Modeling transition patterns between events for temporal human action segmentation and classification

@article{Kim2015ModelingTP,
  title={Modeling transition patterns between events for temporal human action segmentation and classification},
  author={Yelin Kim and Jixu Chen and Ming-Ching Chang and Xin Wang and Emily Mower Provost and Siwei Lyu},
  journal={2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)},
  year={2015},
  volume={1},
  pages={1-8}
}
We propose a temporal segmentation and classification method that accounts for transition patterns between events of interest. We apply this method to automatically detect salient human action events from videos. A discriminative classifier (e.g., Support Vector Machine) is used to recognize human action events and an efficient dynamic programming algorithm is used to jointly determine the starting and ending temporal segments of recognized human actions. The key difference from previous work… CONTINUE READING
9 Citations
30 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 30 references

and F

  • D. Huang, Y. Wang, S. Yao
  • De la Torre. Sequential max-margin event…
  • 2014

F

  • F. Zhou
  • De la Torre, and J. K. Hodgins. Hierarchical…
  • 2013

Similar Papers

Loading similar papers…