SAMGA achieves 91.3% Top-1 intra-subject and 34.4% Top-1 inter-subject accuracy on THINGS-EEG by constructing subject-specific multi-granularity visual targets and performing coarse-to-fine cross-modal alignment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval
SAMGA achieves 91.3% Top-1 intra-subject and 34.4% Top-1 inter-subject accuracy on THINGS-EEG by constructing subject-specific multi-granularity visual targets and performing coarse-to-fine cross-modal alignment.