Deterministic Initialization of Hidden Markov Models for Human Action Recognition

@article{Moghaddam2009DeterministicIO,
  title={Deterministic Initialization of Hidden Markov Models for Human Action Recognition},
  author={Zia Moghaddam and Massimo Piccardi},
  journal={2009 Digital Image Computing: Techniques and Applications},
  year={2009},
  pages={188-195}
}
Human action recognition is often approached in terms of probabilistic models such as the hidden Markov model or other graphical models. When learning such models by way of Expectation-Maximisation algorithms, arbitrary choices must be made for their initial parameters. Often, solutions for the selection of the initial parameters are based on random functions. However, in this paper, we argue that deterministic alternatives are preferable, and propose various methods. Experiments on a video… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 20 references

Action recognition by learning mid-level motion features

2008 IEEE Conference on Computer Vision and Pattern Recognition • 2008
View 1 Excerpt

Action recognition using weighted three-state Hidden Markov Model

2008 9th International Conference on Signal Processing • 2008
View 3 Excerpts

Machine Recognition of Human Activities: A Survey

IEEE Transactions on Circuits and Systems for Video Technology • 2008
View 1 Excerpt

View-invariant action recognition using fundamental ratios

2008 IEEE Conference on Computer Vision and Pattern Recognition • 2008
View 1 Excerpt

Actions as Space-Time Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2007
View 2 Excerpts

Human activity recognition with action primitives

2007 IEEE Conference on Advanced Video and Signal Based Surveillance • 2007
View 1 Excerpt

Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model

2007 IEEE Conference on Computer Vision and Pattern Recognition • 2007
View 2 Excerpts

A Survey of Advances in Vision-Based Human Motion Capture and Analysis

T. B. Moeslund, A. Hilton, V. Kru ̈ger
Computer Vision and Image Understanding, vol. 104, no. 2-3, 2006, pp. 90-126. • 2006
View 1 Excerpt

Similar Papers

Loading similar papers…