Name
Abstract | ||
|---|---|---|
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 the 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. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/CVPR.2019.01112 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Inference,Source code,Computer science,Pose,Interference (wave propagation),Artificial intelligence,Machine learning,Graph model | Journal | abs/1812.00324 |
ISSN | Citations | PageRank |
1063-6919 | 10 | 0.46 |
References | Authors | |
15 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jiefeng Li | 1 | 21 | 3.65 |
| Can Wang | 2 | 10 | 0.46 |
| Hao Zhu | 3 | 13 | 1.51 |
| Yihuan Mao | 4 | 10 | 0.46 |
| Haoshu Fang | 5 | 57 | 6.86 |
| Cewu Lu | 6 | 993 | 62.08 |