2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

一种新的分段式细粒度正则化的鲁棒跟踪算法

安志勇 梁顺楷 李博 赵峰 窦全胜 相忠良

安志勇, 梁顺楷, 李博, 赵峰, 窦全胜, 相忠良. 一种新的分段式细粒度正则化的鲁棒跟踪算法. 自动化学报, 2023, 49(5): 1116−1130 doi: 10.16383/j.aas.c220544
引用本文: 安志勇, 梁顺楷, 李博, 赵峰, 窦全胜, 相忠良. 一种新的分段式细粒度正则化的鲁棒跟踪算法. 自动化学报, 2023, 49(5): 1116−1130 doi: 10.16383/j.aas.c220544
An Zhi-Yong, Liang Shun-Kai, Li Bo, Zhao Feng, Dou Quan-Sheng, Xiang Zhong-Liang. Robust visual tracking with a novel segmented fine-grained regularization. Acta Automatica Sinica, 2023, 49(5): 1116−1130 doi: 10.16383/j.aas.c220544
Citation: An Zhi-Yong, Liang Shun-Kai, Li Bo, Zhao Feng, Dou Quan-Sheng, Xiang Zhong-Liang. Robust visual tracking with a novel segmented fine-grained regularization. Acta Automatica Sinica, 2023, 49(5): 1116−1130 doi: 10.16383/j.aas.c220544

一种新的分段式细粒度正则化的鲁棒跟踪算法

doi: 10.16383/j.aas.c220544
基金项目: 国家自然科学基金(61976125, 62176140), 山东省自然科学基金(ZR2021MF068, ZR2021MF015, ZR2021MF107, ZR2021QF134)资助
详细信息
    作者简介:

    安志勇:山东工商学院计算机科学与技术学院副教授. 2008年获得西安电子科技大学计算机系统结构专业博士学位. 主要研究方向为计算机视觉, 目标跟踪. E-mail: azytyut@163.com

    梁顺楷:山东工商学院计算机科学与技术学院硕士研究生. 2019年获得广东工业大学物联网工程专业学士学位. 主要研究方向为计算机视觉, 目标跟踪. E-mail: keith1063@163.com

    李博:山东工商学院计算机科学与技术学院副教授. 2013年获得东北大学计算机系统结构专业博士学位. 主要研究方向为人工智能, 机器学习. 本文通信作者. E-mail: libokkkkk@sdtbu.edu.cn

    赵峰:山东工商学院计算机科学与技术学院教授. 2008年获得西安电子科技大学计算机应用技术专业博士学位. 主要研究方向为人工智能, 机器学习, 医学图像分析和金融大数据分析. E-mail: zhaofeng1016@126.com

    窦全胜:山东工商学院计算机科学与技术学院教授. 2005年获得吉林大学计算机应用技术专业博士学位. 主要研究方向为计算智能, 数据挖掘, 知识工程和知识处理. E-mail: douqsh@sdtbu.edu.cn

    相忠良:山东工商学院计算机科学与技术学院讲师. 2015年获得韩国东西大学信息技术专业博士学位. 主要研究方向为机器学习, 贝叶斯网络学习. E-mail: zlxiang@sdtbu.edu.cn

Robust Visual Tracking With a Novel Segmented Fine-grained Regularization

Funds: Supported by National Natural Science Foundation of China (61976125, 62176140) and Natural Science Foundation of Shandong Province (ZR2021MF068, ZR2021MF015, ZR2021MF107, ZR2021QF134)
More Information
    Author Bio:

    AN Zhi-Yong Associate professor at the School of Computer Science and Technology, Shandong Technology and Business University. He received his Ph.D. degree in computer system architecture from Xidian University in 2008. His research interest covers computer vision and object tracking

    LIANG Shun-Kai Master student at the School of Computer Science and Technology, Shandong Technology and Business University. He received his bachelor degree in internet of things from Guangdong University of Technology in 2019. His research interest covers computer vision and object tracking

    LI Bo Associate professor at the School of Computer Science and Technology, Shandong Technology and Business University. He received his Ph.D. degree in computer system architecture from Northeastern University in 2013. His research interest covers artificial intelligence and machine learning. Corresponding author of this paper

