Spatio-temporal Event Classification Using Time-Series Kernel Based Structured Sparsity

@article{Jeni2014SpatiotemporalEC,
  title={Spatio-temporal Event Classification Using Time-Series Kernel Based Structured Sparsity},
  author={L{\'a}szl{\'o} A. Jeni and Andr{\'a}s L{\"o}rincz and Zolt{\'a}n Szab{\'o} and Jeffrey F. Cohn and Takeo Kanade},
  journal={Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision},
  year={2014},
  volume={2014},
  pages={135-140}
}
In many behavioral domains, such as facial expression and gesture, sparse structure is prevalent. This sparsity would be well suited for event detection but for one problem. Features typically are confounded by alignment error in space and time. As a consequence, high-dimensional representations such as SIFT and Gabor features have been favored despite their much greater computational cost and potential loss of information. We propose a Kernel Structured Sparsity (KSS) method that can handle… CONTINUE READING
Highly Cited
This paper has 22 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 13 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 42 references

Ground truth FACS action unit coding on the group formation task

  • J. Girard, J. Cohn
  • Tech. rep., University of Pittsburgh
  • 2013
1 Excerpt

Universal Motion-Based Control and Motion Recognition

  • M. Chen
  • Ph.D. thesis, Georgia Institute of Technology
  • 2013

Similar Papers

Loading similar papers…