Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
This work addresses action recognition for computer vision applications, but it is incremental as it builds on improved Dense Trajectories.
The authors tackled action recognition by proposing the Trajectory-Set (TS) feature, which encodes only trajectories around interest points without appearance features, and achieved an accuracy of 85.4% on HMDB51, outperforming a deep method's 80.2%.
We propose a feature for action recognition called Trajectory-Set (TS), on top of the improved Dense Trajectory (iDT). The TS feature encodes only trajectories around densely sampled interest points, without any appearance features. Experimental results on the UCF50, UCF101, and HMDB51 action datasets demonstrate that TS is comparable to state-of-the-arts, and outperforms many other methods; for HMDB the accuracy of 85.4%, compared to the best accuracy of 80.2% obtained by a deep method. Our code is available on-line at https://github.com/Gauffret/TrajectorySet .