.png){kind=icon}
Return
CATVis: Context-Aware Thought Visualization
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-04927-8_10.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
EEG-based brain-computer interfaces (BCIs) have shown promise in various applications, such as motor imagery and cognitive state monitoring. However, decoding visual representations from EEG signals remains a significant challenge due to their complex and noisy nature. We thus propose a novel 5-stage framework for decoding visual representations from EEG signals: (1) an EEG encoder for concept classification, (2) cross-modal alignment of EEG and text embeddings in CLIP feature space, (3) caption refinement via re-ranking, (4) weighted interpolation of concept and caption embeddings for richer semantics, and (5) image generation using a pre-trained Stable Diffusion model. We enable context-aware EEG-to-image generation through cross-modal alignment and re-ranking. Experimental results demonstrate that our method generates high-quality images aligned with visual stimuli, outperforming SOTA approaches by 27.08% in Classification Accuracy, 15.21% in Generation Accuracy and reducing Frechet Inception Distance by 36.61%, indicating superior semantic alignment and image quality. The code is available at https://github.com/CVLABLUMS/CATVis.
Keywords:
Brain-Computer Interfaces (BCIs)
EEG Decoding
Visual Reconstruction
Cross-Modal Alignment
Journal
M
IF:
0
Papers:
52
Citations:
0
Organization
Cited Papers
Identification and Removal of Physiological Artifacts From Electroencephalogram Signals: A Review.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSaveSeeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
OAAI
OAAIShareSave
View more