Least Soft-Threshold Squares Tracking

@article{Wang2013LeastSS,
  title={Least Soft-Threshold Squares Tracking},
  author={Dong Wang and Huchuan Lu and Ming-Hsuan Yang},
  journal={2013 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2013},
  pages={2371-2378}
}
In this paper, we propose a generative tracking method based on a novel robust linear regression algorithm. In contrast to existing methods, the proposed Least Soft-thresold Squares (LSS) algorithm models the error term with the Gaussian-Laplacian distribution, which can be solved efficiently. Based on maximum joint likelihood of parameters, we derive a LSS distance to measure the difference between an observation sample and the dictionary. Compared with the distance derived from ordinary least… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 136 CITATIONS, ESTIMATED 99% COVERAGE

Object tracking based on Huber loss function

  • The Visual Computer
  • 2018
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Structured and weighted multi-task low rank tracker

  • Pattern Recognition
  • 2018
VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Robust Discriminative Tracking via Landmark-Based Label Propagation

  • IEEE Transactions on Image Processing
  • 2015
VIEW 15 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Adaptive Appearance Modeling With Point-to-Set Metric Learning for Visual Tracking

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2017
VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Generalized ℓP-regularized representation for visual tracking

  • Neurocomputing
  • 2016
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Nonlinear metric learning for visual tracking

  • 2016 IEEE International Conference on Multimedia and Expo (ICME)
  • 2016
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Patch-based scale calculation for visual tracking

  • 2015 International Conference on Wireless Communications & Signal Processing (WCSP)
  • 2015
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Visual Object Tracking by Structure Complexity Coefficients

  • IEEE Transactions on Multimedia
  • 2015
VIEW 19 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 32 Highly Influenced Citations

  • Averaged 17 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Incremental Learning for Robust Visual Tracking

  • International Journal of Computer Vision
  • 2007
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Face-TLD: Tracking-Learning-Detection applied to faces

  • 2010 IEEE International Conference on Image Processing
  • 2010
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Online Object Tracking With Sparse Prototypes

  • IEEE Transactions on Image Processing
  • 2013
VIEW 2 EXCERPTS

Decomposing and regularizing sparse/non-sparse components for motion field estimation

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 1 EXCERPT

Object Tracking via 2DPCA and $\ell_{1}$-Regularization

  • IEEE Signal Processing Letters
  • 2012
VIEW 1 EXCERPT

Pixel-Wise Spatial Pyramid-Based Hybrid Tracking

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2012

Real time robust L1 tracker using accelerated proximal gradient approach

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 2 EXCERPTS