This repository will contain the official code for our pre-print: Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity. This work was also presented at the 2023 CV4Animals workshop at CVPR!
Code will be made available soon!
This code will also be integrated in DeepLabCut!
We are grateful to the authors of HRNet and MIPNet as our code builds on their work!
If you find this code useful, please cite:
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity by Mu Zhou*, Lucas Stoffl*, Mackenzie Mathis and Alexander Mathis.
@misc{zhou2023rethinking,
title={Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity},
author={Mu Zhou and Lucas Stoffl and Mackenzie Mathis and Alexander Mathis},
year={2023},
eprint={2306.07879},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
BUCTD will be released under the Apache 2.0 license. Please see the LICENSE file for more information.