FastNet: Fast high-resolution network for human pose estimation

作者：

Highlights：

• FastNet outperforms popular lightweight networks on human pose estimation.

• The asymmetric bottleneck module can extract keypoint features with multi-scale.

• The waterfall module can obtain delicate local representations.

摘要

Highlights•FastNet outperforms popular lightweight networks on human pose estimation.•The asymmetric bottleneck module can extract keypoint features with multi-scale.•The waterfall module can obtain delicate local representations.

论文关键词：Human pose estimation,FastNet,Asymmetric bottleneck module,Waterfall module

论文评审过程：Received 21 August 2021, Revised 15 January 2022, Accepted 17 January 2022, Available online 22 January 2022, Version of Record 1 February 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104390