Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition

Liu, Ye and Wu, Tianyong and Shi, Tianhao and Wang, Miaohui and Gao, Hao and Liu, Jun (2025) Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition. IEEE Transactions on Industrial Informatics. ISSN 1551-3203

Text (TII-24-3242.R1_Proof_hi)
TII-24-3242.R1_Proof_hi.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (2MB)

Abstract

In recent years, remarkable progress has been made in skeleton-based action recognition. However, there is a significant amount of noise in skeleton data, which is simply overlooked by most existing methods. Some methods have designed specialized mechanisms to handle noise, but these mechanisms are either based on prior knowledge or require additional supervision information. To overcome these problems, we propose in this article a fully implicit solution, which embeds a soft-thresholding-based denoising module into existing networks, which can automatically learn to remove noise without any prior knowledge or additional supervision information. In addition, by relaxing the nonnegative constraint, the module gains the ability to adaptively enhance key features. Based on this, we further propose a two-staged method for coupled noise suppression and feature enhancement. The proposed method achieves state-of-the-art performance on public datasets. Moreover, on noise polluted datasets, the proposed method demonstrates significant performance advantages over existing methods.