Fusing temporal, spectral, and spatial EEG views with cross-attention and view-wise masking improves downstream classification and cross-dataset generalization over prior EEG pretraining models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations
Fusing temporal, spectral, and spatial EEG views with cross-attention and view-wise masking improves downstream classification and cross-dataset generalization over prior EEG pretraining models.