This document summarizes a technique for human action recognition based on spatio-temporal features. The technique uses Lucas-Kanade optical flow to extract motion features and Viola-Jones features to extract shape features from localized regions of interest in video frames. These motion and shape features are combined over a period of time to form spatio-temporal features, which are then classified using AdaBoost to recognize different human actions. The technique is applied to the Weizman human action dataset and achieves accurate action recognition results.