Quo Vadis, Skeleton Action Recognition ?
This repository contains datasets and scripts for the paper Quo Vadis, Skeleton Action Recognition ?, accepted for publication at International Journal of Computer Vision IJCV .
This paper primarily contributes towards benchmarking of exisiting skeleton human action recognition models on larger datasets like NTU-120 and also provides insight on how these models performs for in the wild data as well.
We also introduce 3 new skeleton human action datasets:
The details about each of these datasets can be found in skeletics-152 README, skeleton-mimetics README and metaphorics README.
Pre Trained models
This repository contains pre-trained model weights for all the models that were trained as mentioned in the paper. The weights of different models for different datasets can be found here
Scripts
The scripts needed to parse VIBE skeleton data into usable VA-CNN and GCN formats can be found here
Citation
@article{Gupta2021,
author={Gupta, Pranay and Thatipelli, Anirudh and Aggarwal, Aditya and Maheshwari, Shubh and Trivedi, Neel and Das, Sourav and Sarvadevabhatla, Ravi Kiran},
title={Quo Vadis, Skeleton Action Recognition?},
journal={International Journal of Computer Vision},
year={2021},
month={May},
day={05},
issn={1573-1405},
doi={10.1007/s11263-021-01470-y},
url={https://doi.org/10.1007/s11263-021-01470-y}
}