Accepted author manuscript, 2.07 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition
AU - Liu, Ye
AU - Wu, Tianyong
AU - Shi, Tianhao
AU - Wang, Miaohui
AU - Gao, Hao
AU - Liu, Jun
PY - 2025/4/30
Y1 - 2025/4/30
N2 - 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.
AB - 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.
U2 - 10.1109/tii.2024.3519783
DO - 10.1109/tii.2024.3519783
M3 - Journal article
VL - 21
SP - 3017
EP - 3026
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
SN - 1551-3203
IS - 4
ER -