Self-Supervised 3D Skeleton Representation Learning with Active Sampling and Adaptive Relabeling for Action Recognition

Self-supervised 3D skeleton representation learning has recently shown great potential for action recognition via contrastive learning. However, existing methods suffer from limited learning efficiency and the unreliability of representations, which is not conducive to action recognition. To this en...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 56 - 60
Main Authors Wang, Guoquan, Liu, Hong, Guo, Tianyu, Guo, Jingwen, Wang, Ti, Li, Yidi
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
3D skeleton representation learning
action recognition
active sampling
adaptive relabeling
Bones
Dictionaries
Image recognition
Learning systems
Reliability
Representation learning
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Self-supervised 3D skeleton representation learning has recently shown great potential for action recognition via contrastive learning. However, existing methods suffer from limited learning efficiency and the unreliability of representations, which is not conducive to action recognition. To this end, we propose an Active Sampling and Adaptive Relabeling (ASAR) contrastive learning method to achieve efficient and reliable learning of 3D skeleton representations. Specifically, the active sampling strategy is used to build a dictionary with informative samples for efficient representation learning. Additionally, the adaptive relabeling strategy is proposed to automatically modify the confidence scores of the extra positive samples and alleviate the unreliability of representations. Extensive experiments on NTU-60, NTU-120, and PKU-MMD datasets demonstrate the superiority of our approach.
DOI:10.1109/ICIP49359.2023.10221961