Journal of Eye Movement Research (MDPI)

AI systems increasingly influence both which images people encounter and predictions of how those images attract attention. This session examines the relationship between automated image selection, predicted visual attention and measured human responses. Peter Steidl presents Visual GEO and a two-stage account of visual communication: an image must first be recognized and selected by a machine before human attention can be measured. Hedda Martina Šola compares machine predictions with human measurements in two published studies using the same material, including a case where an AI-created design was evaluated unfavorably by another AI assessment. Together, the presentations trace the processes determining image visibility and subsequent memory, with implications for benchmarking, transparency, robustness, ethics and the generalizability of predictive models across populations and contexts. The programme includes introductions, discussion and questions.