Predicting Visual Attention in Graphic Design Documents

TL;DR

This paper introduces a deep learning model that predicts both static visual saliency and dynamic gaze sequences in graphic design documents, especially webpages, outperforming existing methods and generalizing well across various visual media.

Contribution

It is the first to jointly predict spatial saliency and temporal fixation sequences in graphic design documents using a two-stage deep learning approach.

Findings

Model outperforms existing saliency and scanpath prediction models.

Large dataset of 450 webpages collected for evaluation.

Good generalization to comics, posters, UIs, and natural images.

Abstract

We present a model for predicting visual attention during the free viewing of graphic design documents. While existing works on this topic have aimed at predicting static saliency of graphic designs, our work is the first attempt to predict both spatial attention and dynamic temporal order in which the document regions are fixated by gaze using a deep learning based model. We propose a two-stage model for predicting dynamic attention on such documents, with webpages being our primary choice of document design for demonstration. In the first stage, we predict the saliency maps for each of the document components (e.g. logos, banners, texts, etc. for webpages) conditioned on the type of document layout. These component saliency maps are then jointly used to predict the overall document saliency. In the second stage, we use these layout-specific component saliency maps as the state representation for an inverse reinforcement learning model of fixation scanpath prediction during document viewing. To test our model, we collected a new dataset consisting of eye movements from 41 people freely viewing 450 webpages (the largest dataset of its kind). Experimental results show that our model outperforms existing models in both saliency and scanpath prediction for webpages, and also generalizes very well to other graphic design documents such as comics, posters, mobile UIs, etc. and natural images.