Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition

@article{Su2014RateInvariantAO,
  title={Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition},
  author={Jingyong Su and Anuj Srivastava and Fillipe D. M. de Souza and Sudeep Sarkar},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={620-627}
}
In statistical analysis of video sequences for speech recognition, and more generally activity recognition, it is natural to treat temporal evolutions of features as trajectories on Riemannian manifolds. However, different evolution patterns result in arbitrary parameterizations of these trajectories. We investigate a recent framework from statistics literature that handles this nuisance variability using a cost function/distance for temporal registration and statistical summarization… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS
24 Citations
21 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Similar Papers

Loading similar papers…