracking Methods. arXiv preprint arXiv:2306.05089 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:03:45Z","timestamp":1765343025000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758220"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":49,"alternative-id":["10.1145\/3746027.3758220","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758220","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}