Learning weighted features for human action recognition

In traditional bag-of-words method, each local feature is treated evenly for representation. One disadvantage of this method is that it is not robust to noise, which makes the performance impaired. In this paper, a novel human action recognition approach which learns weights for features is proposed, where each feature is assigned a weight for human action representation. These weights are learned jointly with discriminative model. There are two advantages of our model. First, small weights are assigned to noise, which can help to reduce the effect of noise on representation of human action. Second, discriminative features, which are critical for human action recognition, are assigned large weights. Experimental results demonstrate the advantages of the proposed method.