Enhancing Appearance-Based Gaze Estimation Through Attention-Based Convolutional Neural Networks

: Appearance-based gaze estimation is crucial for applications like assistive technology and human-computer interaction, but high accuracy is challenging due to complex gaze patterns and individual appearance variations. This paper proposes an Attention-Enhanced Convolutional Neural Network (AE-CNN) to address these challenges. By integrating attention submodules, AE-CNN improves feature extraction by focusing on the most relevant regions of input data. We evaluate AE-CNN using the ColumbiaGaze dataset and show that it surpasses previous methods, achieving a remarkable accuracy of 99.98%. This work advances gaze estimation by leveraging attention mechanisms to improve performance.

• Publication year

  2025

• Venue

  International Conference on Agents and Artificial Intelligence

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.5220/0013055500003890
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Bilinear Pooling for Thyroid Nodule Classification in Ultrasound Imaging

  2023cited by this paper
• Gaze estimation using convolutional neural networks

  2023influential reference
• DeepPupil Net: Deep Residual Network for Precise Pupil Center Localization

  2022cited by this paper
• End-to-End Multitask Learning for Driver Gaze and Head Pose Estimation

  2020influential reference
• Image Augmentation for Eye Contact Detection Based on Combination of Pre-trained Alex-Net CNN and SVM

  2020influential reference
• A Fully Automatic based Deep Learning Approach for Aneurysm Detection in DSA Images

  2018cited by this paper
• Learning to find eye region landmarks for remote gaze estimation in unconstrained settings

  2018cited by this paper
• 3D gaze estimation without explicit personal calibration

  2018cited by this paper
• Learn To Pay Attention

  2018cited by this paper
• Appearance-Based Gaze Estimation Using Dilated-Convolutions

  2018influential reference
• Attention is All you Need

  2017cited by this paper
• Non-local Neural Networks

  2017cited by this paper
• Real Time Eye Gaze Tracking with 3D Deformable Eye-Face Model

  2017cited by this paper
• Squeeze-and-Excitation Networks

  2017cited by this paper
• Real-time categorization of driver's gaze zone and head pose using the convolutional neural network

  2016cited by this paper
• Real-time eye gaze direction classification using convolutional neural network

  2016cited by this paper
• Near-Eye Display Gaze Tracking via Convolutional Neural Networks

  2016cited by this paper
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

  2015cited by this paper
• Real time gaze estimation with a consumer depth camera

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• EyeTab: model-based gaze estimation on unmodified tablet computers

  2014cited by this paper
• Hybrid method based on topography for robust detection of iris center and eye corners

  2013cited by this paper
• Gaze locking: passive eye contact detection for human-object interaction

  2013cited by this paper
• The MUCT Landmarked Face Database

  2010cited by this paper
• 3D gaze estimation with a single camera without IR illumination

  2008cited by this paper
• Eye gaze estimation from a single image of one eye

  2003cited by this paper
• Robust Face Detection Using the Hausdorff Distance

  2001cited by this paper

• A Multi-Task Convolutional Neural Network for Gaze Estimation: A From-Scratch Approach

  2025cites this paper