On-line deep learning method for action recognition

  title={On-line deep learning method for action recognition},
  author={Konstantinos Charalampous and Antonios Gasteratos},
  journal={Pattern Analysis and Applications},
In this paper an unsupervised on-line deep learning algorithm for action recognition in video sequences is proposed. Deep learning models capable of deriving spatio-temporal data have been proposed in the past with remarkable results, yet, they are mostly restricted to building features from a short window length. The model presented here, on the other hand, considers the entire sample sequence and extracts the description in a frame-by-frame manner. Each computational node of the proposed… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 10 extracted citations


Publications referenced by this paper.
Showing 1-10 of 86 references

How the brain might work: a hierarchical and temporal model for learning and recognition

  • D. George
  • Ph.D. thesis, Stanford, CA, USA
  • 2008
Highly Influential
11 Excerpts

Similar Papers

Loading similar papers…