Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.11698 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909788451897344 |
|---|---|
| author | Yeh, Wei-Hsin Su, Yu-An Chen, Chih-Ning Lin, Yi-Hsueh Ku, Calvin Chiu, Wen-Hsin Hu, Min-Chun Ku, Lun-Wei |
| author_facet | Yeh, Wei-Hsin Su, Yu-An Chen, Chih-Ning Lin, Yi-Hsueh Ku, Calvin Chiu, Wen-Hsin Hu, Min-Chun Ku, Lun-Wei |
| contents | Motion instruction is a crucial task that helps athletes refine their technique by analyzing movements and providing corrective guidance. Although recent advances in multimodal models have improved motion understanding, generating precise and sport-specific instruction remains challenging due to the highly domain-specific nature of sports and the need for informative guidance. We propose CoachMe, a reference-based model that analyzes the differences between a learner's motion and a reference under temporal and physical aspects. This approach enables both domain-knowledge learning and the acquisition of a coach-like thinking process that identifies movement errors effectively and provides feedback to explain how to improve. In this paper, we illustrate how CoachMe adapts well to specific sports such as skating and boxing by learning from general movements and then leveraging limited data. Experiments show that CoachMe provides high-quality instructions instead of directions merely in the tone of a coach but without critical information. CoachMe outperforms GPT-4o by 31.6% in G-Eval on figure skating and by 58.3% on boxing. Analysis further confirms that it elaborates on errors and their corresponding improvement methods in the generated instructions. You can find CoachMe here: https://motionxperts.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11698 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoachMe: Decoding Sport Elements with a Reference-Based Coaching Instruction Generation Model Yeh, Wei-Hsin Su, Yu-An Chen, Chih-Ning Lin, Yi-Hsueh Ku, Calvin Chiu, Wen-Hsin Hu, Min-Chun Ku, Lun-Wei Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.7; I.2.10 Motion instruction is a crucial task that helps athletes refine their technique by analyzing movements and providing corrective guidance. Although recent advances in multimodal models have improved motion understanding, generating precise and sport-specific instruction remains challenging due to the highly domain-specific nature of sports and the need for informative guidance. We propose CoachMe, a reference-based model that analyzes the differences between a learner's motion and a reference under temporal and physical aspects. This approach enables both domain-knowledge learning and the acquisition of a coach-like thinking process that identifies movement errors effectively and provides feedback to explain how to improve. In this paper, we illustrate how CoachMe adapts well to specific sports such as skating and boxing by learning from general movements and then leveraging limited data. Experiments show that CoachMe provides high-quality instructions instead of directions merely in the tone of a coach but without critical information. CoachMe outperforms GPT-4o by 31.6% in G-Eval on figure skating and by 58.3% on boxing. Analysis further confirms that it elaborates on errors and their corresponding improvement methods in the generated instructions. You can find CoachMe here: https://motionxperts.github.io/ |
| title | CoachMe: Decoding Sport Elements with a Reference-Based Coaching Instruction Generation Model |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.7; I.2.10 |
| url | https://arxiv.org/abs/2509.11698 |