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

Source: [Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation](<https://www.sota2.com/research/paper/68fa66b61e209131cea12052>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:11:40.194Z

Authors: Jia Li, Wen Su, Zengfu Wang

Published: 2019-11-24T13:51:38.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Keypoint Detection on MS COCO 2017 (test-dev)](<https://www.sota2.com/research/sota/keypoint-detection-on-ms-coco-2017-test-dev.md>): Keypoint Detection; MS COCO 2017 (test-dev); AP: 68.1.

- [Multi-Person Pose Estimation on COCO (test-dev)](<https://www.sota2.com/research/sota/multi-person-pose-estimation-on-coco-test-dev.md>): Multi-person Pose Estimation; COCO (test-dev); AP: 64.6.

- [Human Pose Estimation on COCO 2017 (test-dev)](<https://www.sota2.com/research/sota/human-pose-estimation-on-coco-2017-test-dev.md>): Human Pose Estimation; COCO 2017 (test-dev); AP: 68.5.

- [2D Human Pose Estimation on COCO 2017 (val)](<https://www.sota2.com/research/sota/2d-human-pose-estimation-on-coco-2017-val.md>): 2D Human Pose Estimation; COCO 2017 (val); AP: 66.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.10529>)

[PDF](<https://arxiv.org/pdf/1911.10529.pdf>)

[Implementation](<https://github.com/jialee93/Improved-Body-Parts>)
