Journal article · 2026 · Open access
Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization
IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15 · Published 6 October 2026 · DOI 10.1109/tpami.2026.3741078
In brief
“Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization” is a 2026 journal article by Kanglei Zhou and 6 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 10 citations as of 18 November 2026, which puts it in the top 2% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Durham Research Online (Durham University).
- Citations
- 10
- Most cited in
- 2026 (10)
- Field-weighted impact
- 13.22
- References
- 71
- Authors
- 7
Abstract
Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization of conventional methods. We introduce Continual AQA (CAQA), which equips AQA with Continual Learning (CL) capabilities to handle evolving distributions while mitigating catastrophic forgetting. Although parameter-efficient fine-tuning of pretrained models has shown promise in CL for image classification, we find it insufficient for CAQA. Our empirical and theoretical analyses reveal two insights: (i) Full-Parameter Fine-Tuning (FPFT) is necessary for effective representation learning; yet (ii) uncontrolled FPFT induces overfitting and feature manifold shift, thereby aggravating forgetting. To address this, we propose Adaptive Manifold Aligned Graph Regularization (MAGR++), which couples back bone fine-tuning that stabilizes shallow layers while adapting deeper ones with a two-step feature rectification pipeline: a manifold projector to translate deviated historical features into the current representation space, and a graph regularizer to align local and global distributions. We construct four CAQA benchmarks from three datasets with tailored evaluation protocols and strong baselines, enabling systematic cross-dataset comparison. Extensive experiments show that MAGR++ achieves state-of-the-art performance, with average correlation gains of 3.6% offline and 12.2% online over the strongest baseline, confirming its robustness and effectiveness.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhou, K., Pan, Q., Zhang, X., Shum, H. P. H., Li, F. W. B., Liang, X., & Wang, L. (2026). Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15. https://doi.org/10.1109/tpami.2026.3741078
MLA 9
Zhou, Kanglei, et al. “Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tpami.2026.3741078.
Chicago
Zhou, Kanglei, Qingyi Pan, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang, and Liyuan Wang. 2026. “Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–15. https://doi.org/10.1109/tpami.2026.3741078.
Harvard
Zhou, K. et al. (2026) ‘Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–15. doi:10.1109/tpami.2026.3741078.
IEEE
K. Zhou et al., “Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–15, 2026, doi: 10.1109/tpami.2026.3741078.
BibTeX
@article{zhou2026continual,
title = {{Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization}},
author = {Zhou, Kanglei and Pan, Qingyi and Zhang, Xingxing and Shum, Hubert P. H. and Li, Frederick W. B. and Liang, Xiaohui and Wang, Liyuan},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {PP},
pages = {1--15},
doi = {10.1109/tpami.2026.3741078},
url = {https://doi.org/10.1109/tpami.2026.3741078}
}
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
- action quality assessment
- continual learning
- catastrophic forgetting
- manifold alignment
- graph regularization
- full-parameter fine-tuning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Zhou, K., Pan, Q., Zhang, X., Shum, H. P. H., Li, F. W. B., Liang, X., & Wang, L. (2026). Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–15. https://doi.org/10.1109/tpami.2026.3741078
How many times has this paper been cited?
10 times, according to OpenAlex on 18 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 Durham Research Online (Durham University): sign in and open the PDF from this page.
Who wrote this paper?
Kanglei Zhou, Qingyi Pan, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang, Liyuan Wang.
What is the DOI of this paper?
10.1109/tpami.2026.3741078, permanently at https://doi.org/10.1109/tpami.2026.3741078. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 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.