NAVER LABS Europe seminars are open to the public. This seminar is virtual and requires registration.
Date: 14th January 2021, 10am (GMT +01.00)
Speaker: Alessio Del Bue is a tenured senior researcher leading the PAVIS (Pattern Analyisis and computer VISion) research line of the Italian Institute of Technology (IIT) in Genova, Italy. Previously, he was a researcher in the Institute for Systems and Robotics at the Instituto Superior Técnico (IST) in Lisbon, Portugal. Before that, he obtained his Ph.D. under the supervision of Dr. Lourdes Agapito in the Department of Computer Science at Queen Mary University of London. His current research interests are related to 3D scene understanding from multi-modal input (images, depth, audio) to support the development of assistive Artificial Intelligence systems. He is co-author of more than 100 scientific publications, in refereed journals and international conferences, member of the technical committees of important computer vision conferences (CVPR, ICCV, ECCV, BMVC, etc.), and he serves as an associate editor of Patter Recognition and Computer Vision and Image Understanding journals. Finally, Dr. Del Bue is an IEEE and ELLIS member.
Abstract: In this talk I will present the current activities of Pattern Analysis and Computer Vision (PAVIS) Lab at the Italian Institute of Technology (IIT) focusing on our newly developed infrastructure for Assistive AI. After a brief introduction on the hardware and computational architecture, I will present our contributions related to Social AI, modelling and forecasting human interaction in real world scenarios, and Spatial AI, understanding and reasoning over the semantic of 3D scenes. In details, I will present first our recent efforts on Visual Social Distancing for monitoring resilient spaces (Social AI) where we deployed methods for automatically assessing the inter-personal distance among people using uncalibrated cameras in real scenarios. Then, related to Spatial AI, the talk will present active vision approaches for autonomous 3D reconstruction, exploration and localisation in unconstrained real-word scenarios with applications to AR and human-robot interaction.