# Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

arXiv: https://arxiv.org/abs/1911.10529 · HTML: https://mlsanity.com/paper/1911.10529/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2019.

## Built on by (most cited first, 27 of 27)

- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing](https://mlsanity.com/paper/2103.04570/) (2021)
- [HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar](https://mlsanity.com/paper/2210.12564/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation](https://mlsanity.com/paper/2109.03622/) (2021)
- [Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation](https://mlsanity.com/paper/2208.00090/) (2022)
- [Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection](https://mlsanity.com/paper/2305.01652/) (2023)
- [MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos](https://mlsanity.com/paper/2512.10881/) (2025)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression](https://mlsanity.com/paper/2210.04014/) (2022)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Morphology-Aware Interactive Keypoint Estimation](https://mlsanity.com/paper/2209.07163/) (2022)
- [Real-time Pose Estimation from Images for Multiple Humanoid Robots](https://mlsanity.com/paper/2107.02675/) (2021)
- [Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging](https://mlsanity.com/paper/2510.21654/) (2025)
- [SpaDen : Sparse and Dense Keypoint Estimation for Real-World Chart Understanding](https://mlsanity.com/paper/2308.01971/) (2023)
- [Incremental Learning for Animal Pose Estimation using RBF k-DPP](https://mlsanity.com/paper/2110.13598/) (2021)
- [X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention](https://mlsanity.com/paper/2310.08042/) (2023)
- [Attend-and-Refine: Interactive keypoint estimation and quantitative cervical vertebrae analysis for bone age assessment](https://mlsanity.com/paper/2507.07670/) (2025)
- [Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation](https://mlsanity.com/paper/2107.03098/) (2021)
- [SHOP: A Deep Learning Based Pipeline for near Real-Time Detection of Small Handheld Objects Present in Blurry Video](https://mlsanity.com/paper/2203.15228/) (2022)
- [Towards High Performance One-Stage Human Pose Estimation](https://mlsanity.com/paper/2301.04842/) (2023)
- [Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/2303.14888/) (2023)
- [Spatial Attention-based Distribution Integration Network for Human Pose Estimation](https://mlsanity.com/paper/2311.05323/) (2023)
- [Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation](https://mlsanity.com/paper/2410.03174/) (2024)
- [RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild](https://mlsanity.com/paper/2604.07331/) (2026)

## Abstract (arXiv)

We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to hard keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available online.