Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Kaifan, He, Lihuo, Ke, Junjie, Ji, Yuqi, Wu, Lukun, Wang, Lizi, Gao, Xinbo
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.12722
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914390611066880
author Zhang, Kaifan
He, Lihuo
Ke, Junjie
Ji, Yuqi
Wu, Lukun
Wang, Lizi
Gao, Xinbo
author_facet Zhang, Kaifan
He, Lihuo
Ke, Junjie
Ji, Yuqi
Wu, Lukun
Wang, Lizi
Gao, Xinbo
contents Visual stimuli reconstruction from EEG remains challenging due to fidelity loss and representation shift. We propose CognitionCapturerPro, an enhanced framework that integrates EEG with multi-modal priors (images, text, depth, and edges) via collaborative training. Our core contributions include an uncertainty-weighted similarity scoring mechanism to quantify modality-specific fidelity and a fusion encoder for integrating shared representations. By employing a simplified alignment module and a pre-trained diffusion model, our method significantly outperforms the original CognitionCapturer on the THINGS-EEG dataset, improving Top-1 and Top-5 retrieval accuracy by 25.9% and 10.6%, respectively. Code is available at: https://github.com/XiaoZhangYES/CognitionCapturerPro.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12722
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CognitionCapturerPro: Towards High-Fidelity Visual Decoding from EEG/MEG via Multi-modal Information and Asymmetric Alignment
Zhang, Kaifan
He, Lihuo
Ke, Junjie
Ji, Yuqi
Wu, Lukun
Wang, Lizi
Gao, Xinbo
Computer Vision and Pattern Recognition
Artificial Intelligence
Visual stimuli reconstruction from EEG remains challenging due to fidelity loss and representation shift. We propose CognitionCapturerPro, an enhanced framework that integrates EEG with multi-modal priors (images, text, depth, and edges) via collaborative training. Our core contributions include an uncertainty-weighted similarity scoring mechanism to quantify modality-specific fidelity and a fusion encoder for integrating shared representations. By employing a simplified alignment module and a pre-trained diffusion model, our method significantly outperforms the original CognitionCapturer on the THINGS-EEG dataset, improving Top-1 and Top-5 retrieval accuracy by 25.9% and 10.6%, respectively. Code is available at: https://github.com/XiaoZhangYES/CognitionCapturerPro.
title CognitionCapturerPro: Towards High-Fidelity Visual Decoding from EEG/MEG via Multi-modal Information and Asymmetric Alignment
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.12722