2D Box
2D Keypoints
Pose Estimation
License: Unknown


Multi-person pose estimation is fundamental to many computer vision tasks and has made significant progress in recent years. However, few previous methods explored the problem of pose estimation in crowded scenes while it remains challenging and inevitable in many scenarios. Moreover, current benchmarks cannot provide an appropriate evaluation for such cases. In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms. Our model consists of two key components: joint-candidate single person pose estimation (SPPE) and global maximum joints association. With multi-peak prediction for each joint and global association using graph model, our method is robust to inevitable interference in crowded scenes and very efficient in inference. The proposed method surpasses the state-of-the-art methods on CrowdPose dataset by 5.2 mAP and results on MSCOCO dataset demonstrate the generalization ability of our method. Source code and dataset will be made publicly available.


We provide evaluation tools for CrowdPose dataset. Our evaluation tools is developed based on @cocodataset/cocoapi. The source code of our model has been integrated into AlphaPose.

CrowdPose API (based on COCO API)

To install:

  • For Python, run "sh" under coco/PythonAPI


If you find our works useful in your reasearch, please consider citing:

  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
Data Summary
Provided by
Shanghai Jiao Tong University
Shanghai Jiao Tong University (SJTU), as one of the higher education institutions which enjoy a long history and a world-renowned reputation in China.
Start Building AI Now