Understanding and Predicting Temporal Visual Attention Influenced by Dynamic Highlights in Monitoring Task

2025-10-09

AI Summary

This study investigates the dual effects—attentional guidance versus distraction—of dynamic visual highlighting on users’ temporal visual attention during monitoring tasks, and proposes a computational model to quantitatively predict these effects. Addressing the limitation of conventional saliency models that ignore artificial highlighting interventions, we introduce the Highlight-Informed Saliency Model (HISM), which integrates eye-tracking data with normalized saliency (NS) metrics and employs temporal modeling to capture fine-grained, highlight-driven saliency evolution. Experiments demonstrate that highlighting triggers rapid attentional capture but suppresses global search behavior. HISM significantly outperforms baseline models in temporal NS prediction (p < 0.01). To our knowledge, this is the first work to explicitly incorporate highlighting as an input signal into saliency modeling. It provides an interpretable, quantitative foundation for optimizing highlighting strategies in time-critical monitoring interfaces.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Computer Vision: Motion & Tracking
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web search models and ranking

Abstract

Monitoring interfaces are crucial for dynamic, highstakes tasks where effective user attention is essential. Visual highlights can guide attention effectively but may also introduce unintended disruptions. To investigate this, we examined how visual highlights affect users' gaze behavior in a drone monitoring task, focusing on when, how long, and how much attention they draw. We found that highlighted areas exhibit distinct temporal characteristics compared to non-highlighted ones, quantified using normalized saliency (NS) metrics. Highlights elicited immediate responses, with NS peaking quickly, but this shift came at the cost of reduced search efforts elsewhere, potentially impacting situational awareness. To predict these dynamic changes and support interface design, we developed the Highlight-Informed Saliency Model (HISM), which provides granular predictions of NS over time. These predictions enable evaluations of highlight effectiveness and inform the optimal timing and deployment of highlights in future monitoring interface designs, particularly for time-sensitive tasks.

Problem

• Investigating visual highlights' impact on gaze behavior in monitoring tasks
• Quantifying temporal attention changes using normalized saliency metrics
• Developing predictive model to optimize highlight timing and deployment

Innovation

• Developed Highlight-Informed Saliency Model for predictions
• Quantified attention using normalized saliency metrics
• Predicted temporal visual attention changes dynamically