EUVIMEDEUVIMED entdecken
Crossref

DAMind: Zero-Shot Visual Cross-Domain Alignment and Representation for EEG Decoding

Haodong Jing, Yongqiang Ma, Panqi Yang, Haoyu Li, Shuai Huang, Badong Chen, Nanning Zheng

IEEE Transactions on Image Processing · 2026 · 35 · 3214-3227

DOI: 10.1109/tip.2026.3666730 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Haodong Jing und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Electroencephalography, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: Brain Networks and Brain-Inspired Intelligence Science Breakthrough Pilot Project, National Natural Science Foundation of China, STI2030-Major Projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To efficiently assist humans in various tasks, it is crucial to accurately decode and understand the rich information embedded in brain's visual cognition. Existing brain-driven research often fails to overcome the challenge of small target data domains, and the lack of explicit semantic, spatial, and other information constraints on feature extractors prevents brain decoding models from learning uniform cross-domain representations, leading to degradation of their performance in unseen domains. To overcome these limitations, we propose DAMind, a multimodal EEG-based model for robust visual cross-domain alignment and decoding. Our approach integrates VLM with brain-inspired cognitive mechanisms, leveraging the strong image-text representation abilities to learn both fine-grained primary visual features and high-level semantic concepts from neural signals, provide effective visual fine-tuning using the visual guidance mechanism. DAMind introduces a stepwise EEG encoding process aligned with visual processing, and employs an instruction-based learning strategy for effective cross-domain zero-shot transfer. Its robust architecture efficiently achieves good generalization performance, enabling the mapping of EEG signals from multiple domains to a unified learning domain. We construct a comprehensive EEG decoding benchmark EBench, DAMind achieves state-of-the-art results on several visual tasks, and outperforms the baseline in zero-shot setting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographySignal Processing, Computer-AssistedHumansAlgorithmsBrainRepresentation Machine Learning

Förderung

  • Brain Networks and Brain-Inspired Intelligence Science Breakthrough Pilot Project
  • National Natural Science Foundation of China
  • STI2030-Major Projects

Zitieren

APA

Jing, H., Ma, Y., Yang, P., Li, H., Huang, S., Chen, B., & Zheng, N. (2026). DAMind: Zero-Shot Visual Cross-Domain Alignment and Representation for EEG Decoding. IEEE Transactions on Image Processing, 35, 3214-3227. https://doi.org/10.1109/tip.2026.3666730

Vancouver

Jing H, Ma Y, Yang P, Li H, Huang S, Chen B, et al. DAMind: Zero-Shot Visual Cross-Domain Alignment and Representation for EEG Decoding. IEEE Transactions on Image Processing. 2026;35:3214-3227. doi:10.1109/tip.2026.3666730

BibTeX
@article{Jing2026,
  author = {Jing, Haodong and Ma, Yongqiang and Yang, Panqi and Li, Haoyu and Huang, Shuai and Chen, Badong and Zheng, Nanning},
  title = {DAMind: Zero-Shot Visual Cross-Domain Alignment and Representation for EEG Decoding},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {3214--3227},
  doi = {10.1109/tip.2026.3666730}
}
Kostenlos starten →