Webpage Saliency Prediction with Two-stage Generative Adversarial Networks
This work addresses a domain-specific challenge in computer vision for improving webpage design and user experience, but it appears incremental as it builds on existing GAN methods with added outline information.
The paper tackles webpage saliency prediction by proposing a two-stage generative adversarial network that incorporates webpage outline information to generate saliency maps indicating regions of interest, achieving better performance on the FIWI dataset.
Web page saliency prediction is a challenge problem in image transformation and computer vision. In this paper, we propose a new model combined with web page outline information to prediction people's interest region in web page. For each web page image, our model can generate the saliency map which indicates the region of interest for people. A two-stage generative adversarial networks are proposed and image outline information is introduced for better transferring. Experiment results on FIWI dataset show that our model have better performance in terms of saliency prediction.