Four papers accepted at ICCV 2025

August 04, 2025

Four papers accepted at ICCV 2025
Publications

We are proud to announce that the following papers have been accepted to ICCV 2025 , that will take place from October 19th to October 23rd in Honolulu (United States).


  • What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models [paper] [project page]
    by Lorenzo Baraldi, Davide Bucciarelli, Federico Betti, Marcella Cornia, Lorenzo Baraldi, Nicu Sebe, Rita Cucchiara

  • Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation [paper] [project page]
    by Luca Barsellotti, Lorenzo Bianchi, Nicola Messina, Fabio Carrara, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Rita Cucchiara

  • Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction [paper] [project page]
    by Giuseppe Cartella, Vittorio Cuculo, Alessandro D'Amelio, Marcella Cornia, Giuseppe Boccignone, Rita Cucchiara

  • MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models
    by Vittorio Pipoli, Alessia Saporita, Federico Bolelli, Marcella Cornia, Lorenzo Baraldi, Costantino Grana, Rita Cucchiara, Elisa Ficarra