Artificial intelligence (AI) techniques have impacted on our lives profoundly, such as providing more secured and resilient social environments and assisting more accurate medical diagnosis. As machine perception is one of the most fundamental and important components in computer vision and machine learning pipelines, achieving accurate and robust machine perception abilities in various situations plays a critical role in modern AI systems.


In this talk, I will present our recent research results on machine perception algorithms in surveillance systems as well as in AI assisted medical diagnosis. In particular, I will introduce our face hallucination methods that significantly improve the perception ability of surveillance systems, thus ensuring the security of our society or facilitating forensics. I will also present our developed advanced brain tumor diagnosis algorithms to address the problems of limited medical data or missing medical data which often happen in real-world clinical practice, while improving the perception ability in AI assisted medical diagnosis systems.

Speaker Bio:

Xin Yu is a Senior Lecturer at the University of Technology Sydney. Previously, he was a research fellow at the Australian National University (ANU). He received a PhD degree from Tsinghua University and a second PhD degree from the Australian National University. His research interests cover a wide range of topics in Computer Vision and Machine Learning. He has published more than 70 papers on top-tier conference papers and journals, such as CVPR, ECCV, NeurIPS, ICLR, TPAMI, and IJCV. Dr. Yu was awarded ARC Discovery Early Career Researcher Award (DECRA) in 2022. He received Outstanding Reviewer Awards multiple times in the leading computer vision conferences. He also received Best Paper Honorable Mention Award in WACV 2020, and his paper was nominated for the Best Paper Award in CVPR 2020. He is a recipient of Google Research Scholar Award in 2021 (one of the five recipients in machine perception world-wide). He also won several Challenges in the workshops of CVPR, ECCV, ACCV, etc.

About Data Science Seminar

This seminar series will be run as weekly sessions and is hosted by ITEE Data Science.

On Zoom