EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

A Graph Convolutional Network for Action Recognition in Occluded Skeleton Data

Sicheng Jin, Kai Hu, Shuai Shen, Yongkai Cai, Chengxue Cai

Electronics · 2026-05-26 · 15 (11) · 2311

DOI: 10.3390/electronics15112311 ↗

At a glance

Journal article in Electronics, published online on 2026-05-26. Written by Sicheng Jin and 4 co-authors. 47 references. The full text is freely available (open access, CC BY 4.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Skeleton-based human action recognition has achieved significant progress, but local occlusions and missing joints in complex environments (e.g., occlusion and low-light conditions) still degrade recognition accuracy and stability. Existing GCN-based methods aggregate features uniformly across joints and lack mechanisms to suppress unreliable observations or recover structural semantics under large-area occlusion. To address this, we propose a Robust Occlusion-Compensated Graph Convolutional Network (ROC-GCN) with two complementary components: an adaptive dropout module that suppresses spatiotemporal noise via attention-guided Bernoulli sampling with dynamic spatial–temporal fusion, and an Occlusion Compensation Graph Convolution Module that compensates occluded features through Local–Global Body-Prior-Guided Attention together with feature-guided and multi-hop aggregation. To enable systematic evaluation, we further construct two complementary occlusion benchmarks on NTU RGB+D 60/120 covering spatial-random and spatiotemporal-continuous occlusion, and additionally validate the model on a real-world missing-joint subset. On standard NTU60/120 X-Sub, ROC-GCN improves Top-1 accuracy by +0.41% and +0.48% over the baseline, with the Top-1 standard deviation reduced from 0.61 → 0.17 and 0.47 → 0.10. On the occlusion benchmarks, Top-1 accuracy further improves by +0.98% and +0.73%, and consistent gains are also observed on the real-world missing-joint validation, confirming improved robustness and training stability.

Cite

APA

Jin, S., Hu, K., Shen, S., Cai, Y., & Cai, C. (2026). A Graph Convolutional Network for Action Recognition in Occluded Skeleton Data. Electronics, 15(11), 2311. https://doi.org/10.3390/electronics15112311

Vancouver

Jin S, Hu K, Shen S, Cai Y, Cai C. A Graph Convolutional Network for Action Recognition in Occluded Skeleton Data. Electronics. 2026;15(11):2311. doi:10.3390/electronics15112311

BibTeX
@article{Jin2026,
  author = {Jin, Sicheng and Hu, Kai and Shen, Shuai and Cai, Yongkai and Cai, Chengxue},
  title = {A Graph Convolutional Network for Action Recognition in Occluded Skeleton Data},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {2311},
  doi = {10.3390/electronics15112311}
}
Start for free →