Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, current EEG-to-image retrieval methods perform far below their within-subject counterparts for new use...
Zhenyao Cui, Siyuan Kan, Siyang Li et al.· 1 citation
Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulus presentation that...
Zhenyao Cui, Siyuan Kan, Dingkun Liu et al.· 0 citations
RAMamba-Net is proposed, a reliability-aware Mamba-based multimodal fusion network for AAD that effectively exploits complementary EEG-EOG information, yielding accuracy gains over unimodal baselines, and is robust to signal perturbation and parameter variation.
CoMA-DiT is proposed, a bidirectional cross-modal Diffusion Transformer for latent augmentation that treats paired modalities as sources of mutual generative supervision rather than merely as inputs to be fused.
Zi-Wei Wang, Xing-Yi He, Hong-Bin Wang et al.· 0 citations
The results indicate that: 1) linear probing is frequently insufficient; 2) specialist models trained from scratch remain competitive across many tasks; and 3) larger FMs do not necessarily yield better generalization performance under current data regimes and training practices.
Dingkun Liu, Yu-Heng Chen, Zhu Chen et al.· National Science Review· 12 citations· ⚡3
STEAM is presented, a hierarchical transfer framework that reconciles general-purpose representation learning with paradigm-specific specialization in EEG foundation models and attains the best average rank among the compared methods at a competitive inference cost measured in FLOPs.
Zhu Chen, Dingkun Liu, Yu-Heng Chen et al.· 0 citations
Shrinkage-Whitened Proxy Cross-Entropy (SW-ProxyCE), a query-free task-aware attack framework that recovers task-level decision geometry from a small labeled reference set through shrinkage-whitened class prototypes, enabling transferable adversarial generation without training an additional surrogate classifier is pro...
Linhua Cong, Dingkun Liu, Dongrui Wu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