    ZHAO Feng Professor at the School of Computer Science and Technology, Shandong Technology and Business University. He received his Ph.D. degree in computer application technology from Xidian University in 2008. His research interest covers artificial intelligence, machine learning, medical image analysis, and financial big data analysis

    DOU Quan-Sheng Professor at the School of Computer Science and Technology, Shandong Technology and Business University. He received his Ph.D. degree in computer application technology from Jilin University in 2005. His research interest covers computational intelligence, data mining, knowledge engineering, and knowledge management

    XIANG Zhong-Liang Lecturer at the School of Computer Science and Technology, Shandong Technology and Business University. He received his Ph.D. degree in information technology from Dongseo University in 2015. His research interest covers machine learning and Bayesian network learning

  • 摘要: 孪生网络跟踪算法在训练阶段多数采用$ {L_2}$正则化, 而忽略了网络架构的层次和特点, 因此跟踪的鲁棒性较差. 针对该问题, 提出一种分段式细粒度正则化跟踪(Segmented fine-grained regularization tracking, SFGRT)算法, 将孪生网络的正则化划分为滤波器、通道和神经元三个粒度层次. 创新性地建立了分段式细粒度正则化模型, 分段式可针对不同层次粒度组合, 利用组套索构造惩罚函数, 并通过梯度自平衡优化函数自适应地优化各惩罚函数系数, 该模型可提升网络架构的泛化能力并增强鲁棒性. 最后, 基于VOT2019跟踪数据库的消融实验表明, 与基线算法SiamRPN++比较, 在鲁棒性指标上降低了7.1%及在平均重叠期望(Expected average overlap, EAO)指标上提升了1.7%, 由于鲁棒性指标越小越好, 因此鲁棒性得到显著增强. 基于VOT2018、VOT2019、UAV123和LaSOT等主流数据库的实验也表明, 与国际前沿跟踪算法相比, 所提算法具有较好的鲁棒性和跟踪性能.
  • 图  1  分段式细粒度正则化跟踪算法的训练框架图

    Fig.  1  The training framework of the segmented fine-grained regularization tracking

    图  2  细粒度组套索示意图

    Fig.  2  Fine-grained group lasso

    图  3  细粒度组套索正则化在各网络分段的效果对比

    Fig.  3  Comparison of the effects of fine-grained group lasso regularization in each network segment

    图  4  分段式细粒度正则化模型示意图

    Fig.  4  Segmented fine-grained regularization model

    图  5  梯度自平衡优化方法

    Fig.  5  The gradient self-balancing optimization approach

    图  6  分段式细粒度正则化和细粒度组套索的跟踪效果对比

    Fig.  6  Comparison of tracking results between segmented fine-grained regularization and fine-grained group lasso

    图  7  训练损失曲线对比

    Fig.  7  Comparison of training loss curve

    图  8  UAV123基准上的性能对比

    Fig.  8  Comparison of tracking results on UAV123

    图  9  LaSOT基准上的性能对比

    Fig.  9  Comparison of tracking results on LaSOT

    图  10  UAV123和LaSOT基准上的多挑战属性下精度对比

    Fig.  10  Comparison of precision under different challenging attributes on UAV123 and LaSOT benchmarks

    图  11  VOT2019测试集部分视频序列的跟踪结果

    Fig.  11  Tracking results for some video sequences on VOT2019

    表  1  VOT2019上的消融实验

    Table  1  Ablation study on VOT2019

    基线算法+细粒度组套索+分段式细粒度正则化
    EAO↑0.2870.2930.304
    Accuracy↑0.5950.6000.586
    Robustness↓0.4670.4560.396
    下载: 导出CSV

    表  2  在VOT2018上与SOTA算法的比较

    Table  2  Comparison with SOTA trackers on VOT2018

    算法出版EAO↑Accuracy↑Robustness↓
    SiamRPNCVPR20180.3830.5860.276
    SiamRPN++CVPR20190.4140.6000.234
    SiamMaskCVPR20190.3800.6090.276
    LADCFITIP20190.3890.5030.159
    ATOMCVPR20190.4010.5900.204
    GFS-DCFICCV20190.3970.5110.143
    SiamBANCVPR20200.4520.5970.178
    SFGRT (Ours)0.4220.5890.197
    下载: 导出CSV

