Volgen
Roberto Amoroso
Titel
Geciteerd door
Geciteerd door
Jaar
Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images
R Amoroso, D Morelli, M Cornia, L Baraldi, A Del Bimbo, R Cucchiara
arXiv preprint arXiv:2304.00500, 2023
272023
Investigating Bidimensional Downsampling in Vision Transformer Models
P Bruno, R Amoroso, M Cornia, S Cascianelli, L Baraldi, R Cucchiara
Image Analysis and Processing–ICIAP 2022: 21st International Conference …, 2022
62022
FOSSIL: Free Open-Vocabulary Semantic Segmentation through Synthetic References Retrieval
L Barsellotti, R Amoroso, L Baraldi, R Cucchiara
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
42024
Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation
L Barsellotti, R Amoroso, M Cornia, L Baraldi, R Cucchiara
Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern …, 2024
32024
Assessing the role of boundary-level objectives in indoor semantic segmentation
R Amoroso, L Baraldi, R Cucchiara
Computer Analysis of Images and Patterns: 19th International Conference …, 2021
32021
Improving indoor semantic segmentation with boundary-level objectives
R Amoroso, L Baraldi, R Cucchiara
Advances in Computational Intelligence: 16th International Work-Conference …, 2021
32021
Estimation of traffic matrices via super-resolution and federated learning
R Amoroso, F Esposito, ML Merani
Proceedings of the 16th International Conference on emerging Networking …, 2020
32020
What’s Outside the Intersection? Fine-grained Error Analysis for Semantic Segmentation Beyond IoU
M Bernhard, R Amoroso, Y Kindermann, L Baraldi, R Cucchiara, V Tresp, ...
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
22024
Enhancing Open-Vocabulary Semantic Segmentation with Prototype Retrieval
L Barsellotti, R Amoroso, L Baraldi, R Cucchiara
International Conference on Image Analysis and Processing, 196-208, 2023
22023
Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training
L Baraldi, R Amoroso, M Cornia, A Pilzer, R Cucchiara
arXiv preprint arXiv:2306.07346, 2023
22023
A Federated Learning Approach to Traffic Matrix Estimation using Super-resolution Techniques
R Amoroso, L Pappone, F Esposito
2023 IEEE 20th Consumer Communications & Networking Conference (CCNC), 473-476, 2023
2023
Superpixel Positional Encoding to Improve ViT-based Semantic Segmentation Models
R Amoroso, M Tomei, L Baraldi, R Cucchiara
Proceedings of the British Machine Vision Conference 2023, 2023
2023
Stima di Matrici di Traffico tramite Super-resolution e Federated Learning
R AMOROSO
2020
Radioactive Watermarks
R Amoroso, P Fernandez, FT Figueroa, P Kartheek, AR Preda, ...
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–14