An Element Sensitive Saliency Model with Position Prior Learning for Web Pages

TL;DR

This paper introduces a novel deep generative model for predicting Web page saliency by learning position biases and element-specific features, outperforming existing models on a public dataset.

Contribution

The paper presents a new end-to-end deep saliency model with position prior learning and element-specific branches tailored for Web pages, addressing their diverse content and layout.

Findings

Outperforms state-of-the-art Web saliency models on FiWI dataset.

Effectively models position biases using variational auto-encoder.

Accurately detects discriminative regions and prominent text areas.

Abstract

Understanding human visual attention is important for multimedia applications. Many studies have attempted to learn from eye-tracking data and build computational saliency prediction models. However, limited efforts have been devoted to saliency prediction for Web pages, which are characterized by more diverse content elements and spatial layouts. In this paper, we propose a novel end-to-end deep generative saliency model for Web pages. To capture position biases introduced by page layouts, a Position Prior Learning sub-network is proposed, which models position biases as multivariate Gaussian distribution using variational auto-encoder. To model different elements of a Web page, a Multi Discriminative Region Detection (MDRD) branch and a Text Region Detection(TRD) branch are introduced, which target to extract discriminative localizations and "prominent" text regions likely to correspond to human attention, respectively. We validate the proposed model with FiWI, a public Web-page dataset, and shows that the proposed model outperforms the state-of-art models for Web-page saliency prediction.