    表  3  在VOT2019上与SOTA算法的比较

    Table  3  Comparison with SOTA trackers on VOT2019

    算法出版EAO↑Accuracy↑Robustness↓
    SPMCVPR20190.2750.5770.507
    SiamRPN++CVPR20190.2870.5950.467
    SiamMaskCVPR20190.2870.5940.461
    SiamDWCVPR20190.2990.6000.467
    MemDTCPAMI20190.2280.4850.587
    ATOMCVPR20190.2920.6030.411
    Roam++CVPR20200.2810.5610.438
    SiamBANCVPR20200.3270.6020.396
    SFGRT (Ours)0.3040.5860.396
    下载: 导出CSV

    表  4  在UAV123基准上与SOTA算法在8个挑战性属性下的精度对比

    Table  4  Comparison of precision with SOTA trackers on 8 challenging attributes on UAV123

    AttributeECOSiamRPNDaSiamRPNSiamRPN++SiamCARSiamBANHiFTSFGRT
    CVPR2017CVPR2018ECCV2018CVPR2019CVPR2020CVPR2020ICCV2021
    POC0.6690.6740.7010.7330.7240.7650.6840.744
    IV0.7100.7030.7100.7750.7480.7660.7000.779
    CM0.7210.7780.7860.8190.7970.8480.7990.838
    FM0.6520.7010.7370.7240.7420.8050.7780.774
    SV0.7070.7390.7540.7800.7910.8130.7680.806
    BC0.6240.5890.6700.6330.6590.6450.5940.651
    OV0.5900.6380.6930.7890.7350.7890.7000.778
    LR0.6830.6480.6630.6580.6930.7190.6550.699
    Overall0.7410.7680.7810.8040.8130.8330.7870.828
    下载: 导出CSV

    表  5  在LaSOT基准上与SOTA算法在8个挑战性属性下的归一化精度对比

    Table  5  Comparison of norm precision with SOTA trackers on 8 challenging attributes on LaSOT

    AttributeSPLTC-RPNSiamDWSiamMaskSiamRPN++GFS-DCFATOMSiamBANCLNetSFGRT
    ICCV2019CVPR2019CVPR2019CVPR2019CVPR2019ICCV2019CVPR2019CVPR2020ICCV2021
    DEF0.5200.5780.5000.5930.6040.4360.5740.6090.6060.620
    VC0.5050.4910.3500.4990.5020.4270.4930.5260.4940.531
    IV0.5240.6030.4360.6250.6330.5810.5600.6420.6400.678
    MB0.4650.4860.4120.4930.5100.4430.5640.5560.5080.557
    ROT0.4880.5200.4180.5340.5520.4250.5240.5790.5550.583
    ARC0.4730.5180.4150.5240.5390.4230.5440.5670.5460.567
    SV0.4960.5400.4330.5480.5680.4470.5630.5950.5720.589
    OV0.4470.4380.3680.4580.4740.3720.4730.4950.4710.507
    Overall0.4940.5420.4370.5520.5700.4530.5700.5980.5740.590
    下载: 导出CSV

    表  6  不同跟踪算法的模型大小和平均帧速率对比

    Table  6  Comparison of model size and average framerate for different trackers

    算法出版模型大小(MB)帧速率(FPS)
    SiamRPN++CVPR2019431.280.20
    SiamMaskCVPR201986.1106.43
    SiamBANCVPR2020430.981.76
    SFGRT (Ours)431.279.99
    下载: 导出CSV
  • [1] Xing D T, Evangeliou N, Tsoukalas A, Tzes A. Siamese transformer pyramid networks for real-time UAV tracking. In: Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Waikoloa, USA: IEEE, 2022. 1898−1907
    [2] Fang L P, Liang N X, Kang W X, Wang Z Y, Feng D D. Real-time hand posture recognition using hand geometric features and fisher vector. Signal Processing: Image Communication, 2020, 82: Article No. 115729 doi: 10.1016/j.image.2019.115729
    [3] Ballester I, Fontán A, Civera J, Strobl K H, Triebel R. DOT: Dynamic object tracking for visual SLAM. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA). Xi'an, China: IEEE, 2021. 11705−11711
    [4] Wu Y, Lim J, Yang M H. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834-1848 doi: 10.1109/TPAMI.2014.2388226
    [5] Tang M, Yu B, Zhang F, Wang J Q. High-speed tracking with multi-kernel correlation filters. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 4874−4883
    [6] Sun Y X, Sun C, Wang D, He Y, Lu H C. ROI pooled correlation filters for visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 5783−5791
    [7] 仇祝令, 查宇飞, 吴敏, 王青. 基于注意力学习的正则化相关滤波跟踪算法. 电子学报, 2020, 48(9): 1762-1768 doi: 10.3969/j.issn.0372-2112.2020.09.014

