Sebastiano Milardo
Sebastiano Milardo received his Bachelor’s and Master’s degrees in Computer Engineering from the University of Catania in 2011 and 2013, respectively, and earned a Ph.D. in Information and Communication Technologies from the University of Palermo in 2018. From 2014 to 2015, he was a Researcher at the Italian National Consortium of Telecommunications, contributing to the NEWCOM# and SIGMA projects. He served as a Postdoctoral Fellow at the MIT Senseable City Laboratory from 2018 to 2021, where he worked on interdisciplinary research at the intersection of urban science, networks, and data-driven technologies. Since 2021, he has been working as a freelance researcher and consultant, collaborating on projects involving advanced data analytics and artificial intelligence.
His research interests include software-defined networks, network protocols for the Internet of Things, and big data. More recently, his focus has expanded to artificial intelligence, with particular attention to large language models (LLMs), machine learning pipelines, and the practical application of AI technologies in complex, real-world scenarios.
Session
The exponential growth of video data presents significant challenges for effective content discovery. Traditional keyword search falls short when dealing with visual nuances. This talk addresses the design and implementation of a robust system for large-scale, multi-modal video retrieval, enabling search across petabytes of data using diverse inputs like text descriptions (e.g., appearance, actions) and query images (e.g., faces). We will explore an architecture combining efficient batch preprocessing for feature extraction (including person detection, face/CLIP-style embeddings) with optimized vector database indexing. Attendees will learn about strategies for managing massive datasets, optimizing ML inference pipelines for speed and cost-efficiency (touching upon lightweight models and specialized runtimes), and building interactive systems that bridge pre-computed indexes with real-time analysis capabilities for enhanced insights.