Model card: arXiv:2611.08969 and citation
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- physiowave
|
| 5 |
- physiowave-t
|
|
@@ -16,6 +17,8 @@ library_name: pytorch
|
|
| 16 |
|
| 17 |
# PhysioWave-T-sEMG: multi-route pretrained sEMG encoder
|
| 18 |
|
|
|
|
|
|
|
| 19 |
One of the three **PhysioWave-T** encoders ([EEG](https://huggingface.co/ForeverBlue/EEG), [ECG](https://huggingface.co/ForeverBlue/ECG), sEMG); the [RALF fusion model](https://huggingface.co/ForeverBlue/RALF-SeizeIT2) combines them. Code: <https://github.com/ForeverBlue816/PhysioWave>.
|
| 20 |
|
| 21 |
Masked dual-reconstruction pretraining on surface EMG from wristbands, forearm arrays and high-density grids. One shared transformer serves three electrode layouts through route-specific wavelet frontends, and electrode identity enters as a learned embedding of the electrode NAME rather than of its index.
|
|
@@ -226,6 +229,27 @@ mismatch rather than silently training on relabelled channels.
|
|
| 226 |
|
| 227 |
Code: <https://github.com/ForeverBlue816/PhysioWave>
|
| 228 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 229 |
---
|
| 230 |
Prepared by `scripts/prepare_hf_release.py` from `pretrain_emg_c1_moe`
|
| 231 |
on 2026-10-29.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: feature-extraction
|
| 4 |
tags:
|
| 5 |
- physiowave
|
| 6 |
- physiowave-t
|
|
|
|
| 17 |
|
| 18 |
# PhysioWave-T-sEMG: multi-route pretrained sEMG encoder
|
| 19 |
|
| 20 |
+
Paper: [PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals](https://huggingface.co/papers/2611.08969) 路 [arXiv:2611.08969](https://arxiv.org/abs/2611.08969)
|
| 21 |
+
|
| 22 |
One of the three **PhysioWave-T** encoders ([EEG](https://huggingface.co/ForeverBlue/EEG), [ECG](https://huggingface.co/ForeverBlue/ECG), sEMG); the [RALF fusion model](https://huggingface.co/ForeverBlue/RALF-SeizeIT2) combines them. Code: <https://github.com/ForeverBlue816/PhysioWave>.
|
| 23 |
|
| 24 |
Masked dual-reconstruction pretraining on surface EMG from wristbands, forearm arrays and high-density grids. One shared transformer serves three electrode layouts through route-specific wavelet frontends, and electrode identity enters as a learned embedding of the electrode NAME rather than of its index.
|
|
|
|
| 229 |
|
| 230 |
Code: <https://github.com/ForeverBlue816/PhysioWave>
|
| 231 |
|
| 232 |
+
|
| 233 |
+
## Citation
|
| 234 |
+
|
| 235 |
+
This model is described in [PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals](https://arxiv.org/abs/2611.08969) (arXiv:2611.08969), which extends [PhysioWave (NeurIPS 2025)](https://arxiv.org/abs/2506.10351).
|
| 236 |
+
|
| 237 |
+
```bibtex
|
| 238 |
+
@article{chen2026physiowavet,
|
| 239 |
+
title = {PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals},
|
| 240 |
+
author = {Chen, Yanlong and Benatti, Simone and Benini, Luca and Guan, Cuntai and Li, Yawei},
|
| 241 |
+
journal = {arXiv preprint arXiv:2611.08969},
|
| 242 |
+
year = {2026}
|
| 243 |
+
}
|
| 244 |
+
|
| 245 |
+
@inproceedings{chen2025physiowave,
|
| 246 |
+
title = {PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation},
|
| 247 |
+
author = {Chen, Yanlong and Orlandi, Mattia and Rapa, Pierangelo Maria and Benatti, Simone and Benini, Luca and Li, Yawei},
|
| 248 |
+
booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
|
| 249 |
+
year = {2025}
|
| 250 |
+
}
|
| 251 |
+
```
|
| 252 |
+
|
| 253 |
---
|
| 254 |
Prepared by `scripts/prepare_hf_release.py` from `pretrain_emg_c1_moe`
|
| 255 |
on 2026-10-29.
|