ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Minxu, Guan, Donghai, Zheng, Chuhang, Tian, Chunwei, Wen, Jie, Zhu, Qi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908513853243392
author Liu, Minxu
Guan, Donghai
Zheng, Chuhang
Tian, Chunwei
Wen, Jie
Zhu, Qi
author_facet Liu, Minxu
Guan, Donghai
Zheng, Chuhang
Tian, Chunwei
Wen, Jie
Zhu, Qi
contents Understanding and decoding brain activity into visual representations is a fundamental challenge at the intersection of neuroscience and artificial intelligence. While EEG visual decoding has shown promise due to its non-invasive, and low-cost nature, existing methods suffer from Hierarchical Neural Encoding Neglect (HNEN)-a critical limitation where flat neural representations fail to model the brain's hierarchical visual processing hierarchy. Inspired by the hierarchical organization of visual cortex, we propose ViEEG, a neuro-We further adopt hierarchical contrastive learning for EEG-CLIP representation alignment, enabling zero-shot object recognition. Extensive experiments on the THINGS-EEG dataset demonstrate that ViEEG significantly outperforms previous methods by a large margin in both subject-dependent and subject-independent settings. Results on the THINGS-MEG dataset further confirm ViEEG's generalization to different neural modalities. Our framework not only advances the performance frontier but also sets a new paradigm for EEG brain decoding. inspired framework that addresses HNEN. ViEEG decomposes each visual stimulus into three biologically aligned components-contour, foreground object, and contextual scene-serving as anchors for a three-stream EEG encoder. These EEG features are progressively integrated via cross-attention routing, simulating cortical information flow from low-level to high-level vision.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding
Liu, Minxu
Guan, Donghai
Zheng, Chuhang
Tian, Chunwei
Wen, Jie
Zhu, Qi
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Understanding and decoding brain activity into visual representations is a fundamental challenge at the intersection of neuroscience and artificial intelligence. While EEG visual decoding has shown promise due to its non-invasive, and low-cost nature, existing methods suffer from Hierarchical Neural Encoding Neglect (HNEN)-a critical limitation where flat neural representations fail to model the brain's hierarchical visual processing hierarchy. Inspired by the hierarchical organization of visual cortex, we propose ViEEG, a neuro-We further adopt hierarchical contrastive learning for EEG-CLIP representation alignment, enabling zero-shot object recognition. Extensive experiments on the THINGS-EEG dataset demonstrate that ViEEG significantly outperforms previous methods by a large margin in both subject-dependent and subject-independent settings. Results on the THINGS-MEG dataset further confirm ViEEG's generalization to different neural modalities. Our framework not only advances the performance frontier but also sets a new paradigm for EEG brain decoding. inspired framework that addresses HNEN. ViEEG decomposes each visual stimulus into three biologically aligned components-contour, foreground object, and contextual scene-serving as anchors for a three-stream EEG encoder. These EEG features are progressively integrated via cross-attention routing, simulating cortical information flow from low-level to high-level vision.
title ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2505.12408