Depth-Adaptive Computational Policies for Efficient Visual Tracking

@article{Ying2017DepthAdaptiveCP,
  title={Depth-Adaptive Computational Policies for Efficient Visual Tracking},
  author={Chris Ying and K. Fragkiadaki},
  journal={ArXiv},
  year={2017},
  volume={abs/1801.00508}
}
  • Chris Ying, K. Fragkiadaki
  • Published 2017
  • Computer Science
  • ArXiv
  • Current convolutional neural networks algorithms for video object tracking spend the same amount of computation for each object and video frame. However, it is harder to track an object in some frames than others, due to the varying amount of clutter, scene complexity, amount of motion, and object's distinctiveness against its background. We propose a depth-adaptive convolutional Siamese network that performs video tracking adaptively at multiple neural network depths. Parametric gating… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-5 OF 5 CITATIONS

    Improved Techniques for Training Adaptive Deep Networks

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    LAP-Net: Level-Aware Progressive Network for Image Dehazing

    VIEW 1 EXCERPT
    CITES METHODS

    Layer Flexible Adaptive Computational Time for Recurrent Neural Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    Visual Tracking with Fully Convolutional Networks

    VIEW 1 EXCERPT

    Hierarchical Convolutional Features for Visual Tracking

    VIEW 1 EXCERPT

    Spatially Adaptive Computation Time for Residual Networks

    VIEW 1 EXCERPT

    Siamese Neural Networks for One-Shot Image Recognition

    • Gregory R. Koch
    • Computer Science
    • 2015
    VIEW 2 EXCERPTS

    The Visual Object Tracking VOT2016 Challenge Results

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Holistically-Nested Edge Detection

    VIEW 1 EXCERPT