Self-Supervised Action Representation Learning Based on Asymmetric Skeleton Data Augmentation

Self-Supervised Action Representation Learning Based on Asymmetric Skeleton Data Augmentation

Contrastive learning has received increasing attention in the field of skeleton-based action representations in recent years. Most contrastive learning methods use simple augmentation strategies to construct pairs of positive samples. When using such pairs of positive samples to learn action represe...

Full description

Bibliographic Details
Main Authors: Hualing Zhou, Xi Li, Dahong Xu, Hong Liu, Jianping Guo, Yihan Zhang
Format: Article
Language:English
Published: MDPI AG 2022-11-01
Series:Sensors
Subjects:
action representation
contrastive learning
data augmentation
self-supervised
Online Access:https://www.mdpi.com/1424-8220/22/22/8989

Internet

https://www.mdpi.com/1424-8220/22/22/8989

Similar Items