@article{xu2021vipnas,
title={ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search},
author={Xu, Lumin and Guan, Yingda and Jin, Sheng and Liu, Wentao and Qian, Chen and Luo, Ping and Ouyang, Wanli and Wang, Xiaogang},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
year={2021}
}
@inproceedings{lin2014microsoft,
title={Microsoft coco: Common objects in context},
author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
booktitle={European conference on computer vision},
pages={740--755},
year={2014},
organization={Springer}
}
Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset
Arch | Input Size | AP | AP50 | AP75 | AR | AR50 | ckpt | log |
---|---|---|---|---|---|---|---|---|
S-ViPNAS-MobileNetV3 | 256x192 | 0.700 | 0.887 | 0.783 | 0.758 | 0.929 | ckpt | log |
S-ViPNAS-Res50 | 256x192 | 0.711 | 0.894 | 0.787 | 0.769 | 0.934 | ckpt | log |