Publications

April Yang, Roberto Amoroso, Nikita Durasov, Devansh Bisla, Sandipan Kundu, Elmar Haussmann, Ruchi Bhargava, Maying Shen, Nadine Chang, Jose M. Alvarez (2026). Scalable Parallel Prompting for Complex AV Video Captioning. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2026.

Francesco Ferroni, Prithvijit Chattopadhyay, Greg Heinrich, Mike Ranzinger, Roberto Amoroso, Alice Luo, Andrew Wang, Ming-Yu Liu (2025). Cosmos-Embed1: A Joint Video-Text Embedder for Physical AI.

Cite HuggingFace Website Demo

Roberto Amoroso (2025). Multimodal Attentive Deep Learning Architectures for Visual-Semantic Understanding. PhD Thesis.

Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia, Lorenzo_Baraldi, Andrea Pilzer, Rita Cucchiara (2025). MaPeT: Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training.

PDF Cite Code ArXiv

Roberto Amoroso, Gengyuan Zhang, Rajat Koner, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp (2024). Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries. In Winter Conference on Applications of Computer Vision (WACV) 2025.

Luca Barsellotti, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara (2024). FreeDA: Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024.

Maximilian Bernhard, Roberto Amoroso, Yannic Kindermann, Lorenzo Baraldi, Rita Cucchiara, Volker Tresp, Matthias Schubert (2023). What’s Outside the Intersection? Fine-grained Error Analysis for Semantic Segmentation Beyond IoU. In Winter Conference on Applications of Computer Vision (WACV) 2024.

Luca Barsellotti, Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara (2023). FOSSIL: Free Open-Vocabulary Semantic Segmentation through Synthetic References Retrieval. In Winter Conference on Applications of Computer Vision (WACV) 2024.

Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto Del Bimbo, Rita Cucchiara (2023). Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images.

PDF Cite Dataset ArXiv

Roberto Amoroso, Matteo Tomei, Lorenzo Baraldi, Rita Cucchiara (2023). Superpixel Positional Encoding to Improve ViT-based Semantic Segmentation Models. In British Machine Vision Conference (BMVC) 2023.

Luca Barsellotti, Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara (2023). Enhancing Open-Vocabulary Semantic Segmentation with Prototype Retrieval. In International Conference on Image Analysis and Processing (ICIAP) 2023.

Roberto Amoroso, Lorenzo Pappone, Flavio Esposito (2022). A Federated Learning Approach to Traffic Matrix Estimation using Super-resolution Techniques. In IEEE Consumer Communications and Networking Conference (CCNC) 2022.

Paolo Bruno, Roberto Amoroso, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara (2022). Investigating Bidimensional Downsampling in Vision Transformer Models. In International Conference on Image Analysis and Processing (ICIAP) 2021.

Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara (2021). Assessing the Role of Boundary-Level Objectives in Indoor Semantic Segmentation. In International Conference on Computer Analysis of Images and Patterns (CAIP) 2021.

Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara (2021). Improving Indoor Semantic Segmentation with Boundary-Level Objectives. In International Work-Conference on Artificial Neural Networks (IWANN) 2021.

Roberto Amoroso, Flavio Esposito, Maria Luisa Merani (2020). Estimation of Traffic Matrices via Super-resolution and Federated Learning. In International Conference on Emerging Networking EXperiments and Technologies (CoNEXT) 2020.