Pith

open record

sign in
Browse

arxiv: 1711.10143 · v1 · pith:Y3TKSR2E · submitted 2017-11-28 · cs.CV

Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:Y3TKSR2Erecord.jsonopen to challenge →

classification cs.CV
keywords actionfeatureaccuracydenseimprovedrecognitiontrajectoriesappearance
0
0 comments X
read the original 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 .

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.