Federico Signoretta
Papers
1
Total Citations
2
H-Index
1
About
Federico Signoretta is an emerging researcher working at the intersection of generative modeling and human trajectory prediction. His most notable work, "AA-SGAN: Adversarially Augmented Social GAN with Synthetic Data" (2025), demonstrates a sophisticated approach to improving pedestrian motion forecasting by leveraging adversarial augmentation techniques combined with synthetic data generation. This contribution addresses a critical challenge in the field — the scarcity of diverse, real-world training data — by developing a framework that enriches existing datasets through adversarially generated synthetic samples, ultimately enhancing the robustness and generalization of Social GAN-based models. Although early in its citation trajectory with 2 citations since its 2025 publication, the work tackles a timely and high-impact problem with broad applications in autonomous driving, robotics, and smart surveillance systems. Signoretta's research reflects a growing trend of combining adversarial learning strategies with social force modeling to better capture the complex, interactive dynamics of crowd behavior. As the autonomous systems community continues to prioritize reliable motion prediction, his contributions position him as a promising voice in this rapidly evolving research landscape.
Research Focus
Key Achievements
Top Papers
- 1AA-SGAN: Adversarially Augmented Social GAN with Synthetic Data2 citations · 2025