Machine learning of where people look in images/videos

Ziqi Li


Supervised by Hantao Liu; Moderated by Irena Spasic

Do you know where you are looking at while watching online videos? Do you know where the computers think you are looking at? Modelling visual saliency - predicting where human eyes pay attention to in visual content - has been a very active research area over the past few years in both academia and industry. This project aims to analyse visual attention data (both ground truth and predicted) in emerging applications in image and vision computing, such as computer rendered images, high-dynamic-range (HDR) imaging, medical imaging, and mobile.

The main objective is to assess and/or improve the prediction accuracy of a set of state-of-the-art saliency models over visual content. The project will highlight pros and cons of each saliency model tested and point out different directions along which research can be devoted to improve these models.

Final Report (07/09/2023) [Zip Archive]

Publication Form