Gaze EstiMation

Gaze estimation, the process of determining where someone is looking based on images of their eyes, aims to accurately predict gaze direction from various input modalities, including images and videos. Current research focuses on improving accuracy and robustness in challenging real-world scenarios, employing deep learning models, particularly those leveraging appearance-based methods and incorporating contextual information like scene understanding and semantic cues to enhance performance. This field is crucial for applications ranging from human-computer interaction and assistive technologies to medical diagnostics and behavioral analysis, offering valuable insights into human attention and cognition.