EUVIMEDEUVIMED entdecken
Crossref

FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion

Dian Shao, Mingfei Shi, Like Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (11) · 8842-8850

DOI: 10.1609/aaai.v40i11.37838 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Dian Shao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recognizing fine-grained actions from temporally corrupted skeleton sequences remains a significant challenge, particularly in real-world scenarios where online pose estimation often yields substantial missing data. Existing methods often struggle to accurately recover temporal dynamics and fine-grained spatial structures, resulting in the loss of subtle motion cues crucial for distinguishing similar actions. To address this, we propose FineTec, a unified framework for Fine-grained action recognition under Temporal Corruption. FineTec first restores a base skeleton sequence from corrupted input using context-aware completion with diverse temporal masking. Next, a skeleton-based spatial decomposition module partitions the skeleton into five semantic regions, further divides them into dynamic and static subgroups based on motion variance, and generates two augmented skeleton sequences via targeted perturbation. These, along with the base sequence, are then processed by a physics-driven estimation module, which utilizes Lagrangian dynamics to estimate joint accelerations. Finally, both the fused skeleton position sequence and the fused acceleration sequence are jointly fed into a GCN-based action recognition head. Extensive experiments on both coarse-grained (NTU-60, NTU-120) and fine-grained (Gym99, Gym288) benchmarks show that FineTec significantly outperforms previous methods under various levels of temporal corruption. Specifically, FineTec achieves top-1 accuracies of 89.1% and 78.1% on the challenging Gym99-severe and Gym288-severe settings, respectively, demonstrating its robustness and generalizability.

Zitieren

APA

Shao, D., Shi, M., & Liu, L. (2026). FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(11), 8842-8850. https://doi.org/10.1609/aaai.v40i11.37838

Vancouver

Shao D, Shi M, Liu L. FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(11):8842-8850. doi:10.1609/aaai.v40i11.37838

BibTeX
@article{Shao2026,
  author = {Shao, Dian and Shi, Mingfei and Liu, Like},
  title = {FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {11},
  pages = {8842--8850},
  doi = {10.1609/aaai.v40i11.37838}
}
Kostenlos starten →