AI Paper Atlas

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

Neural encoding with visual attention

Meenakshi Khosla, Gia Ngo, Keith Jamison, Amy Kuceyeski, Mert Sabuncu

NeurIPS 2020 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 2 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
add gaze-weighted attention pooling (vs no attention), linear response model (ablation)ResNet-50 encoder · HCP 7T fMRI movie testmean prediction accuracy over synchronous voxels: ~ 40 \% improvementImproved
add gaze-weighted attention pooling (vs no attention), convolutional response model (ablation)ResNet-50 encoder · HCP 7T fMRI movie testmean prediction accuracy over synchronous voxels: ~ 47 \% improvementImproved
use convolutional instead of linear response model (ablation)encoding model · HCP 7T fMRI movie testprediction accuracyImproved
replace center-weighted or no attention with learned soft attention (ablation)convolutional encoding model · HCP 7T fMRI movie testmean prediction accuracyImproved
attention modulation on other ResNet-50 layers (ablation)encoding models · HCP 7T fMRI movie testprediction accuracyImproved
learned attention vs Deepgaze-II on saliencyattention network · gaze predictionSIM: 0.359 -> 0.392Improved
learned attention vs Deepgaze-II on saliencyattention network · gaze predictionNSS: 1.425 -> 1.375Hurt
learned attention vs Deepgaze-II on saliencyattention network · gaze predictionAUC: 0.808 -> 0.754Hurt
learned attention vs center-weighted baseline on saliencyattention network · gaze predictionCC: 0.350 -> 0.403Improved
hemodynamic delay of 4 s chosen (ablation)regression encoding · HCP 7T fMRIprediction accuracyImproved

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