AI Paper Atlas

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

Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment

Dongjun Liu, Weichen Dai, Jingsheng Qian, Honggang Liu, Hangjie Yi, Wanzeng Kong

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding

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 text-guided visual decoupling (non-uniform center-sharp Gaussian blur) to vanilla contrastive alignment (ablation)EEG-image contrastive alignment · THINGS-EEG (intra-subject)Top-1 accuracy (%): 43.6 -> 54.9Improved
add text-guided visual decoupling to vanilla contrastive alignment (ablation)EEG-image contrastive alignment · THINGS-EEG (intra-subject)Top-5 accuracy (%): 77.0 -> 87.7Improved
add dynamic alignment strategy on top of decoupling (ablation)Decouple configuration · THINGS-EEG (intra-subject)Top-1 accuracy (%): 54.9 -> 55.6Improved
add dynamic alignment strategy on top of decoupling (ablation)Decouple configuration · THINGS-EEG (intra-subject)Top-5 accuracy (%): 87.7 -> 87.5No clear effect
add multimodal similarity modulation (semantic enhancement) (ablation)Dynamic configuration · THINGS-EEG (intra-subject)Top-1 accuracy (%): 55.6 -> 58.2Improved
add multimodal similarity modulation (semantic enhancement) (ablation)Dynamic configuration · THINGS-EEG (intra-subject)Top-5 accuracy (%): 87.5 -> 89.1Improved
increase central blur level c from 0.1 to 0.5 (ablation)Ours · THINGS-EEG (intra-subject)Top-1 accuracy (%): 56.2 -> 58.2Improved
vary c between 0.2 and 0.5 (ablation)Ours · THINGS-EEG (intra-subject)Top-5 accuracy (%): 88.1 to 89.1No clear effect
swap CLIP RN50 image encoder for RN101 (ablation)Ours · THINGS-EEG (intra-subject)Top-1 accuracy (%): 58.2 -> 55.8Hurt
swap CLIP RN50 image encoder for ViT-B/16 (ablation)Ours · THINGS-EEG (intra-subject)Top-1 accuracy (%): 58.2 -> 54.5Hurt
swap CLIP RN50 image encoder for ViT-B/32 (ablation)Ours · THINGS-EEG (intra-subject)Top-1 accuracy (%): 58.2 -> 58.0No clear effect
replace UBP with the proposed methodTHINGS-EEG inter-subject retrieval · THINGS-EEG (inter-subject, leave-one-out)Top-1 accuracy (%): 12.4 -> 15.8Improved

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