AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features

Simone Palazzo, Concetto Spampinato, Isaak Kavasidis, Daniela Giordano, Joseph Schmidt, Mubarak Shah

TPAMI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 192 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
restrict EEG input to high gamma band 55-95 Hz instead of all frequencies (ablation)EEG-ChannelNet · EEG classificationaccuracy: 31.3% -> 48.1%Improved
use high gamma instead of all gamma (ablation)EEG-ChannelNet · EEG classificationaccuracy: 40.0% -> 48.1%Improved
use entire 20-460 ms EEG course instead of 20-350 ms (ablation)EEG-ChannelNet · EEG classificationaccuracy: 43.8% -> 48.1%Improved
include the first 110 ms of EEG (20-460 vs 130-460) (ablation)EEG-ChannelNet · EEG classificationaccuracy: 26.3% -> 48.1%Improved
add joint visual-EEG embedding learning (ablation)EEG-ChannelNet · EEG classificationaccuracy: 48.1% -> 60.4%Improved
add joint EEG-visual fine-tuning (ablation)Inception-v3 · Image classificationaccuracy: 93.1% -> 94.4%Improved
add joint EEG-visual fine-tuning (ablation)ResNet-101 · Image classificationaccuracy: 90.3% -> 90.5%Improved
add joint EEG-visual fine-tuning (ablation)DenseNet-161 · Image classificationaccuracy: 91.4% -> 92.1%Improved
add joint EEG-visual fine-tuning (ablation)AlexNet · Image classificationaccuracy: 65.5% -> 69.4%Improved
use EEG-visual compatibility instead of classifier log-likelihood for saliencypatch suppression saliency · Saliency detectionNSS: 0.495 -> 0.942Improved
use neural-driven saliency instead of SALICONSALICON · Saliency detections-AUC: 0.678 -> 0.643Hurt
use neural-driven saliency instead of SALICONSALICON · Saliency detectionNSS: 0.728 -> 0.942Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy