Distance-based Visual Scanpath Estimation and Applications
Kailin Yin · 2023
Existing studies used to estimate visual attention with the bottom-up (e.g., image salient features) and top-down methods (e.g., task-driven information searching patterns) and have gained progressive results in computing probable visual attention with various image types, user groups, and viewing durations. However, these works are mostly based on fixed distances of viewing and cannot be generalised to visual scanpath estimation at dynamic viewing distances. Therefore, the research fills this gap by 1) investigating user's visual attention patterns at different viewing distances, and 2) developing the distance-based visual scanpath estimation model that can generate human-like visual scanpath at different distances. The research also prepares a large-scale eye tracking dataset to support the visual scanpath model and evaluates it with applications such as graphic design and advertisement. The research's main contributions are two-fold. Firstly, it provides the novel visual scanpath estimation model that works at different viewing distances and secondly, draws insights into how effective of the model in different applications.