Learning Delicate Local Representations for Multi-Person Pose Estimation

Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo, Binyi Yin, Angang Du, Haoqian Wang, Xiangyu Zhang, Xinyu Zhou, Erjin Zhou, Jian Sun

ECCV 2020

doi:10.1007/978-3-030-58580-8_27 /eccv/2020/cai2020eccv-learning/

Abstract

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/

PDF ECCV Semantic Scholar

Cite

Text

Cai et al. "Learning Delicate Local Representations for Multi-Person Pose Estimation." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58580-8_27

Markdown

[Cai et al. "Learning Delicate Local Representations for Multi-Person Pose Estimation." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/cai2020eccv-learning/) doi:10.1007/978-3-030-58580-8_27

BibTeX

@inproceedings{cai2020eccv-learning,
  title     = {{Learning Delicate Local Representations for Multi-Person Pose Estimation}},
  author    = {Cai, Yuanhao and Wang, Zhicheng and Luo, Zhengxiong and Yin, Binyi and Du, Angang and Wang, Haoqian and Zhang, Xiangyu and Zhou, Xinyu and Zhou, Erjin and Sun, Jian},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58580-8_27},
  url       = {https://mlanthology.org/eccv/2020/cai2020eccv-learning/}
}