LieNet-master

Zhiwu Huang, Chengde Wan, Thomas Probst, Luc Van Gool. Deep Learning on Lie Groups for Skeleton-based Action Recognition, In Proc. CVPR 2017.

Version 1.0, Copyright(c) November, 2017.

Note that the copyright of the manopt toolbox is reserved by https://www.manopt.org/

Usage

Step1: Place the <a href="https://data.vision.ee.ethz.ch/zzhiwu/ManifoldNetData/LieData/G3D_Lie_data.zip"> G3D </a> LieGroup data under the folder "./data/g3d/".

Step2: Launch lienet_g3d.m for a simple example.

Related Work/Implementation

1. Thanks to Oleg Smirnov who is Sr. Applied Scientist at Amazon, a <a href="https://github.com/master/tensorflow-manopt"> TensorFlow ManOpt </a> library is released to reproduce our LieNet.

How to Cite <a name="How-to-Cite"></a>

If you find this project helpful, please consider citing us as follows:

@inproceedings{huang2017lienet,
      title = {Deep Learning on Lie Groups for Skeleton-based Action Recognition},
      author    = {Huang, Zhiwu and
                   Wan, Chengde and
                   Probst, Thomas and
                   Van Gool, Luc},
      year = {2017},
      booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition (CVPR)}
}