Global video representation comparison

Download code to reproduce results in the Tech report:

Michael Sapienza, Fabio Cuzzolin, Philip H.S. Torr, Feature sampling and partitioning for visual vocabulary generation on large action classification datasets,

Department of Computing and Communications Technology, Oxford Brookes University, and Department of Engineering Science, Univerisity of Oxford, 2014. [pdf - BibTex]

Usage:

1) Add folder to current MATLAB directory and set the path to the toolkit directory: /home/your_folders/global_video_representation_comparison

2) Run "demo.m"

(Tested on MATLAB 2011a + Ubuntu 12.04 64bit)

Download