A small parallel Croatian-English corpus was analyzed in order to study the role of implicit prosody in silent reading. Croatian and English are well suited for this purpose with English having a stress-timed prosody and Croatian being more of a syllable-...

Appearance-based gaze tracking algorithms, which compute gaze direction from user face images, are an attractive alternative to infrared-based external devices. Their accuracy has greatly benefited by using powerful machine-learning techniques. The ...

We introduce the Webcam Eye Dataset (WEyeDS) 1, a dataset of images collected from desktops and laptops. WEyeDS will be openly available with the goal of providing researchers a dataset for training gaze estimation models. Our preliminary dataset was ...

The advancement of image restoration, especially in reconstructing missing or damaged image areas, has benefited significantly from self-supervised learning techniques, notably through the recent Masked Auto Encoder (MAE) strategy. In this project, we ...

This paper presents a novel Contrastive Self-Attention Convolutional Neural Network (CSA-CNN) model with enhanced Difficulty Aware (DA) loss function to improve the segmentation of pupils in eye images. The incorporation of transformer-style self-...

Calibrating gaze estimation models is crucial to maximize the effectiveness of these systems, although its implementation also poses challenges related to usability. Therefore, the simplification of this process is key. In this work, we dissect the ...

This study investigated saccadic behaviour during the fusional vergence test as a function of disparity vergence demand. Participants’ divergence and convergence fusional vergence ranges were measured in an haploscopic setup. Disparity of a column of ...