# Human Pose Estimation using Global and Local Normalization

arXiv: https://arxiv.org/abs/1709.07220 · HTML: https://mlsanity.com/paper/1709.07220/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2017.

## Built on by (most cited first, 10 of 10)

- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Location-free Human Pose Estimation](https://mlsanity.com/paper/2205.12619/) (2022)
- [Error Estimation for Single-Image Human Body Mesh Reconstruction](https://mlsanity.com/paper/2305.17245/) (2023)
- [A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios](https://mlsanity.com/paper/2311.00401/) (2023)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Multi-Person Human Motion Forecasting in Complex Scenes](https://mlsanity.com/paper/2608.27039/) (2026)

## Abstract (arXiv)

In this paper, we address the problem of estimating the positions of human joints, i.e., articulated pose estimation. Recent state-of-the-art solutions model two key issues, joint detection and spatial configuration refinement, together using convolutional neural networks. Our work mainly focuses on spatial configuration refinement by reducing variations of human poses statistically, which is motivated by the observation that the scattered distribution of the relative locations of joints e.g., the left wrist is distributed nearly uniformly in a circular area around the left shoulder) makes the learning of convolutional spatial models hard. We present a two-stage normalization scheme, human body normalization and limb normalization, to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation. In addition, our empirical results show that incorporating multi-scale supervision and multi-scale fusion into the joint detection network is beneficial. Experiment results demonstrate that our method consistently outperforms state-of-the-art methods on the benchmarks.