Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
2017-11-28Code Available0· sign in to hype
Kenji Matsui, Toru Tamaki, Gwladys Auffret, Bisser Raytchev, Kazufumi Kaneda
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Gauffret/TrajectorySetOfficialIn papernone★ 0
Abstract
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 .