English

Alljoined1 -- A dataset for EEG-to-Image decoding

Neurons and Cognition 2024-05-15 v3 Artificial Intelligence

Abstract

We present Alljoined1, a dataset built specifically for EEG-to-Image decoding. Recognizing that an extensive and unbiased sampling of neural responses to visual stimuli is crucial for image reconstruction efforts, we collected data from 8 participants looking at 10,000 natural images each. We have currently gathered 46,080 epochs of brain responses recorded with a 64-channel EEG headset. The dataset combines response-based stimulus timing, repetition between blocks and sessions, and diverse image classes with the goal of improving signal quality. For transparency, we also provide data quality scores. We publicly release the dataset and all code at https://linktr.ee/alljoined1.

Keywords

Cite

@article{arxiv.2404.05553,
  title  = {Alljoined1 -- A dataset for EEG-to-Image decoding},
  author = {Jonathan Xu and Bruno Aristimunha and Max Emanuel Feucht and Emma Qian and Charles Liu and Tazik Shahjahan and Martyna Spyra and Steven Zifan Zhang and Nicholas Short and Jioh Kim and Paula Perdomo and Ricky Renfeng Mao and Yashvir Sabharwal and Michael Ahedor Moaz Shoura and Adrian Nestor},
  journal= {arXiv preprint arXiv:2404.05553},
  year   = {2024}
}

Comments

8 Pages, 6 Figures

R2 v1 2026-06-28T15:47:35.260Z