CAST reconstructs cross-subject cortical iEEG from scalp EEG using a two-stage temporal encoder and channel-aware decoder, achieving peak correlations of 0.864 in sensorimotor areas and mean 0.545 with channel selection on 1282 channels.
Machine translation of cortical activity to text with an encoder–decoder framework.Nature neu- roscience, 23(4):575–582
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cross-Subject Intracranial EEG Reconstruction from Scalp Recordings Using Multi-Scale Cross-Attention Transformers
CAST reconstructs cross-subject cortical iEEG from scalp EEG using a two-stage temporal encoder and channel-aware decoder, achieving peak correlations of 0.864 in sensorimotor areas and mean 0.545 with channel selection on 1282 channels.