Fitting Product of HMM to Human Motions
The Product of Hidden Markov Models (PoHMM) is a mixed graphical model defining a probability distribution on a sequence space from the normalized product of several simple Hidden Markov Models (HMMs). Here, we use this model to approach the human action recognition task incorporating mixture-Gaussian output distributions. PoHMM allow us to consider context at different range and to model different dynamics corresponding to different body parts in an efficient way. For estimating the normalization constant Z we introduce the annealed importance sampling (AIS) method in the context of PoHMM in order to obtain no-relative estimates of Z. We compare our approach with one based on fitting a logistic regression model to each two PoHMMs.
Keywordspartition function PoHMM human action recognition
Unable to display preview. Download preview PDF.
- 2.Brown, A., Hinton, G.E.: Products of hidden markov models. Artificial Intelligence and Statistics, 3–11 (2001)Google Scholar
- 6.Salakhutdinov, R., Murray, I.: On the quantitative analysis of deep belief networks. In: Proceedings of the Int. conf. on Machine Learning, vol. 25, pp. 872–879 (2008)Google Scholar
- 7.Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. Pattern Recognition 3(1), 32–36 (2004)Google Scholar
- 8.Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. Computer Vision 2, 726–733 (2003)Google Scholar