    Qiu Zhu-Ling, Zha Yu-Fei, Wu Min, Wang Qing. Learning attentional regularized correlation filter for visual tracking. Acta Electronica Sinica, 2020, 48(9): 1762-1768 doi: 10.3969/j.issn.0372-2112.2020.09.014
    [8] 朱建章, 王栋, 卢湖川. 学习时空一致性相关滤波的视觉跟踪. 中国科学: 信息科学, 2020, 50(1): 128-150 doi: 10.1360/N112018-00232

    Zhu Jian-Zhang, Wang Dong, Lu Hu-Chuan. Learning temporal-spatial consistency correlation filter for visual tracking. Scientia Sinica Informationis, 2020, 50(1): 128-150 doi: 10.1360/N112018-00232
    [9] Hu H W, Ma B, Shen J B, Shao L. Manifold regularized correlation object tracking. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(5): 1786-1795 doi: 10.1109/TNNLS.2017.2688448
    [10] Xu T Y, Feng Z H, Wu X J, Kittler J. Joint group feature selection and discriminative filter learning for robust visual object tracking. In: Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea: IEEE, 2019. 7949−7959
    [11] Zhang T Z, Xu C S, Yang M H. Multi-task correlation particle filter for robust object tracking. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 4819−4827
    [12] 黄树成, 张瑜, 张天柱, 徐常胜, 王直. 基于条件随机场的深度相关滤波目标跟踪算法. 软件学报, 2019, 30(4): 927-940 doi: 10.13328/j.cnki.jos.005662

    Huang Shu-Cheng, Zhang Yu, Zhang Tian-Zhu, Xu Chang-Sheng, Wang Zhi. Improved deep correlation filters via conditional random field. Journal of Software, 2019, 30(4): 927-940 doi: 10.13328/j.cnki.jos.005662
    [13] 张伟俊, 钟胜, 徐文辉, Wu Ying. 融合显著性与运动信息的相关滤波跟踪算法. 自动化学报, 2021, 47(7): 1572-1588 doi: 10.16383/j.aas.c190122

    Zhang Wei-Jun, Zhong Sheng, Xu Wen-Hui, Wu Ying. Correlation filter based visual tracking integrating saliency and motion cues. Acta Automatica Sinica, 2021, 47(7): 1572-1588 doi: 10.16383/j.aas.c190122
    [14] 郭文, 游思思, 高君宇, 杨小汕, 张天柱, 徐常胜. 深度相对度量学习的视觉跟踪. 中国科学: 信息科学, 2018, 48(1): 60-78 doi: 10.1360/N112017-00124

    Guo Wen, You Si-Si, Gao Jun-Yu, Yang Xiao-Shan, Zhang Tian-Zhu, Xu Chang-Sheng. Deep relative metric learning for visual tracking. Scientia Sinica Informationis, 2018, 48(1): 60-78 doi: 10.1360/N112017-00124
    [15] Bertinetto L, Valmadre J, Henriques J F, Vedaldi A, Torr P H S. Fully-convolutional Siamese networks for object tracking. In: Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016. 850−865
    [16] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, USA: ACM, 2012. 1097−1105
    [17] Li B, Yan J J, Wu W, Zhu Z, Hu X L. High performance visual tracking with Siamese region proposal network. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 8971−8980
    [18] Li B, Wu W, Wang Q, Zhang F Y, Xing J L, Yan J J. SiamRPN++: Evolution of Siamese visual tracking with very deep networks. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 4282−4291
    [19] Wang Q, Zhang L, Bertinetto L, Hu W M, Torr P H S. Fast online object tracking and segmentation: A unifying approach. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 1328−1338
    [20] Zhang Z P, Peng H W. Deeper and wider Siamese networks for real-time visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 4591−4600
    [21] Chen Z D, Zhong B N, Li G R, Zhang S P, Ji R R. Siamese box adaptive network for visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE, 2020. 6667−6676
    [22] Chen Z D, Zhong B N, Li G R, Zhang S P, Ji R R, Tang Z J, et al. SiamBAN: Target-aware tracking with Siamese box adaptive network. IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2022.3195759
    [23] 谭建豪, 郑英帅, 王耀南, 马小萍. 基于中心点搜索的无锚框全卷积孪生跟踪器. 自动化学报, 2021, 47(4): 801-812 doi: 10.16383/j.aas.c200469

