Towards End-to-end Video-based Eye-tracking

ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation

Learning-based Region Selection for End-to-End Gaze Estimation

Deep Hough-Transform Line Priors

We add line priors through a trainable Hough transform block into a deep network.

On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location

We show we can prevent CNNs from exploiting absolute location through image boundary effects.

Long-term Behaviour Recognition in Videos with Actor-focused Region Attention

Long-Term activities involve humans performing complex, minutes-long actions. Differently than in traditional action recognition, complex activities are normally composed of a set of sub-actions, that can appear in different order, duration, and …

Content-Consistent Generation of Realistic Eyes with Style

Photo-realistic Monocular Gaze Redirection Using Generative Adversarial Networks

Evaluation of Appearance-Based Methods for Gaze-Based Applications

Training Person-Specific Gaze Estimators from User Interactions with Multiple Devices