{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:00:38Z","timestamp":1765310438640,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755155","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"1376-1385","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FA\n                    <sup>3<\/sup>\n                    T: Feature-Aware Adversarial Attacks for Multi-modal Tracking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0375-9253","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4710-9249","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2002-3894","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9751-7859","authenticated-orcid":false,"given":"Xinyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, xian, China"}],"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":"10.1109\/ACCESS.2018.2807385"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"e_1_3_2_1_3_1","first-page":"2188","article-title":"Universal adversarial attack on attention and the resulting dataset damagenet","volume":"44","author":"Chen Sizhe","year":"2020","unstructured":"Sizhe Chen, Zhengbao He, Chengjin Sun, Jie Yang, and Xiaolin Huang. 2020. Universal adversarial attack on attention and the resulting dataset damagenet. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 4 (2020), 2188--2197.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109629"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347031"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-007-0078-y"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27920"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"e_1_3_2_1_10_1","volume-title":"et al","author":"Dosovitskiy Alexey","year":"2020","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\/ICCV48922.2021.00741"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3033034"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-06979-y"},{"key":"e_1_3_2_1_14_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382473"},{"key":"e_1_3_2_1_18_1","first-page":"28714","article-title":"3d siamese voxel-to-bev tracker for sparse point clouds","volume":"34","author":"Hui Le","year":"2021","unstructured":"Le Hui, Lingpeng Wang, Mingmei Cheng, Jin Xie, and Jian Yang. 2021. 3d siamese voxel-to-bev tracker for sparse point clouds. Advances in Neural Information Processing Systems 34 (2021), 28714--28727.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00664"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3389454"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3208131"},{"key":"e_1_3_2_1_24_1","volume-title":"European Conference on Computer Vision. Springer, 431--460","author":"Kristan Matej","year":"2022","unstructured":"Matej Kristan, Ale\u0161 Leonardis, Jir\u00ed Matas, Michael Felsberg, Roman Pflugfelder, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, Hyung Jin Chang, Martin Danelljan, Luka Cehovin Zajc, Alan Luke\u017eic, et al. 2022. The tenth visual object tracking vot2022 challenge results. In European Conference on Computer Vision. Springer, 431--460."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198643"},{"key":"e_1_3_2_1_31_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 (2023), 34892--34916."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2019.04.017"},{"key":"e_1_3_2_1_33_1","volume-title":"Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083","author":"Madry Aleksander","year":"2017","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2017. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"e_1_3_2_1_35_1","volume-title":"Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers. Transactions on Machine Learning Research Journal","author":"Nokabadi Fatemeh Nourilenjan","year":"2024","unstructured":"Fatemeh Nourilenjan Nokabadi, Jean-Fran\u00e7ois Lalonde, and Christian Gagn\u00e9. 2024. Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers. Transactions on Machine Learning Research Journal (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28347"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358549"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3436878"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102531"},{"key":"e_1_3_2_1_40_1","first-page":"121475","article-title":"Cogvlm: Visual expert for pretrained language models","volume":"37","author":"Wang Weihan","year":"2024","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Song XiXuan, et al . 2024. Cogvlm: Visual expert for pretrained language models. Advances in Neural Information Processing Systems 37 (2024), 121475--121499.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3318601"},{"key":"e_1_3_2_1_42_1","volume-title":"Luc Van Gool, and Zheng Wang","author":"Wei Hui","year":"2024","unstructured":"Hui Wei, Hao Tang, Xuemei Jia, Zhixiang Wang, Hanxun Yu, Zhubo Li, Shin'ichi Satoh, Luc Van Gool, and Zheng Wang. 2024. Physical adversarial attack meets computer vision: A decade survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"e_1_3_2_1_44_1","volume-title":"Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks. In European Conference on Computer Vision. Springer, 198--214","author":"Wu Zhewei","year":"2024","unstructured":"Zhewei Wu, Ruilong Yu, Qihe Liu, Shuying Cheng, Shilin Qiu, and Shijie Zhou. 2024. Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks. In European Conference on Computer Vision. Springer, 198--214."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00107"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"e_1_3_2_1_50_1","volume-title":"Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification. In The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Yang Xi","year":"2024","unstructured":"Xi Yang, Huanling Liu, De Cheng, Nannan Wang, and Xinbo Gao. 2024. Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827460"},{"key":"e_1_3_2_1_53_1","volume-title":"Adversarial attacks of vision tasks in the past 10 years: A survey. arXiv preprint arXiv:2410.23687","author":"Zhang Chiyu","year":"2024","unstructured":"Chiyu Zhang, Xiaogang Xu, Jiafei Wu, Zhe Liu, and Lu Zhou. 2024. Adversarial attacks of vision tasks in the past 10 years: A survey. arXiv preprint arXiv:2410.23687 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28542"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01280"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0345-5"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3441038"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011253"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234266"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:57:12Z","timestamp":1765310232000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":60,"alternative-id":["10.1145\/3746027.3755155","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755155","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"}}]}}