Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition

@article{Yuan2014ModelingGC,
  title={Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition},
  author={Chunfeng Yuan and Xi Li and Weiming Hu and Haibin Ling and Stephen J. Maybank},
  journal={IEEE Transactions on Image Processing},
  year={2014},
  volume={23},
  pages={658-672}
}
In this paper, we present a new geometric-temporal representation for visual action recognition based on local spatio-temporal features. First, we propose a modified covariance descriptor under the log-Euclidean Riemannian metric to represent the spatio-temporal cuboids detected in the video sequences. Compared with previously proposed covariance descriptors, our descriptor can be measured and clustered in Euclidian space. Second, to capture the geometric-temporal contextual information, we… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 11 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 59 REFERENCES

HAn efficient Bayesian framework for on-line action recognition

  • R. HVezzani, H M. HPiccardi, H R. HCucchiara
  • Proc. HInf. Conf. Image Process., pp. 3553-3556…
  • 2009
Highly Influential
10 Excerpts

Performance Evaluation of the Covariance Descriptor for Target Detection

  • H HP.C.Cargill, HC.U. RiusH, HD. MeryH, A. Soto
  • Proc. Int. Conf. Chilean Computer Science Society…
  • 2009
Highly Influential
8 Excerpts

Similar Papers

Loading similar papers…