{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T04:59:04Z","timestamp":1773118744794,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0105702"],"award-info":[{"award-number":["2020AAA0105702"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225207, U19B2038, 62121002 and 62276243"],"award-info":[{"award-number":["62225207, U19B2038, 62121002 and 62276243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611799","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"193-202","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Alleviating Spatial Misalignment and Motion Interference for UAV-based Video Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1526-9002","authenticated-orcid":false,"given":"Gege","family":"Shi","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8036-4071","authenticated-orcid":false,"given":"Xueyang","family":"Fu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7177-8137","authenticated-orcid":false,"given":"Chengzhi","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.267"},{"key":"e_1_3_2_1_3_1","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML, Vol. 2. 4.","journal-title":"ICML"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICECE51594.2020.9353008"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2017.11"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Guoqiang Gong Liangfeng Zheng Wenhao Jiang and Yadong Mu. 2021. Self-Supervised Video Action Localization with Adversarial Temporal Transforms.. In IJCAI. 693--699.","DOI":"10.24963\/ijcai.2021\/96"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463579"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3150917","article-title":"FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification","volume":"60","author":"Jin Pu","year":"2022","unstructured":"Pu Jin, Lichao Mou, Yuansheng Hua, Gui-Song Xia, and Xiao Xiang Zhu. 2022. FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1--13.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_22_1","volume-title":"Tel Aviv","author":"Kothandaraman Divya","year":"2022","unstructured":"Divya Kothandaraman, Tianrui Guan, Xijun Wang, Shuowen Hu, Ming Lin, and Dinesh Manocha. 2022. FAR: Fourier Aerial Video Recognition. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXVII. Springer, 657--676."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00077"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2969809"},{"key":"e_1_3_2_1_25_1","volume-title":"Repre- sentation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement. arXiv preprint arXiv:2205.03569","author":"Li Bing","year":"2022","unstructured":"Bing Li, Jiaxin Chen, Dongming Zhang, Xiuguo Bao, and Di Huang. 2022. Repre- sentation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement. arXiv preprint arXiv:2205.03569 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00795"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912001"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00435"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00867"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_36_1","unstructured":"Wenyang Luo Yufan Liu Bing Li Weiming Hu Yanan Miao and Yangxi Li. [n. d.]. Long-Short Term Cross-Transformer in Compressed Domain for Few-Shot Video Classification. ([n. d.])."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413934"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977457"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.3005751"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones3040082"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2020.2971958"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0-0.","author":"Perera Asanka G","year":"2018","unstructured":"Asanka G Perera, Yee Wei Law, and Javaan Chahl. 2018. UAV-GESTURE: A dataset for UAV control and gesture recognition. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0-0."},{"key":"e_1_3_2_1_45_1","volume-title":"Ross B. Girshick, and Ali Farhadi.","author":"Redmon Joseph","year":"2015","unstructured":"Joseph Redmon, Santosh Kumar Divvala, Ross B. Girshick, and Ali Farhadi. 2015. You Only Look Once: Unified, Real-Time Object Detection. CoRR abs\/1506.02640 (2015). arXiv:1506.02640 http:\/\/arxiv.org\/abs\/1506.02640"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910412"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision 115 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_50_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103186"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/104"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_55_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00109"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_59_1","volume-title":"Mutually Reinforced Spatio-Temporal Convolutional Tube for Human Action Recognition. In Twenty-Eighth International Joint Conference on Artificial Intelligence IJCAI-19","author":"Wu H.","unstructured":"H. Wu, J. Liu, Z. J. Zha, Z. Chen, and X. Sun. 2019. Mutually Reinforced Spatio-Temporal Convolutional Tube for Human Action Recognition. In Twenty-Eighth International Joint Conference on Artificial Intelligence IJCAI-19."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.5555\/3491440.3491545"},{"key":"e_1_3_2_1_61_1","unstructured":"Shuo Yang and Xinxiao Wu. [n. d.]. Entity-aware and Motion-aware Transformers for Language-driven Action Localization. ([n. d.])."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00869"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548343"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611799","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:50Z","timestamp":1755820910000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611799"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":65,"alternative-id":["10.1145\/3581783.3611799","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611799","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}