International Conference on Computer Vision, ICCV 2025

Giuseppe Cartella, Vittorio Cuculo and Marcella Cornia took part in the International Conference on Computer Vision (ICCV) presenting the paper “Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction”, co‑authored by Giuseppe Cartella, Vittorio Cuculo, Alessandro D’Amelio, Marcella Cornia, Giuseppe Boccignone and Rita Cucchiara. The work introduces ScanDiff, a model that combines diffusion models and Vision Transformers to generate more diverse and realistic gaze trajectories, advancing the state of the art in human scanpath prediction.

For more information, see the programme.