Unexamined Interaction Design Space for Egocentric Systems

Investigate the tasks that naturally arise in everyday settings and characterize how interaction patterns change over time for context-aware egocentric perception systems from a human–computer interaction perspective.

Background

The authors note that advances in egocentric perception have focused on recognition and understanding, but less is known about the resulting interaction design space in everyday life.

They explicitly frame two questions—what tasks arise and how patterns evolve—as open issues within HCI, motivating their longitudinal deployment as initial empirical grounding but leaving the broader space unresolved.

References

These advances have expanded what egocentric systems can perceive and recognize, but the interaction design space—what tasks naturally arise in everyday settings and how interaction patterns change over time—remains largely unexamined from an HCI perspective. Our longitudinal deployment study provides empirical grounding for these open questions.

— VisionClaw: Always-On AI Agents through Smart Glasses  (2604.03486 - Liu et al., 3 Apr 2026) in Section 2.3 Context-Aware Egocentric Perception (Related Work)

Since network size affects performance, denser or larger graphs would introduce more occlusion and clutter; Spherical, with its spacious arrangement, may better accommodate them, though this remains unverified. Real-world analysis also often involves multiple egocentric networks or temporal dynamics. Future work should test how our findings extend to larger, denser, and dynamic settings.

— Surrounded by Friends: Design and Evaluation of Immersive Layouts of Egocentric Network for Visual Analytics  (2608.27194 - Takahira et al., 27 Aug 2026) in Section 8, Limitations, subsection “Network Diversity and Dynamics”