Corpus ID: 49309922

Learning to Update for Object Tracking

@article{Li2018LearningTU,
  title={Learning to Update for Object Tracking},
  author={Bi Li and Wenxuan Xie and Wenjun Zeng and Wenyu Liu},
  journal={ArXiv},
  year={2018},
  volume={abs/1806.07078}
}
  • Bi Li, Wenxuan Xie, +1 author Wenyu Liu
  • Published 2018
  • Computer Science
  • ArXiv
  • Model update lies at the heart of object tracking. [...] Key Method As a first attempt, we design the learned updater based on recurrent neural networks (RNNs) and demonstrate its application in a template-based tracker and a correlation filter-based tracker. Our learned updater consistently improves the base trackers and runs faster than realtime on GPU while requiring small memory footprint during testing. Experiments on standard benchmarks demonstrate that our learned updater outperforms commonly used update…Expand Abstract
    3 Citations
    Learning to Remember Past to Predict Future for Visual Tracking
    • 2
    • PDF
    Re2EMA: Regularized and Reinitialized Exponential Moving Average for Target Model Update in Object Tracking
    • 8
    • Highly Influenced
    • PDF
    i-Siam: Improving Siamese Tracker with Distractors Suppression and Long-Term Strategies
    • Wei Ren Tan, S. Lai
    • Computer Science
    • 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
    • 2019
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 42 REFERENCES
    Re3 : Real-Time Recurrent Regression Networks for Object Tracking
    • 44
    • PDF
    Recurrent Filter Learning for Visual Tracking
    • 57
    • Highly Influential
    • PDF
    Learning Policies for Adaptive Tracking with Deep Feature Cascades
    • 153
    • PDF
    Robust Object Tracking with Online Multiple Instance Learning
    • 1,885
    • PDF
    Learning Dynamic Siamese Network for Visual Object Tracking
    • 317
    • Highly Influential
    • 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
    • PDF
    CREST: Convolutional Residual Learning for Visual Tracking
    • 319
    • PDF
    Semi-supervised On-Line Boosting for Robust Tracking
    • 1,202
    • PDF