Classification of human actions using pose-based features and stacked auto encoder

•Human action recognition using pose-based features is proposed.•Use of key movements of actions for efficient input representation.•Unsupervised pre-training using stacked auto encoder is exploited. [Display omitted] In this paper, we propose a method for classification of human actions using pose based features. We demonstrate that statistical information of key movements of actions can be utilized in designing an efficient input representation, using fuzzy membership functions. The ability of stacked auto encoder to learn the underlying features of input data is exploited to recognize human actions. The efficacy of the proposed approach is demonstrated on CMU MOCAP and Berkeley MHAD datasets.