# Eye Know You: Metric Learning for End-to-end Biometric Authentication Using Eye Movements from a Longitudinal Dataset

arXiv: https://arxiv.org/abs/2104.10489 · HTML: https://mlsanity.com/paper/2104.10489/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [PyTorch Metric Learning](https://mlsanity.com/paper/2008.09164/) (2020)
- [Deep Eyedentification: Biometric Identification using Micro-Movements of the Eye](https://mlsanity.com/paper/1906.11889/) (2019)
- [GazeBase: A Large-Scale, Multi-Stimulus, Longitudinal Eye Movement Dataset](https://mlsanity.com/paper/2009.06171/) (2020)
- [A Score-level Fusion Method for Eye Movement Biometrics](https://mlsanity.com/paper/1601.03333/) (2016)
- [A Discriminative Model for Identifying Readers and Assessing Text Comprehension from Eye Movements](https://mlsanity.com/paper/1809.08031/) (2018)
- [Biometric Performance as a Function of Gallery Size](https://mlsanity.com/paper/1906.06272/) (2019)
- [Deep Distributional Sequence Embeddings Based on a Wasserstein Loss](https://mlsanity.com/paper/1912.01933/) (2019)
- [Evaluating the Data Quality of Eye Tracking Signals from a Virtual Reality System: Case Study using SMI's Eye-Tracking HTC Vive](https://mlsanity.com/paper/1912.02083/) (2019)

## Built on by (most cited first, 11 of 11)

- [EmMixformer: Mix transformer for eye movement recognition](https://mlsanity.com/paper/2401.04956/) (2024)
- [Relax DARTS: Relaxing the Constraints of Differentiable Architecture Search for Eye Movement Recognition](https://mlsanity.com/paper/2409.11652/) (2024)
- [Eye Know You Too: A DenseNet Architecture for End-to-end Eye Movement Biometrics](https://mlsanity.com/paper/2201.02110/) (2022)
- [Temporal Persistence and Intercorrelation of Embeddings Learned by an End-to-End Deep Learning Eye Movement-driven Biometrics Pipeline](https://mlsanity.com/paper/2402.16399/) (2024)
- [Ocular Authentication: Fusion of Gaze and Periocular Modalities](https://mlsanity.com/paper/2505.17343/) (2025)
- [Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models](https://mlsanity.com/paper/2304.13536/) (2023)
- [Recent Advancement in 3D Biometrics using Monocular Camera](https://mlsanity.com/paper/2401.02646/) (2024)
- [EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition](https://mlsanity.com/paper/2409.14432/) (2024)
- [Gaze Authentication: Factors Influencing Authentication Performance](https://mlsanity.com/paper/2509.10969/) (2025)
- [Enhancing Eye Movement Biometrics for User Authentication via Continuous Gaze Offset Score Fusion](https://mlsanity.com/paper/2605.06810/) (2026)
- [EyeMakeYou: Identity-, Task-, and Subjective-State-Conditioned Diffusion for High-Frequency Gaze Synthesis](https://mlsanity.com/paper/2609.04501/) (2026)

## Abstract (arXiv)

The permanence of eye movements as a biometric modality remains largely unexplored in the literature. The present study addresses this limitation by evaluating a novel exponentially-dilated convolutional neural network for eye movement authentication using a recently proposed longitudinal dataset known as GazeBase. The network is trained using multi-similarity loss, which directly enables the enrollment and authentication of out-of-sample users. In addition, this study includes an exhaustive analysis of the effects of evaluating on various tasks and downsampling from 1000 Hz to several lower sampling rates. Our results reveal that reasonable authentication accuracy may be achieved even during both a low-cognitive-load task and at low sampling rates. Moreover, we find that eye movements are quite resilient against template aging after as long as 3 years.