VITAL: VIsual Tracking via Adversarial Learning

@article{Song2018VITALVT,
  title={VITAL: VIsual Tracking via Adversarial Learning},
  author={Yibing Song and Chao Ma and Xiaohe Wu and L. Gong and Linchao Bao and W. Zuo and Chunhua Shen and R. Lau and Ming-Hsuan Yang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={8990-8999}
}
  • Yibing Song, Chao Ma, +6 authors Ming-Hsuan Yang
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • The tracking-by-detection framework consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. [...] Key Method To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes.Expand Abstract
    232 Citations

    Figures, Tables, and Topics from this paper

    Adversarial Feature Sampling Learning for Efficient Visual Tracking
    • 3
    • Highly Influenced
    • PDF
    VTAAN: Visual Tracking with Attentive Adversarial Network
    • Highly Influenced
    Adversarial Deep Tracking
    • 9
    • Highly Influenced
    Appearance variation adaptation tracker using adversarial network
    • 2
    • Highly Influenced
    • PDF
    Improved Real-Time Visual Tracking via Adversarial Learning
    • Highly Influenced
    Learning attention for object tracking with adversarial learning network
    • Highly Influenced
    • PDF
    SAT: Single-Shot Adversarial Tracker
    Adversarial Learning-based Data Augmentation for Rotation-robust Human Tracking
    • 1
    Localization-Aware Meta Tracker Guided With Adversarial Features
    • 6
    • Highly Influenced
    Efficient Adversarial Attacks for Visual Object Tracking
    • 2
    • PDF

    References

    SHOWING 1-10 OF 67 REFERENCES
    Semi Supervised Semantic Segmentation Using Generative Adversarial Network
    • 126
    • PDF
    A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
    • 305
    • PDF
    Fully-Convolutional Siamese Networks for Object Tracking
    • 1,568
    • PDF
    Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
    • 273
    • PDF
    Focal Loss for Dense Object Detection
    • 3,700
    DeLiGAN: Generative Adversarial Networks for Diverse and Limited Data
    • 120
    • PDF
    Visual Tracking with Fully Convolutional Networks
    • 777
    • PDF
    In defense of color-based model-free tracking
    • 268
    • PDF
    Transfer Learning Based Visual Tracking with Gaussian Processes Regression
    • 394
    • PDF
    CREST: Convolutional Residual Learning for Visual Tracking
    • 321
    • PDF