I’m a PhD student at Sapienza, working on human–computer interaction and AI. Most of my projects are things people end up using, such as a desk device that corrects your posture or indoor maps for people with visual and motor disabilities, built from photos of evacuation plans.
01
ICMI ’26 - International Conference on Multimodal Interaction, Napoli
A desk-mounted edge device that tracks sitting posture with on-device pose estimation and corrects it through haptic and visual feedback. Published at ICMI ’26; in a 30-person user study every participant reported better postural awareness and none found it intrusive.
MSc in Computer Science - Sapienza University of Rome
Master’s thesis: a pipeline that turns smartphone photos of evacuation floor plans into clean, editable maps for an indoor navigation system for people with visual and motor disabilities. RT-DETR-L reaches 0.894 mAP@50 and a human-in-the-loop editor replaces manual tracing with quick corrections.
Advanced Machine Learning - Sapienza University of Rome, a.y. 2025/26
Violent actions are rare in motion datasets, so standard classifiers ignore them. We adapt TMR++ text-aligned motion embeddings with first-order MAML and a violence-aware loss: at 30 shots per class the model detects 73.1% of violent actions at a 1% false-positive rate.
02
In November 2026 I started a PhD at GamLab, Sapienza University of Rome, with Prof. Emanuele Panizzi. The topic is human–computer interaction and AI, which is where my master’s thesis was already going: a system that turns phone photos of evacuation plans into editable maps for an indoor navigation app for people with visual and motor disabilities. Of everything on this site it’s the project I care about most: it’s meant for real users and I built it end to end, from the object detector to the editor where a person fixes what the model got wrong. I also learned more from it than from any course.
I worked as a web developer during my bachelor’s and I still do a fair amount of engineering. In group projects I usually look after the models and also the code around them: training and hyperparameter searches, but also backends, Docker and, for BuddyBack, a Raspberry Pi. What I enjoy most is trying things out and then working out why a result came out the way it did, especially when it isn’t what I expected.
Away from the keyboard I’m usually outdoors: on the motorbike, snowboarding, fishing or trekking.
MSc in Computer Science
Sapienza University of Rome · 110/110 cum laude
2024 – 2026
BSc Computer Science
Sapienza University of Rome
2020 – 2024
03
Email is the quickest way to reach me. Write if you want to talk about research, a possible collaboration or one of the projects here.
fraponi98@gmail.com