Harnessing Spectrum Video for Subject-Level Few-Shot and Cross-Montage EEG Generalization
Wei Wang, Fang He, Yifan Li, Wanying Qu, Yawei Li, Quanying Liu, Yanwei Fu
Abstract
Existing EEG models are limited by electrode heterogeneity and rigid "channel-first" architectures that treat sensors as independent features. We propose Brain Signal Rendering (BSR), which reinterprets EEG as a physical projection of neural activity and transforms raw signals into geometry-aware Spectrum Videos. By utilizing VideoMAE for self-supervised pre-training, BSR learns robust, layout-agnostic spatiotemporal representations that preserve neural topology. We further introduce subject-level few-shot learning and cross-montage fine-tuning to rigorously evaluate generalization across subjects and electrode configurations. Experiments show that VideoMAE model integrated with the BSR framework significantly outperforms state-of-the-art spectrum based methods, providing a scalable and data-efficient foundation for generalizable EEG modeling.
BibTeX
@inproceedings{
wang2026harnessing,
title={Harnessing Spectrum Video for Subject-Level Few-Shot and Cross-Montage {EEG} Generalization},
author={Wei Wang and Fang He and Yifan Li and Wanying Qu and Yawei Li and Quanying Liu and Yanwei Fu},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=iCjSoADDPs}
}