# BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports

Source: [BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports](<https://www.sota2.com/research/paper/68fa7b5f1e209131cea87f97>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-02T05:00:04.464Z

Authors: Jing-Yuan Chang

Published: 2025-02-28T14:18:39.000Z

## Abstract

Badminton, known for having the fastest ball speeds among all sports, presents significant challenges to the field of computer vision, including player identification, court line detection, shuttlecock trajectory tracking, and player stroke-type classification. In this paper, we introduce a novel video clipping strategy to extract frames of each player's racket swing in a badminton broadcast match. These clipped frames are then processed by three existing models: one for Human Pose Estimation to obtain human skeletal joints, another for shuttlecock trajectory tracking, and the other for court line detection to determine player positions on the court. Leveraging these data as inputs, we propose Badminton Stroke-type Transformer (BST) to classify player stroke-types in singles. To the best of our knowledge, experimental results demonstrate that our method outperforms the previous state-of-the-art on the largest publicly available badminton video dataset (ShuttleSet), another badminton dataset (BadmintonDB), and a tennis dataset (TenniSet). These results suggest that effectively leveraging ball trajectory is a promising direction for action recognition in racket sports.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Action Recognition on ShuttleSet 35 classes fixed-width strategy (test)](<https://www.sota2.com/research/sota/action-recognition-on-shuttleset-35-classes-fixed-width-strategy-test.md>): Action Recognition; ShuttleSet 35 classes fixed-width strategy (test); Accuracy: 76.95.

- [Action Recognition on ShuttleSet fixed-width strategy 25 classes](<https://www.sota2.com/research/sota/action-recognition-on-shuttleset-fixed-width-strategy-25-classes.md>): Action Recognition; ShuttleSet fixed-width strategy 25 classes; Accuracy: 82.54.

- [Action Recognition on BadmintonDB 18 classes (test)](<https://www.sota2.com/research/sota/action-recognition-on-badmintondb-18-classes-test.md>): Action Recognition; BadmintonDB 18 classes (test); Accuracy: 0.6517.

- [Action Recognition on TenniSet 6 classes (test)](<https://www.sota2.com/research/sota/action-recognition-on-tenniset-6-classes-test.md>): Action Recognition; TenniSet 6 classes (test); Accuracy: 99.23.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.21085>)

[PDF](<https://arxiv.org/pdf/2502.21085.pdf>)
