Action and Event Recognition with Fisher Vectors on a Compact Feature Set

@article{Oneata2013ActionAE,
  title={Action and Event Recognition with Fisher Vectors on a Compact Feature Set},
  author={Dan Oneata and Jakob J. Verbeek and Cordelia Schmid},
  journal={2013 IEEE International Conference on Computer Vision},
  year={2013},
  pages={1817-1824}
}
Action recognition in uncontrolled video is an important and challenging computer vision problem. Recent progress in this area is due to new local features and models that capture spatio-temporal structure between local features, or human-object interactions. Instead of working towards more complex models, we focus on the low-level features and their encoding. We evaluate the use of Fisher vectors as an alternative to bag-of-word histograms to aggregate a small set of state-of-the-art low-level… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 285 CITATIONS

Deep Learning for Fixed Model Reuse

VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Modeling spatio-temporal layout with Lie Algebrized Gaussians for action recognition

  • Multimedia Tools and Applications
  • 2015
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Motion Words for Videos

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

How Shall We Evaluate Egocentric Action Recognition?

  • 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
  • 2017
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Cluster trees of improved trajectories for action recognition

  • Neurocomputing
  • 2016
VIEW 10 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Going Deeper into Action Recognition: A Survey

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Machine learning solutions to visual recognition problems

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Tracking Salient Keypoints for Human Action Recognition

  • 2015 IEEE International Conference on Systems, Man, and Cybernetics
  • 2015
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 28 Highly Influenced Citations

  • Averaged 31 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 46 REFERENCES

Actions in context

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Large-scale web video event classification by use of Fisher Vectors

  • 2013 IEEE Workshop on Applications of Computer Vision (WACV)
  • 2013
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Multimodal feature fusion for robust event detection in web videos

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Action Recognition with Improved Trajectories

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 1 EXCERPT

Better Exploiting Motion for Better Action Recognition

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 2 EXCERPTS

Explicit Modeling of Human-Object Interactions in Realistic Videos

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
VIEW 1 EXCERPT