AI Paper Atlas

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

Decoding 3D Perception via BrainSSD: Synergistic Fusion of EEG Representations from Static and Dynamic Visual Streams

Yincheng Yao, Enze Shi, Shu Zhang

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
fuse static and dynamic EEG streams instead of using the static stream alone (ablation)BrainSSD · EEG-3D retrieval (72-way)Top-1 accuracy (%): 4.98 -> 6.65Improved
fuse static and dynamic EEG streams instead of using the dynamic stream alone (ablation)BrainSSD · EEG-3D retrieval (72-way)Top-1 accuracy (%): 4.80 -> 6.65Improved
add hierarchical multi-level fusion (ablation)BrainSSD · EEG-3D retrieval (72-way)Top-1 accuracy (%): 5.15 -> 6.65Improved
add PAC-guided attention (ablation)BrainSSD · EEG-3D retrieval (72-way)Top-1 accuracy (%): 4.75 -> 6.65Improved
add alignment losses PDA and GSC (ablation)BrainSSD · EEG-3D discriminative tasksTop-K accuracyImproved
couple theta-alpha phase with gamma amplitude in PAC (ablation)BrainSSD · EEG-3D retrievalTop-1 accuracy (%)Improved
use OpenCLIP as vision encoder (ablation)BrainSSD · EEG-3D retrievalTop-1 accuracy (%)Improved
use dynamic-only instead of static-only EEG for 3D geometry (ablation)BrainSSD generative pipeline · EEG-3D 3D reconstructionChamfer Distance: 0.130 -> 0.096Improved
use dynamic-only instead of static-only EEG for classification (ablation)BrainSSD · EEG-3D discriminative tasksTop-1 accuracy (%): Retrieval Top-1 4.98 -> 4.80Hurt
fuse both streams for 3D reconstruction vs single stream (ablation)BrainSSD generative pipeline · EEG-3D 3D reconstructionF-score: 0.273 -> 0.304Improved
fuse both streams for Chamfer Distance vs dynamic-only (ablation)BrainSSD generative pipeline · EEG-3D 3D reconstructionChamfer Distance: 0.096 -> 0.113Hurt

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