# EM-Net: Gaze Estimation with Expectation Maximization Algorithm

arXiv: https://arxiv.org/abs/2412.08074 · HTML: https://mlsanity.com/paper/2412.08074/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 43 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features](https://mlsanity.com/paper/2209.15159/) (2022)
- [Towards Self-Supervised Gaze Estimation](https://mlsanity.com/paper/2203.10974/) (2022)
- [FR-Net:A Light-weight FFT Residual Net For Gaze Estimation](https://mlsanity.com/paper/2305.11875/) (2023)

## Built on by (most cited first, 1 of 1)

- [DMAGaze: Gaze Estimation Based on Feature Disentanglement and Multi-Scale Attention](https://mlsanity.com/paper/2504.11160/) (2025)

## Abstract (arXiv)

In recent years, the accuracy of gaze estimation techniques has gradually improved, but existing methods often rely on large datasets or large models to improve performance, which leads to high demands on computational resources. In terms of this issue, this paper proposes a lightweight gaze estimation model EM-Net based on deep learning and traditional machine learning algorithms Expectation Maximization algorithm. First, the proposed Global Attention Mechanism(GAM) is added to extract features related to gaze estimation to improve the model's ability to capture global dependencies and thus improve its performance. Second, by learning hierarchical feature representations through the EM module, the model has strong generalization ability, which reduces the need for sample size. Experiments have confirmed that, on the premise of using only 50% of the training data, EM-Net improves the performance of Gaze360, MPIIFaceGaze, and RT-Gene datasets by 2.2%, 2.02%, and 2.03%, respectively, compared with GazeNAS-ETH. It also shows good robustness in the face of Gaussian noise interference.