EUVIMEDEUVIMED entdecken
Crossref

PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction

Kanglei Zhou, Hubert P H Shum, Frederick W B Li, Xingxing Zhang, Xiaohui Liang

IEEE Transactions on Image Processing · 2025 · 34 · 3718-3732

DOI: 10.1109/tip.2025.3574938 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Kanglei Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Long-term Action Quality Assessment (AQA) aims to evaluate the quantitative performance of actions in long videos. However, existing methods face challenges due to domain shifts between the pre-trained large-scale action recognition backbones and the specific AQA task, thereby hindering their performance. This arises since fine-tuning resource-intensive backbones on small AQA datasets is impractical. We address this by identifying two levels of domain shift: task-level, regarding differences in task objectives, and feature-level, regarding differences in important features. For feature-level shifts, which are more detrimental, we propose Progressive Hierarchical Instruction (PHI) with two strategies. First, Gap Minimization Flow (GMF) leverages flow matching to progressively learn a fast flow path that reduces the domain gap between initial and desired features across shallow to deep layers. Additionally, a temporally-enhanced attention module captures long-range dependencies essential for AQA. Second, List-wise Contrastive Regularization (LCR) facilitates coarse-to-fine alignment by comprehensively comparing batch pairs to learn fine-grained cues while mitigating domain shift. Integrating these modules, PHI offers an effective solution. Experiments demonstrate that PHI achieves state-of-the-art performance on three representative long-term AQA datasets, proving its superiority in addressing the domain shift for long-term AQA.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhou, K., Shum, H. P. H., Li, F. W. B., Zhang, X., & Liang, X. (2025). PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction. IEEE Transactions on Image Processing, 34, 3718-3732. https://doi.org/10.1109/tip.2025.3574938

Vancouver

Zhou K, Shum HPH, Li FWB, Zhang X, Liang X. PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction. IEEE Transactions on Image Processing. 2025;34:3718-3732. doi:10.1109/tip.2025.3574938

BibTeX
@article{Zhou2025,
  author = {Zhou, Kanglei and Shum, Hubert P H and Li, Frederick W B and Zhang, Xingxing and Liang, Xiaohui},
  title = {PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {3718--3732},
  doi = {10.1109/tip.2025.3574938}
}
Kostenlos starten →