Predicting Eye Gaze Location on Websites

TL;DR

This paper introduces a deep learning model that predicts eye-gaze locations on websites from screenshots, using a unified dataset and attention mechanisms to improve accuracy and establish a new benchmark.

Contribution

It presents a novel dataset and a deep learning approach combining image and text data for accurate eye-gaze prediction on websites.

Findings

The model achieves state-of-the-art accuracy in eye-gaze prediction.

Fine-tuning on the unified dataset significantly improves performance.

The approach effectively focuses on targeted areas like images and text.

Abstract

World-wide-web, with the website and webpage as the main interface, facilitates the dissemination of important information. Hence it is crucial to optimize them for better user interaction, which is primarily done by analyzing users' behavior, especially users' eye-gaze locations. However, gathering these data is still considered to be labor and time intensive. In this work, we enable the development of automatic eye-gaze estimations given a website screenshots as the input. This is done by the curation of a unified dataset that consists of website screenshots, eye-gaze heatmap and website's layout information in the form of image and text masks. Our pre-processed dataset allows us to propose an effective deep learning-based model that leverages both image and text spatial location, which is combined through attention mechanism for effective eye-gaze prediction. In our experiment, we show the benefit of careful fine-tuning using our unified dataset to improve the accuracy of eye-gaze predictions. We further observe the capability of our model to focus on the targeted areas (images and text) to achieve high accuracy. Finally, the comparison with other alternatives shows the state-of-the-art result of our model establishing the benchmark for the eye-gaze prediction task.