Towards Simple and Accurate Human Pose Estimation With Stair Network

Chenru Jiang, Kaizhu Huang*, Shufei Zhang, Xinheng Wang, Jimin Xiao, Zhenxing Niu, Amir Hussain

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


In this paper, we focus on tackling the precise keypoint coordinates regression task. Most existing approaches adopt complicated networks with a large number of parameters, leading to a heavy model with poor cost-effectiveness in practice. To overcome this limitation, we develop a small yet discrimicative model called STair Network, which can be simply stacked towards an accurate multi-stage pose estimation system. Specifically, to reduce computational cost, STair Network is composed of novel basic feature extraction blocks which focus on promoting feature diversity and obtaining rich local representations with fewer parameters, enabling a satisfactory balance on efficiency and performance. To further improve the performance, we introduce two mechanisms with negligible computational cost, focusing on feature fusion and replenish. We demonstrate the effectiveness of the STair Network on two standard datasets, e.g., 1-stage STair Network achieves a higher accuracy than HRNet by 5.5% on COCO test dataset with 80% fewer parameters and 68% fewer GFLOPs.

Original languageEnglish
Pages (from-to)805-817
Number of pages13
JournalIEEE Transactions on Emerging Topics in Computational Intelligence
Issue number3
Publication statusPublished - 1 Jun 2023


  • Stair network
  • feature diversity
  • human pose estimation


Dive into the research topics of 'Towards Simple and Accurate Human Pose Estimation With Stair Network'. Together they form a unique fingerprint.

Cite this