AI Paper Atlas

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

Leveraging Visual Blur Perception Characteristics for EEG Decoding

Wenchao Liu, Hongwei Li, Zhouyang Xu, Lin Ma, Haifeng Li

AAAI 2026 · 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 the multi-level Gaussian blurring pipeline (ablation)EEG decoding framework · Things-EEG (intra-subject)top-1 accuracy (%): 57.27 -> 80.00Improved
add the multi-level Gaussian blurring pipeline (ablation)EEG decoding framework · Things-EEG (intra-subject)top-5 accuracy (%): 86.95 -> 96.89Improved
add the feature adapter (ablation)EEG decoding framework · Things-EEG (intra-subject)top-1 accuracy (%): 56.21 -> 80.00Improved
add the feature adapter (ablation)EEG decoding framework · Things-EEG (intra-subject)top-5 accuracy (%): 85.68 -> 96.89Improved
add the positively constrained spatial convolution (ablation)EEG decoding framework · Things-EEG (intra-subject)top-1 accuracy (%): 67.04 -> 80.00Improved
add the positively constrained spatial convolution (ablation)EEG decoding framework · Things-EEG (intra-subject)top-5 accuracy (%): 91.45 -> 96.89Improved
replace UBP with the proposed multi-level blur frameworkUBP · Things-EEG (intra-subject)top-1 accuracy (%): 50.9 -> 80.0Improved
replace UBP with the proposed framework (inter-subject)UBP · Things-EEG (inter-subject)top-1 accuracy (%): 12.4 -> 20.0Improved
replace UBP with the proposed frameworkUBP · Things-MEG (intra-subject)top-1 accuracy (%): 26.7 -> 44.0Improved
replace UBP with the proposed framework (inter-subject)UBP · Things-MEG (inter-subject)top-1 accuracy (%): 2.2 -> 5.3Improved
average 10 test repetitions instead of noneProposed framework · Things-EEGtop-1 accuracy (%): 13.8 -> 59.55Improved

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