arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03478cs.LG
收藏

核大小对基于CNN-Vision-Transformer的脑电图凝视预测的影响

Effect of Kernel Size on CNN-Vision-Transformer-Based Gaze Prediction Using Electroencephalography Data

The George Washington University(乔治·华盛顿大学)

Chuhui Qiu, Bugao Liang, Matthew L Key

AI总结:

本文提出一种基于EEG数据的凝视预测算法,通过CNN-Vision-Transformer架构将均方根误差提升至53.06毫米,并将训练时间缩短至原方法的不到33%。

摘要:

在本文中,我们提出了一种基于脑电图(EEG)数据的凝视预测算法。基于EEG的凝视预测是一个新的研究课题,可作为传统基于视频的眼动追踪的替代方案。与现有的最先进(SOTA)方法相比,我们将基于EEG的凝视预测的均方根误差提高到53.06毫米,同时将训练时间缩短至其原始时长的不到33%。我们的源代码可在https://github.com/AmCh-Q/CSCI6907Project找到。

英文摘要:

In this paper, we present an algorithm of gaze prediction from Electroencephalography (EEG) data. EEG-based gaze prediction is a new research topic that can serve as an alternative to traditional video-based eye-tracking. Compared to the existing state-of-the-art (SOTA) method, we improved the root mean-squared-error of EEG-based gaze prediction to 53.06 millimeters, while reducing the training time to less than 33% of its original duration. Our source code can be found at https://github.com/AmCh-Q/CSCI6907Project

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