Home > Research > Publications & Outputs > Coupled Noise Suppression and Feature Enhanceme...

Associated organisational unit

Electronic data

  • TII-24-3242.R1_Proof_hi

    Accepted author manuscript, 2.07 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

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

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition. / Liu, Ye; Wu, Tianyong; Shi, Tianhao et al.
In: IEEE Transactions on Industrial Informatics, Vol. 21, No. 4, 30.04.2025, p. 3017-3026.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Liu, Y, Wu, T, Shi, T, Wang, M, Gao, H & Liu, J 2025, 'Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition', IEEE Transactions on Industrial Informatics, vol. 21, no. 4, pp. 3017-3026. https://doi.org/10.1109/tii.2024.3519783

APA

Liu, Y., Wu, T., Shi, T., Wang, M., Gao, H., & Liu, J. (2025). Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition. IEEE Transactions on Industrial Informatics, 21(4), 3017-3026. https://doi.org/10.1109/tii.2024.3519783

Vancouver

Liu Y, Wu T, Shi T, Wang M, Gao H, Liu J. Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition. IEEE Transactions on Industrial Informatics. 2025 Apr 30;21(4):3017-3026. Epub 2025 Jan 20. doi: 10.1109/tii.2024.3519783

Author

Liu, Ye ; Wu, Tianyong ; Shi, Tianhao et al. / Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition. In: IEEE Transactions on Industrial Informatics. 2025 ; Vol. 21, No. 4. pp. 3017-3026.

Bibtex

@article{771c9bbf2d39493892d51b89fe1c8dc7,
title = "Coupled Noise Suppression and Feature Enhancement Network for Skeleton-Based Action Recognition",
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.",
author = "Ye Liu and Tianyong Wu and Tianhao Shi and Miaohui Wang and Hao Gao and Jun Liu",
year = "2025",
month = apr,
day = "30",
doi = "10.1109/tii.2024.3519783",
language = "English",
volume = "21",
pages = "3017--3026",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Computer Society",
number = "4",

}

RIS

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 -