Action recognition via sparse representation of characteristic frames

For achieving efficient action recognition, some recent works propose to select a smaller number of frames in a video sequence instead of the entire sequence of frames. In this study, we propose to represent a frame by a combination of local and global descriptors instead of the silhouette used in our previous approach aiming at frame selection. Action recognition is then executed on the basis of the selected frames. The experiment on KTH database shows that the selected frames by the proposed framework are, in the minimum number to achieve the best recognition rate, better than those by two compared selection ways.