# Temporal Persistence and Intercorrelation of Embeddings Learned by an End-to-End Deep Learning Eye Movement-driven Biometrics Pipeline

arXiv: https://arxiv.org/abs/2402.16399 · HTML: https://mlsanity.com/paper/2402.16399/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 67 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (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 privacy-preserving approach to streaming eye-tracking data](https://mlsanity.com/paper/2102.01770/) (2021)
- [Eye Know You: Metric Learning for End-to-end Biometric Authentication Using Eye Movements from a Longitudinal Dataset](https://mlsanity.com/paper/2104.10489/) (2021)
- [GazeBaseVR, a large-scale, longitudinal, binocular eye-tracking dataset collected in virtual reality](https://mlsanity.com/paper/2210.07533/) (2022)
- [A Score-level Fusion Method for Eye Movement Biometrics](https://mlsanity.com/paper/1601.03333/) (2016)
- [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)
- [Comprehensive Survey: Biometric User Authentication Application, Evaluation, and Discussion](https://mlsanity.com/paper/2311.13416/) (2023)
- [Eye Movements Biometrics: A Bibliometric Analysis from 2004 to 2019](https://mlsanity.com/paper/2006.01310/) (2020)
- [Signal vs Noise in Eye-tracking Data: Biometric Implications and Identity Information Across Frequencies](https://mlsanity.com/paper/2305.04413/) (2023)
- [Determining Which Sine Wave Frequencies Correspond to Signal and Which Correspond to Noise in Eye-Tracking Time-Series](https://mlsanity.com/paper/2302.00029/) (2023)

## Built on by (most cited first, 2 of 2)

- [Ocular Authentication: Fusion of Gaze and Periocular Modalities](https://mlsanity.com/paper/2505.17343/) (2025)
- [Gaze Authentication: Factors Influencing Authentication Performance](https://mlsanity.com/paper/2509.10969/) (2025)

## Abstract (arXiv)

What qualities make a feature useful for biometric performance? In prior research, pre-dating the advent of deep learning (DL) approaches to biometric analysis, a strong relationship between temporal persistence, as indexed by the intraclass correlation coefficient (ICC), and biometric performance (Equal Error Rate, EER) was noted. More generally, the claim was made that good biometric performance resulted from a relatively large set of weakly intercorrelated features with high ICC. The present study aimed to determine whether the same relationships are found in a state-of-the-art DL-based eye movement biometric system (``Eye-Know-You-Too''), as applied to two publicly available eye movement datasets. To this end, we manipulate various aspects of eye-tracking signal quality, which produces variation in biometric performance, and relate that performance to the temporal persistence and intercorrelation of the resulting embeddings. Data quality indices were related to EER with either linear or logarithmic fits, and the resulting model R^2 was noted. As a general matter, we found that temporal persistence was an important predictor of DL-based biometric performance, and also that DL-learned embeddings were generally weakly intercorrelated.