T3Set: Table Tennis Training Multimodal Dataset

This is the dataset for the KDD'25 (dataset and benchmark track) full paper "T3Set: A Multimodal Dataset with Targeted Suggestions for LLM-based Virtual Coach in Table Tennis Training".

T3Set (Table Tennis Training) is a multimodal dataset with aligned video-sensor-text data in table tennis training. The key features of T3Set include (1)temporal alignment between sensor data, video data, and text data. (2)high-quality targeted suggestions which are consistent with predefined suggestion taxonomy.

The scripts we used for dataset construction and data cleaning processes, are provided in the Github Repo: https://github.com/jima-cs/t3set

If you find this dataset useful, please cite our paper:  
```bibtex  
@inproceedings{
    ma2025t3set,
    title={T3Set: A Multimodal Dataset with Targeted Suggestions for LLM-based Virtual Coach in Table Tennis Training},
    author = {Ma, Ji and Wu, Jiale and Wang, Haoyu and Zhang, Yanze and Xie, Xiao and Zhou, Zheng and Zhang, Hui and Wang, Jiachen and Wu, Yingcai},
    year={2025},
    booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2},
    doi={10.1145/3711896.3737407}
    pages = {5686–5697},
    numpages = {12},
    publisher = {Association for Computing Machinery}
}  
```