AutoMR: A Universal Time Series Motion Recognition Pipeline
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929724075278336 |
|---|---|
| author | Zhang, Likun Yang, Sicheng Wang, Zhuo Liang, Haining Shen, Junxiao |
| author_facet | Zhang, Likun Yang, Sicheng Wang, Zhuo Liang, Haining Shen, Junxiao |
| contents | In this paper, we present an end-to-end automated motion recognition (AutoMR) pipeline designed for multimodal datasets. The proposed framework seamlessly integrates data preprocessing, model training, hyperparameter tuning, and evaluation, enabling robust performance across diverse scenarios. Our approach addresses two primary challenges: 1) variability in sensor data formats and parameters across datasets, which traditionally requires task-specific machine learning implementations, and 2) the complexity and time consumption of hyperparameter tuning for optimal model performance. Our library features an all-in-one solution incorporating QuartzNet as the core model, automated hyperparameter tuning, and comprehensive metrics tracking. Extensive experiments demonstrate its effectiveness on 10 diverse datasets, achieving state-of-the-art performance. This work lays a solid foundation for deploying motion-capture solutions across varied real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15228 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AutoMR: A Universal Time Series Motion Recognition Pipeline Zhang, Likun Yang, Sicheng Wang, Zhuo Liang, Haining Shen, Junxiao Computer Vision and Pattern Recognition Artificial Intelligence In this paper, we present an end-to-end automated motion recognition (AutoMR) pipeline designed for multimodal datasets. The proposed framework seamlessly integrates data preprocessing, model training, hyperparameter tuning, and evaluation, enabling robust performance across diverse scenarios. Our approach addresses two primary challenges: 1) variability in sensor data formats and parameters across datasets, which traditionally requires task-specific machine learning implementations, and 2) the complexity and time consumption of hyperparameter tuning for optimal model performance. Our library features an all-in-one solution incorporating QuartzNet as the core model, automated hyperparameter tuning, and comprehensive metrics tracking. Extensive experiments demonstrate its effectiveness on 10 diverse datasets, achieving state-of-the-art performance. This work lays a solid foundation for deploying motion-capture solutions across varied real-world applications. |
| title | AutoMR: A Universal Time Series Motion Recognition Pipeline |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.15228 |