Local spatio-temporal interest point detection for human action recognition

This paper presents a unified action recognition framework combining harris3D descriptor with 3D SIFT detector. We perform action recognition experiments on the KTH dataset using Support Vector Machines. Experiments apply the leave-one-out and compare our proposed approach with state-of-the-art methods. The result shows that our proposed approach is effective. Compared with other approaches our approach is more robust, easier to compute.