Corpus ID: 56475930

Shallow Cue Guided Deep Visual Tracking via Mixed Models

  title={Shallow Cue Guided Deep Visual Tracking via Mixed Models},
  author={Fangwen Tu and S. Ge and C. Hang},
  • Fangwen Tu, S. Ge, C. Hang
  • Published 2018
  • Computer Science
  • ArXiv
  • In this paper, a robust visual tracking approach via mixed model based convolutional neural networks (SDT) is developed. In order to handle abrupt or fast motion, a prior map is generated to facilitate the localization of region of interest (ROI) before the deep tracker is performed. A top-down saliency model with nineteen shallow cues are employed to construct the prior map with online learnt combination weights. Moreover, apart from a holistic deep learner, four local networks are also… CONTINUE READING


    Publications referenced by this paper.
    Incremental Learning for Robust Visual Tracking
    • 2,839
    • PDF
    Kernel-Based Object Tracking
    • 4,810
    • PDF
    High-Speed Tracking with Kernelized Correlation Filters
    • 2,913
    • PDF
    Hierarchical Convolutional Features for Visual Tracking
    • 1,111
    • PDF
    Visual tracking via adaptive structural local sparse appearance model
    • 1,173
    • Highly Influential
    • PDF
    Visual Tracking with Fully Convolutional Networks
    • 732
    • Highly Influential
    • PDF
    • 2,393
    • PDF
    ImageNet: A large-scale hierarchical image database
    • 7,050
    • PDF
    Learning to predict where humans look
    • 1,664
    • PDF
    Exploiting the Circulant Structure of Tracking-by-Detection with Kernels
    • 1,541
    • PDF