Adaptive Linear Regression for Appearance-Based Gaze Estimation

249 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning from Simulated and Unsupervised Images through Adversarial Training (2016, background): “5 Adaptive Linear Regression ALR) [23] R 16.”
It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation (2016, background): “Usually p is directly defined in the coordinate system of the target screen [17, 26, 27, 29] or, more generally, a virtual plane defined in the camera coordinate system [13].”
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation (2017, methodology): “Following prior work on face [62], [67] and gaze [41], [68] analysis, we use a grey-scale single channel image as input with a resolution of 60 36 pixels.”
ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation (2020, background): “Initial learning-based gaze estimation methods often assume a static head pose [1,21], with later works allowing for gradually more head pose freedom [22,33].”
Eye Tracking for Everyone (2016, unknown): “Appearance-based methods [37, 30, 22, 21, 38, 2] directly use eyes as input and can potentially work on low-resolution images.”
Appearance-based gaze estimation in the wild (2015, background): “Adaptive Linear Regression (ALR) Because it was orig inally designed for a person-specific and sparse set of train ing samples [27], ALR does not scale to large datasets.”