Evaluating Joint Attention for Mixed-Presence Collaboration on Wall-Sized Displays

2025-07-21

AI Summary

To address the challenge of objectively and non-intrusively quantifying shared attention in co-located mixed-reality collaboration on wall-sized displays, this paper proposes a joint attention assessment method integrating multi-user head pose and eye movement tracking. Leveraging spatiotemporal alignment algorithms to model inter-user gaze trajectory synchrony, it achieves the first dynamic, room-scale quantification of collaborative attention. The approach is device-free and compatible with large-scale display environments—including dual-wall configurations—and successfully extracts discriminative temporal features of collaborative attention in user studies. Key contributions include: (1) establishing the first non-intrusive, objective metric for joint attention in large-space mixed collaboration; and (2) empirically validating the efficacy and scalability of head–eye coordinated analysis in natural collaborative settings, thereby introducing a novel paradigm for evaluating immersive collaborative systems.

Technology Category

• Computer Vision: Motion & Tracking
• Multiagent Systems: Coordination and Collaboration
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

To understand and quantify the quality of mixed-presence collaboration around wall-sized displays, robust evaluation methodologies are needed, that are adapted for a room-sized experience and are not perceived as obtrusive. In this paper, we propose our approach for measuring joint attention based on head gaze data. We describe how it has been implemented for a user study on mixed presence collaboration with two wall-sized displays and report on the insights we gained so far from its implementation, with a preliminary focus on the data coming from one particular session.

Problem

• Evaluate mixed-presence collaboration on wall-sized displays
• Measure joint attention using head gaze data
• Develop unobtrusive room-sized evaluation methodologies

Innovation

• Measuring joint attention via head gaze
• Adapting evaluation for wall-sized displays
• Non-obtrusive room-sized collaboration metrics