Séminaire de Wei HU
Date: vendredi 14 juin à 10h00
Lieu: CentraleSupelec, Bâtiment Eiffel, Amphi 4
Titre: Graph Spectral Processing and Analysis for 3D Point Clouds and Beyond
Abstract: Geometric data acquired from real-world scenes, e.g., 2D depth images, 3D point clouds, and 4D dynamic point clouds, have found a wide range of applications including autonomous driving, augmented and virtual reality, surveillance, etc. Due to irregular sampling patterns of most geometric data, traditional image / video processing methodologies are limited, while Graph Signal Processing (GSP)—a fast-developing field in the signal processing community—enables processing signals that reside on irregular domains. Further, GSP provides insightful spectral interpretations and domain knowledge for the recently developed Graph Neural Networks (GNNs), leading to interpretability and robustness of GNNs. In this talk, I will mainly describe three research projects to illustrate the power of graph spectral processing and analysis in terms of geometric structure learning, unsupervised graph representation learning and interpretable analysis via GSP-based prior knowledge.Bio: Wei Hu is a tenured associate professsor and independent PI leading the GLab at Wangxuan Institute of Computer Technology, Peking University, China. She obtained the B.S. degree in Electrical Engineering from University of Science and Technology of China in 2010, and the PhD degree in Electronic and Computer Engineering from The Hong Kong University of Science and Technology in 2015. Before joining Peking University, she was a Researcher in the Imaging Science Laboratory of Technicolor, Rennes, France. Besides, she used to be a visiting student at National Institute of Informatics, Japan. Her research interests include Graph Signal Processing, Graph-based Machine Learning and their applications in the processing, analysis and synthesis of geometric data and beyond (structural data such as images, network data, brain signals, etc.), which lies at the intersection of signal processing and machine learning. She is an elected member of the Multimedia Signal Processing (MMSP) Technical Committee of IEEE Signal Processing Society, and the Multimedia Systems and Applications (MSA) Technical Committee of the IEEE Circuits and Systems Society.
—
—
__________________________________________
Dr. Giuseppe Valenzise
CNRS Researcher
Laboratoire des Signaux et Systèmes (L2S, UMR 8506)
CNRS – CentraleSupelec – Université Paris-Saclay
3, rue Joliot Curie
91192 Gif-sur-Yvette Cedex, France
Editor in Chief EURASIP Journal on Image and Video Processing
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
“Immersive Video Technologies”
