Contact:
Alessio is an independent AI/ML researcher with 10+ years of contributions in computer vision and deep learning methods
for visual privacy, decentralized collaborative spatial intelligence, and multimodal perception applied to robotics.
Alessio worked as a research contractor at the Advanced AI Lab of Samsung Research UK from October 2025 until December 2025.
Previously, he was a PostDoc with the School of Electronic Engineering and Computer Science at Queen Mary University of London (QMUL), UK, from April 2020 until October 2025.
He obtained the Ph.D. in Electronic Engineering with a research focus on Computer Vision from Queen Mary University of London, UK, in September 2020.
He obtained the Master Degree in Telecommunications Engineering and the Bachelor Degree in Electronics and Telecommunication Engineering from the University of Trento in March 2015 and February 2012, respectively.
Artificial Intelligence: Computer Vision | Machine Learning & Deep Learning | Multimodal AI
Perception for Embodied AI: Multimodal Sensing | Human-Robot Interaction | Decentralized Spatial Intelligence
Responsible AI: AI Safety | Visual Privacy | Explainable AI | Adversarial ML
Open Science: Benchmarking | Reproducibility
Paper titled "On the robustness of Vision-Language Models in zero-shot privacy classification" accepted at the 2026 ICPR Workshop on Trustworthy Document Understanding: Privacy, Unlearning, Robustness, and Explainability link
Workshop on "Reproducible Benchmarking of Robotic Grasping and Manipulation: From Advanced AI to Generalized Humanoid Intelligence" accepted at IROS 2026 link
Competition organiser
Human-to-robot handovers in the 11th RGMC@ICRA2026
Guest editor
IEEE RA-P Special Collection - Call for Papers
Learning Privacy from Visual Entities
Proceedings on Privacy Enhancing Technologies (PoPETs) 2025
A spatio-temporal multi-scale binary descriptor
IEEE Tran. Image Process. 2020
Cross-Camera View-Overlap Recognition
Int. Workshop Smart Distributed Cameras, European Conf. Computer Vision, 2022
Audio-Visual Object Classification for Human-Robot Collaboration
IEEE Int. Conf. Acoustic, Speech and Signal Process. 2022