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

TL;DR

Alljoined1 is a comprehensive EEG dataset designed for decoding visual images from brain responses, featuring extensive data collection from multiple participants and diverse images to enhance neural decoding research.

Contribution

The paper introduces Alljoined1, a large-scale, unbiased EEG dataset specifically created for EEG-to-Image decoding, with detailed data collection and quality metrics.

Findings

Dataset includes 46,080 EEG epochs from 8 participants.

Contains responses to 10,000 natural images.

Provides data quality scores for transparency.

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.