Learning to Update for Object Tracking With Recurrent Meta-Learner

@article{Li2019LearningTU,
  title={Learning to Update for Object Tracking With Recurrent Meta-Learner},
  author={Bi Li and Wenxuan Xie and Wenjun Zeng and W. Liu},
  journal={IEEE Transactions on Image Processing},
  year={2019},
  volume={28},
  pages={3624-3635}
}
  • Bi Li, Wenxuan Xie, +1 author W. Liu
  • Published 2019
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • Model update lies at the heart of object tracking. Generally, model update is formulated as an online learning problem, where a target model is learned over the online training set. Our key innovation is to formulate the model update problem in the meta-learning framework and learn the online learning algorithm itself using large numbers of offline videos, i.e., learning to update. The learned updater takes as input the online training set and outputs an updated target model. As a first attempt… CONTINUE READING
    10 Citations
    High-Performance Long-Term Tracking With Meta-Updater
    • 7
    • PDF
    Motion Guided Siamese Trackers for Visual Tracking
    • 5
    • PDF
    Improving Object Tracking by Added Noise and Channel Attention
    • 2
    • PDF
    Bridging the Gap Between Detection and Tracking: A Unified Approach
    • 6
    • PDF
    Learning Soft Mask Based Feature Fusion with Channel and Spatial Attention for Robust Visual Object Tracking
    • 2
    • PDF
    Parallel Three-Branch Correlation Filters for Complex Marine Environmental Object Tracking Based on a Confidence Mechanism
    • PDF
    Multi-AUV Target Recognition Method Based on GAN-meta Learning
    • Qiankun Sun, L. Cai
    • Computer Science
    • 2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)
    • 2020
    Edge Computing Resources Reservation in Vehicular Networks: A Meta-Learning Approach
    • 3
    • PDF

    References

    SHOWING 1-10 OF 51 REFERENCES
    Re3 : Real-Time Recurrent Regression Networks for Object Tracking
    • 44
    • Highly Influential
    • PDF
    Learning Policies for Adaptive Tracking with Deep Feature Cascades
    • 153
    • PDF
    Recurrent Filter Learning for Visual Tracking
    • 57
    • PDF
    Learning Dynamic Siamese Network for Visual Object Tracking
    • 317
    • Highly Influential
    • PDF
    Robust Object Tracking with Online Multiple Instance Learning
    • 1,885
    • PDF
    Siamese Instance Search for Tracking
    • 594
    • PDF
    Fully-Convolutional Siamese Networks for Object Tracking
    • 1,556
    • Highly Influential
    • PDF
    Learning Multi-domain Convolutional Neural Networks for Visual Tracking
    • H. Nam, B. Han
    • Computer Science
    • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2016
    • 1,477
    • Highly Influential
    • PDF
    Re$^3$: Re al-Time Recurrent Regression Networks for Visual Tracking of Generic Objects
    • 65
    • PDF
    Hierarchical Attentive Recurrent Tracking
    • 47
    • PDF