Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

From Video to EEG: Adapting Joint Embedding Predictive Architecture to Uncover Visual Concepts in Brain Signal Analysis

Created by
  • Haebom

Author

Amirabbas Hojjati, Lu Li, Ibrahim Hameed, Anis Yazidi, Pedro G. Lind, Rabindra Khadka

Outline

This paper presents a novel approach to electroencephalography (EEG) signal analysis, which is difficult to analyze effectively due to limited data, high dimensionality, and the absence of models that cannot fully capture spatiotemporal dependencies. Unlike existing self-supervised learning (SSL) methods that focus on either spatial or temporal features, in this paper we propose an EEG-VJEPA model that treats EEG as a video-like sequence and learns spatiotemporal representations. EEG-VJEPA applies the Video Joint Embedding Predictive Architecture (V-JEPA) to EEG classification, and learns meaningful spatiotemporal representations using joint embedding and adaptive masking. Experimental results using the TUH Abnormal EEG dataset demonstrate that EEG-VJEPA outperforms existing state-of-the-art models in classification accuracy, demonstrating its potential to support human-AI collaboration in diagnostic workflows by capturing physiologically relevant spatiotemporal signal patterns and providing interpretable embeddings.

Takeaways, Limitations

Takeaways:
A novel self-supervised learning-based model EEG-VJEPA for EEG classification is presented
Achieving high classification accuracy that surpasses existing state-of-the-art models
Provides interpretable embeddings that capture physiologically meaningful spatiotemporal patterns.
Presenting a scalable and reliable EEG analysis framework in real clinical settings
Suggesting the possibility of supporting human-AI collaboration-based diagnostic workflow
Limitations:
There is no explicit mention of Limitations presented in this paper. Further research is expected to be needed to further verify the model's generalization performance, applicability to various EEG datasets, and clinical usefulness.
👍