We propose a new method for human action recognition based on multiple features and a hybrid generative/discriminative model. Specifically, we propose a new action representation based on computing a rich set of descriptors from Affine-SIFT key point trajectories. A new hybrid generative/discriminative approach based on support vector machine and topic model is proposed using Fisher kernel method for action recognition. Fisher score for the topic model is evaluated by the variational inference algorithm. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors and demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular datasets, show performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature.
"Action recognition using spatiotemporal features and hybrid generative/discriminative models," Journal of Electronic Imaging 21(2), 023010 (22 May 2012). https://doi.org/10.1117/1.JEI.21.2.023010