English

Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization

Computer Vision and Pattern Recognition 2026-05-25 v1 Machine Learning Multimedia

Abstract

Temporal Action Localization (TAL) has been extensively studied in generic video understanding, while fine-grained sports scenarios, such as professional badminton, remain underexplored due to their complex and subtle spatio-temporal dynamics. In this paper, we focus on fine-grained TAL in professional badminton videos and introduce a new benchmark dataset, Fine-Badminton, which consists of 31 matches with 29 fine-grained stroke categories, covering 2104 rallies and 27597 annotated actions. To effectively capture the intricate motion patterns in such scenarios, we propose a Decoupling Spatio-Temporal Adapter (DSTA), which enables efficient modeling of spatio-temporal features within a parameter-efficient framework. Specifically, DSTA decomposes motion representation into three parallel branches, capturing temporal dynamics as well as vertical and horizontal spatial variations. The design allows the model to better distinguish subtle differences among fine-grained actions. Extensive experiments on both the Fine-Badminton dataset and the ShuttleSet benchmark demonstrate that the proposed method achieves state-of-the-art performance while introducing only a marginal increase in computational and parameter cost. These results validate the effectiveness and efficiency of the proposed approach for fine-grained temporal action localization.

Cite

@article{arxiv.2605.23355,
  title  = {Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization},
  author = {Tianyu Wang and Junjie Wu and Jingquan Gao and Shishuo Li},
  journal= {arXiv preprint arXiv:2605.23355},
  year   = {2026}
}

Comments

11 pages, 11figures