Review article · 2025 · Open access

A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions

Yi Liu, Ruyi Liu, Yuzhi Hu, Mengyao Wu, Wentian Xin, Qiguang Miao, Shuai Wu, Long Li

IEEE Transactions on Neural Networks and Learning Systems, 37(5), 2046–2065 · Published 8 December 2025 · DOI 10.1109/tnnls.2025.3632689

Open full textView at the publisherCite this paper

In brief

“A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions” is a 2025 review article by Yi Liu and 7 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 33 citations as of 17 November 2026, which puts it in the top 1% of works published in 2025 by citations. It is open access: the full text is free to read at SSRN Electronic Journal.

Citations
33
Most cited in
2026 (32)
Field-weighted impact
1.53
References
177
Authors
8

Abstract

Human action recognition (HAR), which aims to recognize and understand individual actions and intentions, has rapidly become a research hotspot in computer vision. Compared with other data modalities, skeleton data offers more efficient node semantics and more coherent spatio-temporal motion patterns, effectively reducing the impact of lighting and background changes. In recent years, many researchers have focused on skeleton-based action recognition methods and have made significant progress. However, we believe that the current skeleton-based action recognition methods still face three major challenges: 1) reducing reliance on expensive labeled data while maintaining model performance; 2) enabling the model to understand and recognize new behavior classes with a limited number of samples; and 3) addressing the challenges posed by the lack of skeleton information in single-modality spatio-temporal motion representation learning. Based on these challenges, we conduct a comprehensive review of the existing skeleton-based action recognition methods. Additionally, we provide an extensive review and analysis of publicly available action recognition datasets. This review aims to offer researchers a comprehensive perspective, stimulate more innovative ideas, and promote the application and breakthrough of skeleton action recognition in a wider range of computer vision tasks.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Liu, Y., Liu, R., Hu, Y., Wu, M., Xin, W., Miao, Q., Wu, S., & Li, L. (2025). A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions. IEEE Transactions on Neural Networks and Learning Systems, 37(5), 2046–2065. https://doi.org/10.1109/tnnls.2025.3632689

MLA 9

Liu, Yi, et al. “A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions.” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 5, 2025, pp. 2046–2065. https://doi.org/10.1109/tnnls.2025.3632689.

Chicago

Liu, Yi, Ruyi Liu, Yuzhi Hu, Mengyao Wu, Wentian Xin, Qiguang Miao, Shuai Wu, and Long Li. 2025. “A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions.” IEEE Transactions on Neural Networks and Learning Systems 37 (5): 2046–2065. https://doi.org/10.1109/tnnls.2025.3632689.

Harvard

Liu, Y. et al. (2025) ‘A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions’, IEEE Transactions on Neural Networks and Learning Systems, 37(5), pp. 2046–2065. doi:10.1109/tnnls.2025.3632689.

IEEE

Y. Liu et al., “A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions,” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 5, pp. 2046–2065, 2025, doi: 10.1109/tnnls.2025.3632689.

BibTeX

@article{liu2025systematic,
  title     = {{A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions}},
  author    = {Liu, Yi and Liu, Ruyi and Hu, Yuzhi and Wu, Mengyao and Xin, Wentian and Miao, Qiguang and Wu, Shuai and Li, Long},
  journal   = {IEEE Transactions on Neural Networks and Learning Systems},
  year      = {2025},
  volume    = {37},
  number    = {5},
  pages     = {2046--2065},
  doi       = {10.1109/tnnls.2025.3632689},
  url       = {https://doi.org/10.1109/tnnls.2025.3632689}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition

  • skeleton-based action recognition
  • human action recognition
  • limited labeled data
  • few-shot learning
  • skeleton data

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Liu, Y., Liu, R., Hu, Y., Wu, M., Xin, W., Miao, Q., Wu, S., & Li, L. (2025). A Systematic Review of Skeleton-Based Action Recognition: Methods, Challenges, and Future Directions. IEEE Transactions on Neural Networks and Learning Systems, 37(5), 2046–2065. https://doi.org/10.1109/tnnls.2025.3632689

How many times has this paper been cited?

33 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at SSRN Electronic Journal: sign in and open the full text from this page.

Who wrote this paper?

Yi Liu, Ruyi Liu, Yuzhi Hu, Mengyao Wu, Wentian Xin, Qiguang Miao, Shuai Wu, Long Li.

What is the DOI of this paper?

10.1109/tnnls.2025.3632689, permanently at https://doi.org/10.1109/tnnls.2025.3632689. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.