Gaze Data
Gaze data, the record of eye movements, is increasingly used to understand human visual attention and cognitive processes, particularly in medical image analysis and human-computer interaction. Current research focuses on integrating gaze data with other modalities (e.g., images, text, audio) using various deep learning architectures, including graph neural networks, transformers, and generative adversarial networks, to improve model performance and interpretability in tasks such as disease classification, object detection, and information querying. This research is significant because it bridges the gap between human perception and artificial intelligence, leading to more accurate, efficient, and user-centered systems in healthcare and beyond.
Papers
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations
Stephanie Brandl, Oliver Eberle, Tiago Ribeiro, Anders Søgaard, Nora Hollenstein
PrivatEyes: Appearance-based Gaze Estimation Using Federated Secure Multi-Party Computation
Mayar Elfares, Pascal Reisert, Zhiming Hu, Wenwu Tang, Ralf Küsters, Andreas Bulling