Predicting Eye Fixations on Webpage With an Ensemble of Early Features and High-Level Representations from Deep Network

摘要

In recent decades, webpages are becoming an increasingly important visual information source. Compared with natural images, webpages are different in many ways. For example, webpages are usually rich in semantically meaningful visual media (text, pictures, logos, and animations), which make the direct application of some traditional low-level saliency models ineffective. Besides, distinct web-viewing patterns such as top-left bias and banner blindness suggest different ways for predicting attention deployment on a webpage. In this study, we utilize a new scheme of low-level feature extraction pipeline and combine it with high-level representations from deep neural networks. The proposed model is evaluated on a newly published webpage saliency dataset with three popular evaluation metrics. Results show that our model outperforms other existing saliency models by a large margin and both low- and high-level features play an important role in predicting fixations on webpage.