CVOct 28, 2019
Towards Good Practices for Multi-Person Pose Estimation
arXiv:1911.07938v1
Originality Synthesis-oriented
AI Analysis
This work addresses pose estimation for computer vision applications, but it is incremental as it builds on existing methods.
The paper tackles multi-person pose estimation by refining MSPN and PoseFix networks, achieving 78.7 on COCO test-dev and 76.3 on COCO test-challenge datasets.
Multi-Person Pose Estimation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the MSPN and PoseFix Networks, and empirically evaluate their impact on the final model performance through ablation studies. By taking all the refinements, we achieve 78.7 on the COCO test-dev dataset and 76.3 on the COCO test-challenge dataset.