    Tan Jian-Hao, Zheng Ying-Shuai, Wang Yao-Nan, Ma Xiao-Ping. AFST: Anchor-free fully convolutional Siamese tracker with searching center point. Acta Automatica Sinica, 2021, 47(4): 801-812 doi: 10.16383/j.aas.c200469
    [24] Chen X, Yan B, Zhu J W, Wang D, Yang X Y, Lu H C. Transformer tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, USA: IEEE, 2021. 8122−8131
    [25] Cao Z, Fu C H, Ye J J, Li B W, Li Y M. HiFT: Hierarchical feature transformer for aerial tracking. In: Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, Canada: IEEE, 2021. 15437−15446
    [26] Xu T Y, Feng Z H, Wu X J, Kittler J. AFAT: Adaptive failure-aware tracker for robust visual object tracking. arXiv preprint arXiv: 2005.13708, 2020.
    [27] Kristan M, Matas J, Leonardis A, Felsberg M, Pflugfelder R, Kämäräinen J K, et al. The seventh visual object tracking VOT2019 challenge results. In: Proceedings of IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, South Korea: IEEE, 2019. 2206−2241
    [28] Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Zajc L Č, et al. The sixth visual object tracking VOT2018 challenge results. In: Proceedings of the 14th European Conference on Computer Vision Workshops. Munich, Germany: Springer, 2018. 3−53
    [29] Mueller M, Smith N, Ghanem B. A benchmark and simulator for UAV tracking. In: Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016. 445−461
    [30] Fan H, Lin L T, Yang F, Chu P, Deng G, Yu S J, et al. LaSOT: A high-quality benchmark for large-scale single object tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 5369−5378
    [31] Zhu Z, Wang Q, Li B, Wu W, Yan J J, Hu W M. Distractor-aware Siamese networks for visual object tracking. In: Proceedings of the 15th European Conference on Computer Vision. Munich, Germany: Springer, 2018. 103−119
    [32] He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE, 2016. 770−778
    [33] He A F, Luo C, Tian X M, Zeng W J. A twofold Siamese network for real-time object tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 4834−4843
    [34] Wang Q, Teng Z, Xing J L, Gao J, Hu W M, Maybank S. Learning attentions: Residual attentional Siamese network for high performance online visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 4854−4863
    [35] Du F, Liu P, Zhao W, Tang X L. Correlation-guided attention for corner detection based visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE, 2020. 6835−6844
    [36] Li F, Tian C, Zuo W M, Zhang L, Yang M H. Learning spatial-temporal regularized correlation filters for visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 4904−4913
    [37] Huang Z Y, Fu C H, Li Y M, Lin F L, Lu P. Learning aberrance repressed correlation filters for real-time UAV tracking. In: Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea: IEEE, 2019. 2891−2900
    [38] Li Y M, Fu C H, Ding F Q, Huang Z Y, Lu G. AutoTrack: Towards high-performance visual tracking for UAV with automatic spatio-temporal regularization. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE, 2020. 11920−11929
    [39] Liu X N, Zhou Y, Zhao J Q, Yao R, Liu B, Zheng Y. Siamese convolutional neural networks for remote sensing scene classification. IEEE Geoscience and Remote Sensing Letters, 2019, 16(8): 1200-1204 doi: 10.1109/LGRS.2019.2894399
    [40] Fiaz M, Mahmood A, Baek K Y, Farooq S S, Jung S K. Improving object tracking by added noise and channel attention. Sensors, 2020, 20(13): Article No. 3780 doi: 10.3390/s20133780
    [41] Jia S, Ma C, Song Y B, Yang X K. Robust tracking against adversarial attacks. In: Proceedings of the 16th European Conference on Computer Vision. Glasgow, UK: Springer, 2020. 69−84
    [42] Yuan M, Lin Y. Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2006, 68(1): 49-67 doi: 10.1111/j.1467-9868.2005.00532.x
