Enhanced spatiotemporal skeleton modeling: integrating part-joint attention with dynamic graph convolution

Abstract Human motion prediction and action recognition are critical tasks in computer vision and human-computer interaction, supporting applications in surveillance, robotics, and behavioral analysis. However, effectively capturing the fine-grained semantics and dynamic spatiotemporal dependencies...

Full description

Bibliographic Details

Published in:	Scientific Reports
Main Authors:	Yanghong Qin, Shengrui Liu, Chunhong Yuan
Format:	Article
Language:	English
Published:	Nature Portfolio 2025-10-01
Subjects:	Patiotemporal skeleton modeling Part-joint attention Dynamic graph convolutional network Human motion prediction Action recognition
Online Access:	https://doi.org/10.1038/s41598-025-18520-x