2024/03/08 by He, Tianhao, Niforatos, Evangelos, Kortuem, Gerd
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)
paper · doi:10.48550/arxiv.2403.05201
Video-Based Design (VBD) uses video as a primary medium for analyzing user interactions, prototyping, and generating design insights. However, current VBD workflows are constrained by labor-intensive, inconsistent manual annotations that fragment attention and delay insights. Computer Vision (CV)-powered automatic annotation offers opportunities to reduce manual effort while supporting higher-level interpretation. This paper investigates human-AI collaboration in video analysis by examining how different levels of automated support shape user experience in VBD. We developed MarkupLens, a CV-assisted annotation platform, and conducted a between-subjects eye-tracking study with 36 designers in an urban VBD case. We compared three levels of automation: no support, partial support, and full support, and found that higher levels improved annotation quality, reduced cognitive load, and interestingly, enriched reflection. Our insights on automation levels inform adjustable autonomy and mixed-initiative system design beyond VBD tasks.