Eye Gaze Data Collection Tool for capturing and labeling eye gaze directions with real-time webcam integration. It also supports the collection of metadata, including lighting conditions and glasses usage, to enhance training data for deep learning models, enabling advanced gaze-based applications such as wheelchair control.

Official implementation of CXRGazeLearn

使用OpenCV部署眼睛凝视估计，包含C++和Python两个版本的程序，只依赖opencv库就可以运行，彻底摆脱对任何深度学习框架的依赖。

A simple machine learning model used to estimate the direction of an person's gaze within an image.

End to End Emotion tracker built with Open Face

Feeding an SVM w/ 2D human coordinates to estimate its visual focus of attention

Attention and Anxiety Analysis based on CNN

Gaze Estimation Based on Neural Network. Waiting for update.

Deep learning based Gaze Detection model to control the mouse pointer of your computer.

We try to detect what product a shopper is looking at in a retail store just using single view RGB images from a CCTV viewpoint.

Multi-person eye-contact detection from single-camera videos for clinical and in-the-wild interaction scenarios

Domain adaptation on gaze estimation from MPIIFaceGaze to ColumbiaGaze

Master thesis at Wroclaw University of Science and Technology.

The application uses gaze detection points with the use of deep learning model to estimate the gaze of user's eyes to move the mouse pointer position.

VisionGuard functions as a standalone desktop application using a webcam to detect the user's gaze and estimate screen time. Leverages the Neural Processing Unit (NPU) of an AI PC for local inference.

The formal implementation for SenSys2025 paper: SecureGaze: Defending Gaze Estimation Against Backdoor Attacks

Estimate person gaze based on head orientation and feature landmarks

Computer-Pointer-Controller-OpenVINO is an application which uses a gaze detection model to control the mouse pointer movement. The input requires a video or a live stream from your webcam.