Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose

Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose

Abstract Three-dimensional (3D) human pose recognition techniques based on spatial data have gained attention. However, existing models and algorithms fail to achieve desired precision. We propose a 3D human motion pose recognition method using deep contrastive learning and an improved Transformer....

Full description

Bibliographic Details
Main Authors: Datian Liu, Haitao Yang, Zhang Lei
Format: Article
Language:English
Published: Springer 2023-10-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Pose recognition
Three-dimensional human motion
Deep contrastive learning
Improved transformer
Depth image
Pose feature
Online Access:https://doi.org/10.1007/s44196-023-00351-1

Internet

https://doi.org/10.1007/s44196-023-00351-1

Similar Items