AI-Assisted Visual Search: Effects of Cueing Method and Display Type on Detection, Compliance, and Skill Retention
Year: 2026
Type: article
Abstract: Artificial intelligence (AI)-based detection systems can enhance visual search in safety-critical domains, yet how they present recommendations may determine their effectiveness under display-quality constraints. We compared three cueing methods: an indirect cue signaling only presence (textual alert) and two direct cues marking the target’s location through either signal enhancement (bounding box) or noise reduction (contextual blur), across color and monochrome displays. Participants (N = 122) searched maritime aerial imagery in a fixed-order block structure (unaided, aided, unaided). Direct cues improved detection only under monochrome conditions, whereas the indirect cue lowered joint human–AI accuracy below that of the AI alone. Bounding boxes yielded the highest detection, whereas contextual blur reduced response times and increased compliance. Temporal analyses revealed that aided performance diverged from retained skill, with blur the most durable after withdrawal despite stronger signs of automation dependence. Cueing should be matched to display type and operational context, and judged by the skill that persists after support.
Authors: Marthe Gruner(Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Resources, Software, Validation, Visualization, Writing – original draft, Writing – review & editing), Toni Schumacher(Conceptualization, Software, Writing – original draft, Writing – review & editing), Angelina Grauerholz(Investigation, Writing – original draft), Jan Erik Hannig(Investigation, Writing – original draft), Christoph Schönicke, André Calero Valdez(Conceptualization, Funding acquisition, Project administration, Resources, Supervision, Writing – review & editing)
Institution: University of Lübeck
Language: English
Subfield: Human Factors and Ergonomics
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
Funder: Ministry of Defense
OpenAlex ID: W7155447400
