Deep Learning in Computer Vision: Algorithms, Applications, and Theory


Ping Luo,The University of Hong Kong


2019.09.17 15:00-16:00


Room 306, No.5 Science Building


This talk covers the frontier of deep learning in three aspects. First, I will go through multiple vision-based systems including holistic face analyses, object detection and segmentation, Al in Fashion as well as autonomous driving. Second, I will introduce a new family at Neural Architecture Search (NAS) algorithms by using differential continuous optimization. Third, I will cover advanced topic of theoretically understanding normalization methods such as Batch Normalization in deep learning.


Dr. Ping Luo is an Assistant Professor in the Department of Computer Science, The University of Hong Kong (HKU). He received his PhD degree in 2014 from Information Engineering, the Chinese University of Hong Kong (CUHK), supervised by Prof. Xiaoou Tang and Xiaogang Wang. He was a research director in SenseTime Research. His research interests are machine learning and computer vision. He has published 60+ peer-reviewed articles in top-tier conferences and journals such as TPAMI, IJCV, ICML, ICLR, CVPR, and NeurIPS. His work has high impact with 7300+ citations according to Google Scholar. He has won a number of competitions and awards such as the first runner up in 2014 ImageNet ILSVRC Challenge, the first place in 2017 DAVIS Challenge on Video Object Segmentation, Gold medal in 2017 Youtube‐8M Video Classification Challenge, the first place in 2018 Drivable Area Segmentation Challenge for Autonomous Driving, 2011 Hong Kong PhD Fellow Award, and 2013 Microsoft Research Fellow Award (ten PhDs in Asia).