EmMixformer: Mix transformer for eye movement recognition

arXiv:2401.04956v2 Announce Type: replace-cross
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 …

arxiv attention biometric capture cnn cs.cr cs.cv current data dependencies fail global local network networks neural network neural networks performance recognition solutions temporal