CONFIDENT SEMANTIC RANKING LOSS FOR PART PARSING
If training from scratch, simply run. If not, customize the dir in /experiments/CSR config.py.
@inproceedings{tan2021confident,
title={Confident Semantic Ranking Loss for Part Parsing},
author={Tan, Xin and Xu, Jiachen and Ye, Zhou and Hao, Jinkun and Ma, Lizhuang},
booktitle={2021 IEEE International Conference on Multimedia and Expo (ICME)},
pages={1--6},
year={2021},
organization={IEEE}
}