Code for the BMVC paper (http://bmvc2018.org/contents/papers/1003.pdf)
Official repository for the code from BMVC (British Machine Vision Conference) paper "Part-based Graph Convolutional Network for Action Recognition". The implementation is done in Pytorch and works on it's recent stable version. The repository includes:
TODOs:
unzip nturgbd_skeletons_s001_to_s017.zip -d nturgb+d_skeletons
git clone https://github.com/kalpitthakkar/pb-gcn.git
bash download_checkpoints.sh <path_to_download_directory>
First of all, we need to define the required configuration variables in the YAML file. The instructions on it's structure and editing the file are here.
Once the configuration file is ready, you can start training the model:
python run.py --config <path_to_YAML_config_file>
For citing our paper:
@article{thakkar2018part,
title={Part-based Graph Convolutional Network for Action Recognition},
author={Thakkar, Kalpit and Narayanan, PJ},
journal={arXiv preprint arXiv:1809.04983},
year={2018}
}