XPASS-Vis: A Dataset for Cross-Domain Personalized Image Aesthetic Assessment
Researchers have introduced XPASS-Vis, a novel dataset designed to explore personalized image aesthetic assessment across different visual domains. The dataset includes over 6,500 images from art, fashion, and landscape categories, rated by 129 annotators. Initial experiments using unsupervised domain adaptation show that personalized aesthetic preferences can be transferred across domains with moderate success, though a significant gap remains for PIAA-specific adaptation strategies. AI