{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:07Z","timestamp":1765343107854,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","funder":[{"name":"Guangxi Natural Science Foundation","award":["2024GXNSFAA010484"],"award-info":[{"award-number":["2024GXNSFAA010484"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758243","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12965-12972","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Camouflaged Object Tracking: A Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2294-6708","authenticated-orcid":false,"given":"Xiaoyu","family":"Guo","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2661-6255","authenticated-orcid":false,"given":"Pengzhi","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3933-3819","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9598-523X","authenticated-orcid":false,"given":"DeFeng","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9970-1576","authenticated-orcid":false,"given":"Huikai","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4651-7163","authenticated-orcid":false,"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4587-513X","authenticated-orcid":false,"given":"Shuiwang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, Guangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"European Conference on Computer Vision.","author":"Benchmark UT","year":"2016","unstructured":"UT Benchmark. 2016. A benchmark and simulator for UAV tracking. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_2_1","first-page":"850","volume-title":"Computer Vision-ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14","author":"Bertinetto Luca","unstructured":"Luca Bertinetto and Jack et al. Valmadre. 2016. Fully-convolutional siamese networks for object tracking. In Computer Vision-ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14. Springer, 850-865."},{"key":"e_1_3_2_1_3_1","first-page":"2544","article-title":"Visual object tracking using adaptive correlation filters. In 2010 IEEE computer society conference on computer vision and pattern recognition","author":"Bolme David S","year":"2010","unstructured":"David S Bolme, J Ross Beveridge, Bruce A Draper, and Yui Man Lui. 2010. Visual object tracking using adaptive correlation filters. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 2544-2550.","journal-title":"IEEE"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01762-5"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"e_1_3_2_1_6_1","unstructured":"Wenrui Cai Qingjie Liu and Yunhong Wang. 2024b. HIPTrack: Visual Tracking with Historical Prompts. arXiv:2311.02072 [cs.CV]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13864-13873","author":"Cheng Xuelian","key":"e_1_3_2_1_10_1","unstructured":"Xuelian Cheng, Huan Xiong, and et al., 2022. Implicit motion handling for video camouflaged object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13864-13873."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00650"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2019.07.007"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.490"},{"key":"e_1_3_2_1_15_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_16_1","volume-title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. In European Conference on Computer Vision (ECCV).","author":"Du Dawei","year":"2018","unstructured":"Dawei Du, Yuankai Qi, Hongyang Yu, Yi-Fan Yang, Kaiwen Duan, Guorong Li, W. Zhang, Qingming Huang, and Qi Tian. 2018. The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_17_1","volume-title":"Pranet: Parallel reverse attention network for polyp segmentation. In International conference on medical image computing and computer-assisted intervention","author":"Fan Deng-Ping","year":"2020","unstructured":"Deng-Ping Fan, Ge-Peng Ji, and et al., 2020a. Pranet: Parallel reverse attention network for polyp segmentation. In International conference on medical image computing and computer-assisted intervention. Springer, 263-273."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00285"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"e_1_3_2_1_20_1","first-page":"5369","volume-title":"LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Fan Heng","year":"2019","unstructured":"Heng Fan, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Hexin Bai, Yong Xu, Chunyuan Liao, and Haibin Ling. 2019b. LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 5369-5378."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01056"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 1756-1776","author":"Guo Xiaoyu","year":"2024","unstructured":"Xiaoyu Guo, Pengzhi Zhong, Lizhi Lin, Hao Zhang, Ling Huang, and Shuiwang Li. 2024. Tracking reflected objects: a benchmark. In Proceedings of the Asian Conference on Computer Vision. 1756-1776."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/beheco\/arw081"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2023.3263329"},{"key":"e_1_3_2_1_28_1","volume-title":"Got-10k: A large high-diversity benchmark for generic object tracking in the wild","author":"Huang Lianghua","year":"2019","unstructured":"Lianghua Huang, Xin Zhao, and Kaiqi Huang. 2019. Got-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 5 (2019), 1562-1577."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2516982"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/pr11020312"},{"volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 4282-4291","author":"Li Bo","key":"e_1_3_2_1_31_1","unstructured":"Bo Li and Wei et al. Wu. 2019. Siamrpn: Evolution of siamese visual tracking with very deep networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 4282-4291."