SIFT Accordion: A Space-Time Descriptor Applied to Human Action Recognition

  title={SIFT Accordion: A Space-Time Descriptor Applied to Human Action Recognition},
  author={Ben El Fadhl Ahmed},
Recognizing human action from videos is an active field of research in computer vision and pattern recognition. Human activity recognition has many potential applications such as video surveillance, human machine interaction, sport videos retrieval and robot navigation. Actually, local descriptors and bag of visuals words models achieve state-of-the-art performance for human action recognition. The main challenge in features description is how to represent efficiently the local motion… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 29 references

A Complete Non predictive VideoCompression Scheme Based on a 3 D to 2 D Geometric transform ”

  • W. Ayedi Ouni
  • Proceedings of International Conference on Image…
  • 2010

A Survey of Vision-Based Methods for Action Representation, Segmentation and Recognition

  • D. Weinland, E.R.Ronfard
  • Computer Vision and Image Understanding
  • 2010

Focused Action Localization in Video

  • A. Klaser, M. Marsza lek, C. Schmid, A. Zisserman, ”Human
  • in International Workshop on Sign,
  • 2010

Similar Papers

Loading similar papers…