Abstract Summary/Description
In a visually saturated world, capturing attention across diverse audiences is essential for effective design. Attention processes involve a complex interplay of neuroscience, psychology, and phenomenology. Recent advancements in deep learning have enabled significant achievements in saliency prediction, where deep models automatically learn features and generate attention maps using data from neuroscience, eye-tracking, and mathematical metrics. AI-driven attention mapping tools—such as Attention Insight, and Expoze, released in 2024— offer innovative solutions for visual engagement. However, these models face notable limitations, particularly in cross-cultural adaptability and semantic understanding. This study explores these challenges and potentials, focusing specifically on Middle Eastern designers. Using a multidisciplinary approach that incorporates neuroscience, psychology, and eye-tracking studies, this research investigates how AI-driven tools predict attention patterns and whether they can effectively accommodate non-Western visual and cultural elements. By generating and analyzing attention maps for Middle Eastern design works and collecting qualitative feedback designers, the study examines the strengths, biases, and gaps inherent in these AI models. Key findings reveal that while these tools could be useful at identifying visual focal points and enhancing workflows, they often fail to interpret culturally specific symbols, typography, and color meanings. These limitations underscore the need for more inclusive datasets and critical awareness when applying AI in global design contexts. This research contributes to the development of culturally adaptive AI tools, supporting cross-cultural design practices. The presentation invites dialogue on creating inclusive technologies that empower designers to connect with diverse audiences worldwide.
