Roberto Amoroso

According to our database, Roberto Amoroso authored at least 15 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Parents and Children: Distinguishing Multimodal Deepfakes from Natural Images.

Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto Del Bimbo, Rita Cucchiara

ACM Trans. Multim. Comput. Commun. Appl., January, 2025

Architetture Multimodali Attentive di Deep Learning per la Comprensione Visivo-Semantica.

Roberto Amoroso

PhD thesis, 2025

Learning to mask and permute visual tokens for Vision Transformer pre-training.

Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Andrea Pilzer, Rita Cucchiara

Comput. Vis. Image Underst., 2025

Perceive. Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries.

Roberto Amoroso, Gengyuan Zhang, Rajat Koner, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

2024

Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries.

Roberto Amoroso, Gengyuan Zhang, Rajat Koner, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp

CoRR, 2024

What's Outside the Intersection? Fine-grained Error Analysis for Semantic Segmentation Beyond IoU.

Maximilian Bernhard, Roberto Amoroso, Yannic Kindermann, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp, Matthias Schubert

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

FOSSIL: Free Open-Vocabulary Semantic Segmentation through Synthetic References Retrieval.

Luca Barsellotti, Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation.

Luca Barsellotti, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Enhancing Open-Vocabulary Semantic Segmentation with Prototype Retrieval.

Luca Barsellotti, Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the Image Analysis and Processing - ICIAP 2023, 2023

A Federated Learning Approach to Traffic Matrix Estimation using Super-resolution Techniques.

Roberto Amoroso, Lorenzo Pappone, Flavio Esposito

Proceedings of the 20th IEEE Consumer Communications & Networking Conference, 2023

Superpixel Positional Encoding to Improve ViT-based Semantic Segmentation Models.

Roberto Amoroso, Matteo Tomei, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the 34th British Machine Vision Conference 2023, 2023

2022

Investigating Bidimensional Downsampling in Vision Transformer Models.

Paolo Bruno, Roberto Amoroso, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the Image Analysis and Processing - ICIAP 2022, 2022

2021

Improving Indoor Semantic Segmentation with Boundary-Level Objectives.

Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the Advances in Computational Intelligence, 2021

Assessing the Role of Boundary-Level Objectives in Indoor Semantic Segmentation.

Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara

Proceedings of the Computer Analysis of Images and Patterns, 2021

2020

Estimation of traffic matrices via super-resolution and federated learning.

Roberto Amoroso, Flavio Esposito, Maria Luisa Merani

Proceedings of the CoNEXT '20: The 16th International Conference on emerging Networking EXperiments and Technologies, 2020