Action Recognition with Improved Trajectories

@article{Wang2013ActionRW,
  title={Action Recognition with Improved Trajectories},
  author={Heng Wang and Cordelia Schmid},
  journal={2013 IEEE International Conference on Computer Vision},
  year={2013},
  pages={3551-3558}
}
Recently dense trajectories were shown to be an efficient video representation for action recognition and achieved state-of-the-art results on a variety of datasets. This paper improves their performance by taking into account camera motion to correct them. To estimate camera motion, we match feature points between frames using SURF descriptors and dense optical flow, which are shown to be complementary. These matches are, then, used to robustly estimate a homography with RANSAC. Human motion… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,390 CITATIONS, ESTIMATED 43% COVERAGE

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 421 Highly Influenced Citations

  • Averaged 334 Citations per year over the last 3 years

  • 2% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 43 REFERENCES

Similar Papers

Loading similar papers…