Neural Networks Based Solutions for Geotagging of Objects
About this Topic:
Deep Neural Networks (DNNs) have had tremendous positive impact on performance in several tasks in image processing (e.g. image segmentation).
In this seminar, the presenter will present works done in their team for improving the performance of DNNs, and how efficient solutions based on DNN combined with Graphs, can be designed in applications such as automatic discovery and geotagging of objects.
About the Presenter:
Rozenn Dahyot received the Ph. D. degree from the University Louis Pasteur Strasbourg, France in 2019.
She is currently a Professor of Computer Science at Maynooth University (Ireland). Before joining Maynooth University, she was an Assistant then Associate Professor in Statistics (2008-2021), Lecturer in Computer Science (2005-2008) in the School of Computer Science and Statistics in Trinity College Dublin (Ireland). Before that, she had positions as Research Fellow on European projects (FP5, FP6) with Trinity College Dublin and Cambridge University (UK, 2002-2005), and Research Assistant in Laboratoire des Ponts et Chaussées Strasbourg (France, 1998-2001).
Dr. Dahyot has served as secretary (2008-2014) and president (2014-2020) of the Irish Pattern Recognition and Classification Society (IPRCS) that organizes the yearly Irish Machine Vision and Image Processing Conference (IMVIP).
Want to learn more about upcoming events & webinars?
Visit the events section of the Signal Processing website to see all upcoming lectures, workshops, webinars, and more.