A two-stage multimodal Transformer with fixed pretrained feature extractors predicts fMRI activity from movies with Pearson r = 0.32 (in-domain) and 0.21 (out-of-domain), beating the challenge baseline by about 0.12.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
VIBE: Video-Input Brain Encoder for fMRI Response Modeling
A two-stage multimodal Transformer with fixed pretrained feature extractors predicts fMRI activity from movies with Pearson r = 0.32 (in-domain) and 0.21 (out-of-domain), beating the challenge baseline by about 0.12.