EmMixformer: Mix transformer for eye movement recognition

arXiv:2401.04956v2 Announce Type: replace
Abstract: Eye movement (EM) is a new highly secure biometric behavioral modality that has received increasing attention in recent years. Although deep neural networks, such as convolutional neural network (CNN), have recently achieved promising performance, current solutions fail to capture local and global temporal dependencies within eye movement data. To overcome this problem, we propose in this paper a mixed transformer termed EmMixformer to extract time and frequency domain information for eye movement recognition. To this …

abstract arxiv attention biometric cnn convolutional convolutional neural network cs.cr cs.cv current data dependencies global network networks neural network neural networks performance recognition solutions temporal transformer type