Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910840957960192 |
|---|---|
| author | Shan, Ziwei He, Yaoyu Zhao, Chengfeng Du, Jiashen Zhang, Jingyan Zhang, Qixuan Yu, Jingyi Xu, Lan |
| author_facet | Shan, Ziwei He, Yaoyu Zhao, Chengfeng Du, Jiashen Zhang, Jingyan Zhang, Qixuan Yu, Jingyi Xu, Lan |
| contents | Human bodily movements convey critical insights into action intentions and cognitive processes, yet existing multimodal systems primarily focused on understanding human motion via language, vision, and audio, which struggle to capture the dynamic forces and torques inherent in 3D motion. Inertial measurement units (IMUs) present a promising alternative, offering lightweight, wearable, and privacy-conscious motion sensing. However, processing of streaming IMU data faces challenges such as wireless transmission instability, sensor noise, and drift, limiting their utility for long-term real-time motion capture (MoCap), and more importantly, online motion analysis. To address these challenges, we introduce Mojito, an intelligent motion agent that integrates inertial sensing with large language models (LLMs) for interactive motion capture and behavioral analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16175 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens Shan, Ziwei He, Yaoyu Zhao, Chengfeng Du, Jiashen Zhang, Jingyan Zhang, Qixuan Yu, Jingyi Xu, Lan Computer Vision and Pattern Recognition Artificial Intelligence Graphics Human bodily movements convey critical insights into action intentions and cognitive processes, yet existing multimodal systems primarily focused on understanding human motion via language, vision, and audio, which struggle to capture the dynamic forces and torques inherent in 3D motion. Inertial measurement units (IMUs) present a promising alternative, offering lightweight, wearable, and privacy-conscious motion sensing. However, processing of streaming IMU data faces challenges such as wireless transmission instability, sensor noise, and drift, limiting their utility for long-term real-time motion capture (MoCap), and more importantly, online motion analysis. To address these challenges, we introduce Mojito, an intelligent motion agent that integrates inertial sensing with large language models (LLMs) for interactive motion capture and behavioral analysis. |
| title | Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2502.16175 |