Cascade dictionary learning for action recognition

In this paper, we propose a cascade dictionary learning algorithm for action recognition. In the first stage, a dictionary for basic sparse coding is learned based on local descriptors. And then spatial pyramid features are extracted to represent all the images in the same dimensions. Instead of performing dimension reduction, all the features are regrouped and then fed into second dictionary learning. In the second stage, a supervised dictionary for block and group sparse coding is learned to get discriminative representations based on the regrouped features. Without lowering classification performance, the size of the second dictionary is much smaller than other dictionary based on spatial pyramid features. We evaluate our algorithm on two publicly available databases about action recognition: Willows and People Playing Music Instrument. The numerical results show the effectiveness of the proposed algorithm.