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00515"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900507"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IHMSC49165.2020.10111"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2893843"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC53003.2021.9728332"},{"key":"e_1_3_2_1_38_1","series-title":"Journal of Physics: Conference Series","volume-title":"An unsupervised aerial tracking method of camouflaged targets in complex environments","author":"Liu Yang","year":"2019","unstructured":"Yang Liu, Cong-qing Wang, Bin Xu, and Yongjun Zhou. 2023a. An unsupervised aerial tracking method of camouflaged targets in complex environments. In Journal of Physics: Conference Series, Vol. 2478. IOP Publishing, 062019."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.32.6.063018"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01011"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01142"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00866"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Matthias M\u00fcller Adel Bibi Silvio Giancola Salman Al-Subaihi and Bernard Ghanem. 2018. TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild. In ECCV.","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1111\/brv.12612"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"volume-title":"Proceedings of the 28th ACM international conference on multimedia. 1948-1957","author":"Sio Chon Hou","key":"e_1_3_2_1_49_1","unstructured":"Chon Hou Sio, Yu-Jen Ma, and et al., 2020. S2siamfc: Self-supervised fully convolutional siamese network for visual tracking. In Proceedings of the 28th ACM international conference on multimedia. 1948-1957."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.36"},{"key":"e_1_3_2_1_51_1","volume-title":"BihoT: A Large-Scale Dataset and Benchmark for Hyperspectral Camouflaged Object Tracking. arXiv preprint arXiv:2408.12232","author":"Wang Hanzheng","year":"2024","unstructured":"Hanzheng Wang, Wei Li, Xiang-Gen Xia, and Qian Du. 2024. BihoT: A Large-Scale Dataset and Benchmark for Hyperspectral Camouflaged Object Tracking. arXiv preprint arXiv:2408.12232 (2024)."},{"key":"e_1_3_2_1_52_1","first-page":"15220","article-title":"Displacement-invariant matching cost learning for accurate optical flow estimation","volume":"33","author":"Wang Jianyuan","year":"2020","unstructured":"Jianyuan Wang, Yiran Zhong, and et al., 2020. Displacement-invariant matching cost learning for accurate optical flow estimation. Advances in Neural Information Processing Systems, Vol. 33 (2020), 15220-15231.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition. 8953-8962","author":"Wang Jianyuan","key":"e_1_3_2_1_53_1","unstructured":"Jianyuan Wang, Yiran Guo Zhong, and et al., 2021. Deep two-view structure-from-motion revisited. In Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition. 8953-8962."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"e_1_3_2_1_56_1","volume-title":"Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking. arXiv preprint arXiv:2412.20002","author":"Wu You","year":"2024","unstructured":"You Wu, Yongxin Li, Mengyuan Liu, Xucheng Wang, Xiangyang Yang, Hengzhou Ye, Dan Zeng, Qijun Zhao, and Shuiwang Li. 2024. Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking. arXiv preprint arXiv:2412.20002 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01594"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058783"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_8"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3064443"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"e_1_3_2_1_64_1","volume-title":"Active learning for deep visual tracking","author":"Yuan Di","year":"2023","unstructured":"Di Yuan, Xiaojun Chang, Qiao Liu, Yi Yang, Dehua Wang, Minglei Shu, Zhenyu He, and Guangming Shi. 2023. Active learning for deep visual tracking. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3223216"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"e_1_3_2_1_67_1","unstructured":"Chunhui Zhang Li Liu Guanjie Huang Zhipeng Zhang Hao Wen Xi Zhou Shiming Ge and Yanfeng Wang. [n.d.]. Underwater Camouflaged Object Tracking Meets Vision-Language SAM2. ([n.d.])."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones9010068"},{"key":"e_1_3_2_1_69_1","volume-title":"Ocean: Object-aware anchor-free tracking. In Computer Vision-ECCV 2020: 16th European Conference","author":"Zhang Zhipeng","year":"2020","unstructured":"Zhipeng Zhang, Houwen Peng, Jianlong Fu, Bing Li, and Weiming Hu. 2020. Ocean: Object-aware anchor-free tracking. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXI 16. Springer, 771-787."},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 4514-4530","author":"Zhang Zhewen","year":"2022","unstructured":"Zhewen Zhang, Fuliang Wu, Yuming Qiu, Jingdong Liang, and Shuiwang Li. 2022b. Tracking small and fast moving objects: A benchmark. In Proceedings of the Asian Conference on Computer Vision. 4514-4530."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02308"},{"key":"e_1_3_2_1_72_1","volume-title":"Low-Light Object Tracking: A Benchmark. arXiv preprint arXiv:2408.11463","author":"Zhong Pengzhi","year":"2024","unstructured":"Pengzhi Zhong, Xiaoyu Guo, Defeng Huang, Xiaojun Peng, Yian Li, Qijun Zhao, and Shuiwang Li. 2024. Low-Light Object Tracking: A Benchmark. arXiv preprint arXiv:2408.11463 (2024)."},{"volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12095-12104","author":"Zhong Yiran","key":"e_1_3_2_1_73_1","unstructured":"Yiran Zhong, Pan Ji, and et al., 2019. Unsupervised deep epipolar flow for stationary or dynamic scenes. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12095-12104."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"}],"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\/3746027.3758243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:01:07Z","timestamp":1765342867000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":74,"alternative-id":["10.1145\/3746027.3758243","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758243","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"}}]}}