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

arXiv: https://arxiv.org/abs/2106.15304 · HTML: https://mlsanity.com/paper/2106.15304/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 6 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose](https://mlsanity.com/paper/1811.12004/) (2018)
- [YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design](https://mlsanity.com/paper/2009.05697/) (2020)
- [NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration](https://mlsanity.com/paper/2012.00596/) (2020)
- [EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation](https://mlsanity.com/paper/2007.08090/) (2020)
- [Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device](https://mlsanity.com/paper/2012.13801/) (2020)
- [Real-Time Execution of Large-scale Language Models on Mobile](https://mlsanity.com/paper/2009.06823/) (2020)

## Built on by (most cited first, 5 of 5)

- [Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection](https://mlsanity.com/paper/2207.10955/) (2022)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose](https://mlsanity.com/paper/2111.12696/) (2021)
- [GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation](https://mlsanity.com/paper/2407.10756/) (2024)
- [DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones](https://mlsanity.com/paper/2407.13777/) (2024)

## Abstract (arXiv)

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.