Improving bag-of-features action recognition with non-local cues

@inproceedings{Ullah2010ImprovingBA,
  title={Improving bag-of-features action recognition with non-local cues},
  author={Muhammad Muneeb Ullah and Sobhan Naderi Parizi and Ivan Laptev},
  booktitle={BMVC},
  year={2010}
}
Local space-time features have recently shown promising results within Bag-of-Features (BoF) approach to action recognition in video. Pure local features and descriptors, however, provide only limited discriminative power implying ambiguity among features and sub-optimal classification performance. In this work, we propose to disambiguate local space-time features and to improve action recognition by integrating additional nonlocal cues with BoF representation. For this purpose, we decompose… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 98 CITATIONS

Human Action Recognition for Real-time Applications

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Action recognition by dense trajectories

VIEW 6 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Action recognition by Huffman coding and implicit action model

  • 2015 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)
  • 2015
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Continuous Action Recognition Based on Sequence Alignment

  • International Journal of Computer Vision
  • 2014
VIEW 5 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Graph-based approach for human action recognition using spatio-temporal features

  • J. Visual Communication and Image Representation
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Motion Based Foreground Detection and Poselet Motion Features for Action Recognition

VIEW 3 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Spatio-temporal pyramidal accordion representation for human action recognition

  • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
VIEW 5 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Dense Trajectories and Motion Boundary Descriptors for Action Recognition

  • International Journal of Computer Vision
  • 2012
VIEW 1 EXCERPT
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2010
2018

CITATION STATISTICS

  • 11 Highly Influenced Citations

  • Averaged 6 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Randomized Clustering Forests for Image Classification

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2008
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Actions in context

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Learning realistic human actions from movies

  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

On feature combination for multiclass object classification

  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
VIEW 2 EXCERPTS

Scalable Recognition with a Vocabulary Tree

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT