Deep Learning Methods for Multimodal Data
Ciclo de Conferências 2019/2020 - Tecnologia, Empresa e Sociedade
O evento decorre online - Link de Acesso
Zoom Meeting ID: 733 004 970
Abstract
Deep Learning is revolutionizing several industries in many ways, with applications ranging from autonomous driving, robotics, or medical imaging. Such applications require deep neural networks to be trained on large datasets, often of multiple data modalities such as RGB, depth, audio, etc. This talk will start by giving an overview of deep learning methods for multimodal data related to computer vision tasks, and address the specific scenario of handling missing modalities at test time.
Speaker
Nuno Cruz Garcia (DEISI/ULHT/COPELABS)
Nuno received his PhD from the University of Genova and was a researcher at the Pattern Analysis and Computer Vision lab in Istituto Italiano di Tecnologia. He worked in data analytics at Deloitte and as a data engineer at Miniclip. Before that, he received his M.Sc. degree in Computer Engineering from the University of Beira Interior in 2015. Currently, he teaches at Lusófona University and is affiliated with COPELABS. His research interests are computer vision and machine learning.