Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetics

no code implementations • 31 Oct 2024 • Colin Conwell, Christopher Hamblin, Chelsea Boccagno, David Mayo, Jesse Cummings, Leyla Isik, Andrei Barbu

We show that unimodal vision models (e. g. SimCLR) account for the vast majority of explainable variance in these ratings.