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
  • Ye Liu
  • Tianyong Wu
  • Tianhao Shi
  • Miaohui Wang
  • Hao Gao
  • Jun Liu
Close
<mark>Journal publication date</mark>30/04/2025
<mark>Journal</mark>IEEE Transactions on Industrial Informatics
Issue number4
Volume21
Number of pages10
Pages (from-to)3017-3026
Publication StatusPublished
Early online date20/01/25
<mark>Original language</mark>English

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.