Roberto Amoroso

My name is Roberto Amoroso. I am an ELLIS PhD student of the International Doctorate in ICT at the AImageLab research group of the University of Modena and Reggio Emilia, under the supervision of Prof. Rita Cucchiara and Prof. Lorenzo Baraldi. I am involved in the study and development of novel Computer Vision and Deep Learning techniques. Before joining AImageLab, I was Research Scholar at the Networking Research Group in Saint Louis, USA, working on Super-resolution techniques applied to Internet traffic matrices.

My primary research focus is on Semantic Image Segmentation, which includes multimodal machine learning approaches for learning new semantic concepts from textual information, aka Open-vocabulary Segmentation. In addition, I have also conducted research on the optimization of Transformer-based architecture for image classification.

For more information, visit my website.

Research Projects

• Multidisciplinary AI Italian Skills
• ROAd Digital Sustainable Twins in Emilia-Romagna
• Quality Enhancement and Watermarking for Historical Images
• Post-processing of wall and floor pose recognition and identification
• European Network of Human-centered Artificial Intelligence

Research Activities

Publications

1	Amoroso, Roberto; Zhang, Gengyuan; Koner, Rajat; Baraldi, Lorenzo; Cucchiara, Rita; Tresp, Volker "Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries" Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2025, Tucson, Arizona, Feb 28 – Mar 4, 2025 Conference
2	Baraldi, Lorenzo; Amoroso, Roberto; Cornia, Marcella; Baraldi, Lorenzo; Pilzer, Andrea; Cucchiara, Rita "Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training" COMPUTER VISION AND IMAGE UNDERSTANDING, pp. 1 -10 , 2025 Journal
3	Barsellotti, Luca; Amoroso, Roberto; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita "Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation" Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, pp. 3689 -3698 , 17th-21st June 2024, 2024 | DOI: 10.1109/CVPR52733.2024.00354 Conference
4	Amoroso, Roberto; Morelli, Davide; Cornia, Marcella; Baraldi, Lorenzo; Del Bimbo, Alberto; Cucchiara, Rita "Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images" ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS, pp. 1 -22 , 2024 Journal
5	Bernhard, Maximilian; Amoroso, Roberto; Kindermann, Yannic; Baraldi, Lorenzo; Cucchiara, Rita; Tresp, Volker; Schubert, Matthias "What’s Outside the Intersection? Fine-grained Error Analysis for Semantic Segmentation Beyond IoU" Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, Jan 4-8, 2024 Conference
6	Barsellotti, Luca; Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita "FOSSIL: Free Open-Vocabulary Semantic Segmentation through Synthetic References Retrieval" Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024, Waikoloa, Hawaii, pp. 1453 -1462 , Jan 4-8, 2024, 2024 | DOI: 10.1109/WACV57701.2024.00149 Conference
7	Amoroso, Roberto; Tomei, Matteo; Baraldi, Lorenzo; Cucchiara, Rita "Superpixel Positional Encoding to Improve ViT-based Semantic Segmentation Models" Proceedings of the British Machine Vision Conference 2023, Aberdeen, UK, 20th - 24th November 2023, 2023 Conference
8	Barsellotti, Luca; Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita "Enhancing Open-Vocabulary Semantic Segmentation with Prototype Retrieval" Proceedings of the 22nd International Conference on Image Analysis and Processing, ICIAP 2023, vol. 14234, Udine, Italy, pp. 196 -208 , September 11-15, 2023, 2023 | DOI: 10.1007/978-3-031-43153-1_17 Conference
9	Bruno, Paolo; Amoroso, Roberto; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita "Investigating Bidimensional Downsampling in Vision Transformer Models" Proceedings of the 21st International Conference on Image Analysis and Processing, vol. 13232, Lecce, Italy, pp. 287 -299 , 23 - 27 May 2022, 2022 | DOI: 10.1007/978-3-031-06430-2_24 Conference
10	Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita "Assessing the Role of Boundary-level Objectives in Indoor Semantic Segmentation" COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2021, PT 1, vol. 13052 LNCS, Virtual, pp. 455 -465 , 27 September - 01 October 2021, 2021 | DOI: 10.1007/978-3-030-89128-2_44 Conference
11	Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita "Improving Indoor Semantic Segmentation with Boundary-level Objectives" Proceedings of the 16th International Work-conference on Artificial Neural Networks, vol. 12862, Online, pp. 318 -329 , June 16-18, 2021, 2021 | DOI: 10.1007/978-3-030-85099-9_26 Conference
12	Amoroso, Roberto; Esposito, Flavio; Merani, Maria Luisa "Estimation of Traffic Matrices via Super-resolution and Federated Learning" ACM CoNext, Barcellona, Spagna, pp. 560 -561 , 1-4 dicembre 2020, 2020 | DOI: 10.1145/3386367.3431677 Other