Efficient human action recognition by cascaded linear classifcation

We present a human action recognition system suitable for very short sequences. In particular, we estimate Histograms of Oriented Gradients (HOGs) for the current frame as well as the corresponding dense flow field estimated from two frames. The thus obtained descriptors are then efficiently represented by the coefficients of a Nonnegative Matrix Factorization (NMF). To further speed up the overall process, we apply an efficient cascaded Linear Discriminant Analysis (CLDA) classifier. In the experimental results we show the benefits of the proposed approach on standard benchmark datasets as well as on more challenging and realistic videos. In addition, since other state-of-the-art methods apply weighting between different cues, we provide a detailed analysis of the importance of weighting for action recognition and show that weighting is not necessarily required for the given task.