Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Beyond wheelchairs and blindfolds: Investigating disability stereotypes in T2I models with INCLUDE-BENCH
Sophia Lichtenberg, Albert Gatt, Judith Masthoff
Text-to-image (T2I) models have been shown to exhibit social biases. Prior work has mainly focused on gender, skin tone, and cultural representation within restricted occupational…
cs.CV2026
Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses
Ece Takmaz, Albert Gatt, Jakub Dotlacil
Images vary in how memorable they are to humans. Inspired by findings from cognitive science and computer vision, we explore correlates of image memorability in pretrained transfor…