    [43] Nie F P, Huang H, Cai X, Ding C. Efficient and robust feature selection via joint $ \ell_2, 1$-norms minimization. In: Proceedings of the 23rd International Conference on Neural Information Processing Systems. Vancouver, Canada: ACM, 2010. 1813−1821
    [44] Bach F, Jenatton R, Mairal J, Obozinski G. Structured sparsity through convex optimization. Statistical Science, 2012, 27(4): 450-468
    [45] Yoon J, Hwang S J. Combined group and exclusive sparsity for deep neural networks. In: Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia: JMLR.org, 2017. 3958−3966
    [46] Hu Y H, Li C, Meng K W, Qin J, Yang X Q. Group sparse optimization via $ L_p, q$ regularization. The Journal of Machine Learning Research, 2017, 18(1): 960-1011
    [47] Wen W, Wu C P, Wang Y D, Chen Y R, Li H. Learning structured sparsity in deep neural networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain: ACM, 2016. 2082−2090
    [48] Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, et al. Intriguing properties of neural networks. arXiv preprint arXiv: 1312.6199, 2013.
    [49] Chen Z, Badrinarayanan V, Lee C Y, Rabinovich A. GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In: Proceedings of the 35th International Conference on Machine Learning. Stockholm, Sweden: PMLR, 2018. 793−802
    [50] Lin T Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, et al. Microsoft COCO: Common objects in context. In: Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014. 740−755
    [51] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S A, et al. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3): 211-252 doi: 10.1007/s11263-015-0816-y
    [52] Real E, Shlens J, Mazzocchi S, Pan X, Vanhoucke V. YouTube-BoundingBoxes: A large high-precision human-annotated data set for object detection in video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 7464−7473
    [53] Huang L H, Zhao X, Huang K Q. GOT-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(5): 1562-1577 doi: 10.1109/TPAMI.2019.2957464
    [54] Guo D Y, Wang J, Cui Y, Wang Z H, Chen S Y. SiamCAR: Siamese fully convolutional classification and regression for visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE, 2020. 6268−6276
    [55] Dong X P, Shen J B, Shao L, Porikli F. CLNet: A compact latent network for fast adjusting Siamese trackers. In: Proceedings of the 16th European Conference on Computer Vision. Glasgow, UK: Springer, 2020. 378−395
    [56] Yang T Y, Xu P F, Hu R B, Chai H, Chan A B. ROAM: Recurrently optimizing tracking model. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE, 2020. 6717−6726
    [57] Danelljan M, Bhat G, Khan F S, Felsberg M. ATOM: Accurate tracking by overlap maximization. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 4660−4669
    [58] Yan B, Zhao H J, Wang D, Lu H C, Yang X Y. ‘Skimming-perusal’ tracking: A framework for real-time and robust long-term tracking. In: Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea: IEEE, 2019. 2385−2393
    [59] Fan H, Ling H B. Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 7952−7961
    [60] Yang T Y, Chan A B. Visual tracking via dynamic memory networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 360-374
    [61] Xu T Y, Feng Z H, Wu X J, Kittler J. Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking. IEEE Transactions on Image Processing, 2019, 28(11): 5596-5609 doi: 10.1109/TIP.2019.2919201
    [62] Danelljan M, Bhat G, Khan F S, Felsberg M. ECO: Efficient convolution operators for tracking. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 6931−6939
    [63] Wang G T, Luo C, Xiong Z W, Zeng W J. SPM-Tracker: Series-parallel matching for real-time visual object tracking. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019. 3643−3652
  • 加载中
图(11) / 表(6)
计量
  • 文章访问数:  668
  • HTML全文浏览量:  124
  • PDF下载量:  197
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-07-03
  • 录用日期:  2022-11-12
  • 网络出版日期:  2023-02-06
  • 刊出日期:  2023-05-20

目录

    /

    返回文章
    返回