Enhancing Saliency Prediction in Monitoring Tasks: The Role of Visual Highlights

TL;DR

This paper investigates how visual highlights influence user attention in drone monitoring, introducing a new saliency model that leverages highlight cues to improve attention prediction accuracy.

Contribution

The paper presents a novel highlight-informed saliency model (HISM) that incorporates visual highlight cues to enhance saliency prediction in monitoring tasks.

Findings

Visual highlights significantly speed up attention shifts.

HISM outperforms traditional saliency models in highlight conditions.

Visual cues can be effectively integrated into saliency prediction models.

Abstract

This study examines the role of visual highlights in guiding user attention in drone monitoring tasks, employing a simulated interface for observation. The experiment results show that such highlights can significantly expedite the visual attention on the corresponding area. Based on this observation, we leverage both the temporal and spatial information in the highlight to develop a new saliency model: the highlight-informed saliency model (HISM), to infer the visual attention change in the highlight condition. Our findings show the effectiveness of visual highlights in enhancing user attention and demonstrate the potential of incorporating these cues into saliency prediction models.