Foreground-Driven Contrastive Learning for Unsupervised Human Keypoint Detection

Human keypoint detection has significant value in computer vision tasks such as human-machine interaction. Recently, unsupervised human keypoint detection has become prevalent due to concerns about data privacy. Most existing methods are based on a reconstruction process that extracts appearance and...

Full description

Bibliographic Details

Published in:	IEEE Photonics Journal
Main Authors:	Shuxian Li, Hui Luo, Zhengwei Miao, Zhixing Wang, Qiliang Bao, Jianlin Zhang
Format:	Article
Language:	English
Published:	IEEE 2025-01-01
Subjects:	Unsupervised learning human keypoint detection unsupervised segmentation network global and local contrastive learning
Online Access:	https://ieeexplore.ieee.org/document/10989733/