Proceedings

Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices

Xuan Shen, Geng Yuan, Wei Niu, Xiaolong Ma, Jiexiong Guan, Zhengang Li, Bin Ren, Yanzhi Wang

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Demo Track. Pages 5012-5015.

https://doi.org/10.24963/ijcai.2021/715

Keywords

  • Human-Computer Interaction: General
  • Computer Vision: General
  • Machine Learning: General

Abstract

The rapid development of autonomous driving, abnormal behavior detection, and behavior recognition makes an increasing demand for multi-person pose estimation-based applications, especially on mobile platforms. However, to achieve high accuracy, state-of-the-art methods tend to have a large model size and complex post-processing algorithm, which costs intense computation and long end-to-end latency. To solve this problem, we propose an architecture optimization and weight pruning framework to accelerate inference of multi-person pose estimation on mobile devices. With our optimization framework, we achieve up to 2.51X faster model inference speed with higher accuracy compared to representative lightweight multi-person pose estimator.

Xuan Shen, Geng Yuan, Wei Niu, Xiaolong Ma, Jiexiong Guan, Zhengang Li, Bin Ren, and Yanzhi Wang. 2021. Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 5012–5015. https://doi.org/10.24963/ijcai.2021/715
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards