EmMixformer: Mix transformer for eye movement recognition
This work addresses the need for more accurate biometric authentication using eye movements, though it appears incremental as it builds on existing deep learning methods with novel combinations.
The paper tackled the problem of capturing local and global temporal dependencies in eye movement recognition by proposing EmMixformer, a mixed transformer that combines transformer, attention LSTM, and Fourier transformer modules, resulting in state-of-the-art performance with the lowest verification error on three datasets.
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 end, we propose a mixed block consisting of three modules, transformer, attention Long short-term memory (attention LSTM), and Fourier transformer. We are the first to attempt leveraging transformer to learn long temporal dependencies within eye movement. Second, we incorporate the attention mechanism into LSTM to propose attention LSTM with the aim to learn short temporal dependencies. Third, we perform self attention in the frequency domain to learn global features. As the three modules provide complementary feature representations in terms of local and global dependencies, the proposed EmMixformer is capable of improving recognition accuracy. The experimental results on our eye movement dataset and two public eye movement datasets show that the proposed EmMixformer outperforms the state of the art by achieving the lowest verification error.