My researches aim at (1) developing Differentiable/ Meta/ Reinforcement Learning algorithms that endow machines and devices to solve complex tasks with larger autonomy, (2) understanding foundations of deep learning algorithms, and (3) enabling applications in Machine Vision and Artificial Intelligence such as text to image/video generation, 3D vision, scene and video understanding, and medical image analysis.
Biography
Ping Luo is an Associate Professor in the Department of Computer Science at the University of Hong Kong, an Associate Director of the HKU Musketeers Foundation Institute of Data Science (HKU IDS), and a Deputy Director of the Joint Research Lab of HKU and Shanghai AI Lab. He obtained his Ph.D. in Information Engineering from the Chinese University of Hong Kong in 2014, under the supervision of Prof. Xiaoou Tang (founder of SenseTime) and Prof. Xiaogang Wang. Before joining HKU in 2019, he was a Research Director in SenseTime. He has published 100+ papers in international conferences and journals such as TPAMI, ICML, ICLR, NeurIPS, and CVPR, with over 50,000 citations on Google Scholar. He was awarded the 2015 AAAI Easily Accessible Paper, nominated for the 2022 Computational Visual Media Journal's Best Paper of the Year, won the 2022 ACL Outstanding Paper, the 2023 World Artificial Intelligence Conference (WAIC) Outstanding Papers, and was a candidate for the Best Paper at ICCV’23. He was recognized as one of the innovators under 35 in the Asia-Pacific region by the MIT Technology Review (MIT TR35) in 2020. He has mentored 30 Ph.D. students, many of whom have received significant awards such as the Nvidia Fellowship, Baidu Fellowship, WAIC Yunfan Award, etc.
DeepFashion second edition with a full-spectrum of fashion image analyses.
Meta-learning to learn normalization method for each hidden layer in ConvNet.
Understanding Batch Normalization in deep learning.
Fast scene segmentation by layer cascade deep networks.
Spatial CNN for Lane Detection.
Understanding Normalization Methods in Deep Learning.
Image Generation via GANs.
A large-scale dataset for learning general visual representation.
A large-scale face relationship dataset.
Joint learning image and language.
A large-scale dense face detection challenge.
DeepFashion first edition.
An extremely fast face recognition system .
A large-scale car re-identification benchmark.
Face celebrity dataset for attribute recognition and GANs.
Deep learning for semantic image segmentation.
Pedestrian Detection via Rich Supervisions.
A pedestrian parsing benchmark.