Conference
Open access
Sep 2026
MFMSRNet: An Interpretable Multi-frequency and Multi-scale Riemannian Network for Motor Imagery Decoding
The Multi-frequency and Multi-scale Riemannian Network (MFMSRNet) is proposed, an interpretable end-to-end geometry-aware framework for MI EEG decoding on the SPD manifold that yields more expressive and interpretable representations for robust MI decoding, offering a promising solution for reliable brain–computer inte...
Wen-Hao Rao, Xu-Jie Zhao, Jianhui Zhao et al.
· Proceedings of the Thirty-Fi... · 0 citations