mlsanityData to 14 Oct 2026

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

arXiv 2106.15304 ↗First posted 6 Jun 2021cs.CVcited by 5

Not on the map. Why?

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.

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

14 of 18 references.

References · 14

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  3. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  4. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  5. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  6. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  7. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  8. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  9. 2018Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPosecited by 42
  10. 2020YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Designcited by 24
  11. 2020NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Accelerationcited by 16
  12. 2020EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimationcited by 12
2 more
  1. 2020Achieving Real-Time LiDAR 3D Object Detection on a Mobile Devicecited by 3
  2. 2020Real-Time Execution of Large-scale Language Models on Mobilecited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 0; 2024: 2.

5 papers.

  1. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  2. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  3. 2021A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Posecited by 21
  4. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  5. 2024DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphonescited by 4