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

November 28, 2017 · Entered Twilight · 🏛 arXiv.org

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, BSD_LICENCE.txt, LGPL_LICENSE, LICENCE, README.md, README.md~, TrajectorySet

Authors Kenji Matsui, Toru Tamaki, Gwladys Auffret, Bisser Raytchev, Kazufumi Kaneda arXiv ID 1711.10143 Category cs.CV: Computer Vision Citations 0 Venue arXiv.org Repository https://github.com/Gauffret/TrajectorySet ⭐ 8 Last Checked 2 months ago

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 .