Lorenzo Berlincioni

PhD in Machine Learning and Computer Vision

Currently PostDoc Researcher at MICC

My areas of interests are mostly Generative models, NLP and trajectory prediction.

Currently working on diffusion models for conditional image generation and graph convolutional networks for 3D point cloud upscaling.

news

Oct 4, 2024	Our paper Prompt and Prejudice investigates the impact of using first names in Large Language Models (LLMs) and Vision Language Models (VLMs), particularly when prompted with ethical decision-making tasks. This paper presents a rigorous approach to investigating the impact of demographic information, specifically first names, on the ethical decision-making capabilities of large language models and vision language models. arxiv x.com connectedPapers
May 10, 2023	Our paper Neuromorphic Event-based Facial Expression Recognition got accepted at EVENTVISION2023 CVPR workshop. I’ll be there in Vancouver,Canada full day June 19 2023.
Oct 31, 2022	Started PostDoc research fellowship for 3D video point cloud compression
Jul 16, 2022	Partecipated at ICVSS 2022 - International Computer Vision Summer School

selected publications

Multiple Future Prediction Leveraging Synthetic Trajectories

Lorenzo Berlincioni, Federico Becattini, Lorenzo Seidenari, and 1 more author

2021

HTML
Partially Fake It Till You Make It: Mixing Real and Fake Thermal Images for Improved Object Detection

Francesco Bongini, Lorenzo Berlincioni, Marco Bertini, and 1 more author

2021

Abs HTML

In this paper we propose a novel data augmentation approach for visual content domains that have scarce training datasets, compositing synthetic 3D objects within real scenes. We show the performance of the proposed system in the context of object detection in thermal videos, a domain where i) training datasets are very limited compared to visible spectrum datasets and ii) creating full realistic synthetic scenes is extremely cumbersome and expensive due to the difficulty in modeling the thermal properties of the materials of the scene. We compare different augmentation strategies, including state of the art approaches obtained through RL techniques, the injection of simulated data and the employment of a generative model, and study how to best combine our proposed augmentation with these other techniques. Experimental results demonstrate the effectiveness of our approach, and our single-modality detector achieves state-of-the-art results on the FLIR ADAS dataset.
Autonomous driving research with CARLA simulator

Lorenzo Berlincioni

2022

HTML