SAGCN: Self-Attention Graph Convolutional Network for Human Pose Embedding

Accurate human pose embedding is crucial for action recognition. While traditional convolutional neural networks (CNNs) have advanced pose feature extraction, they struggle to model structural relationships and long-range dependencies between keypoints, and are less robust to occlusions. To address...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Zhongxiong Xu, Jiajun Hong, Yicong Yu, Chengzhu Lin, Linfei Yu, Meixian Xu
Format:	Article
Language:	English
Published:	IEEE 2025-01-01
Subjects:	Graph convolutional network self-attention human pose embedding probabilistic embedding
Online Access:	https://ieeexplore.ieee.org/document/11119677/