Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
CVPR 2018 With spatial feature transform layers, our SFT-GAN can generate more realistic and visually pleasing textures in comparison to state-of-the-art SRGAN and EnhanceNet. Read more ...
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
CVPR 2018 Spotlight A lightweight network with performance comparable to FlowNet2 but 30 times smaller in the model size and 1.36 times faster in the running speed. Read more ...
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
CVPR 2018 A simple block that can be used to perform profile-to-frontal face transformation in the deep feature space. Read more ...
Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
CVPR 2018 Spotlight RL-Restore learns a policy to select appropriate tools from a toolbox to progressively restore the quality of a corrupted image. Read more ...
Optimizing Video Object Detection via a Scale-Time Lattice
CVPR 2018 On ImageNet VID dataset, the proposed method achieves a competitive mAP 79.6% at 20 fps, or 79.0% at 62 fps as a performance/speed tradeoff. Read more ...
Mix-and-Match Tuning for Self-supervised Semantic Segmentation
AAAI 2018 Spotlight M&M allows networks pre-trained with self-supervised learning to outperform the supervised learning counterpart. Read more ...
Merge or Not? Learning to Group Faces via Imitation Learning
AAAI 2018 Spotlight A new face clustering framework that makes sequential merging decision based on short- and long-term rewards. Read more ...
Chen Change (Cavan) Loy
Research Assistant Professor
Laboratory: Multimedia Lab
Ho Sin-Hang Engineering Building
Department of Information Engineering
The Chinese University of Hong Kong
Shatin, NT, Hong Kong
ccloy at ie.cuhk.edu.hk
ccloy at ieee.org
Chen Change Loy is a Research Assistant Professor in the Chinese University of Hong Kong. He received his PhD (2010) in Computer Science from the Queen Mary University of London. From Dec. 2010 – Mar. 2013, he was a postdoctoral researcher at Queen Mary University of London and Vision Semantics Limited. His research interests include computer vision and pattern recognition, with focus on face analysis, deep learning, and visual surveillance. He serves as an Associate Editor of IET Computer Vision Journal and a Guest Editor of the International Journal of Computer Vision. He currently serves as an Area Chair of ECCV 2018 and BMVC 2018. He is a senior member of IEEE.
Highlight Recent Papers, News
06/2018: We won the DAVIS Challenge 2018 as first runner-up. Congratulation to Xiaoxiao Li! Check the technical report that describes the winning method.
04/2018: We organize a new challenge WIDER Face and Pedestrian Challenge in conjunction with ECCV 2018. There are three exciting tracks with great prizes! Deadline of challenge: July 8, 2018
03/2018: Updated results on WIDER FACE. Check the leaderboard.
03/2018: I will serve as the area chair of ECCV 2018 and BMVC 2018.
02/2018: Five papers accepted at CVPR 2018. Two spotlights and three posters.
02/2018: International Journal on Computer Vision Special Issue on Deep Learning for Face Analysis. Submission Closed.
12/2017: Congratulation to Shizhan Zhu for receiving the Faculty's Outstanding Thesis Award 2016.
10/2017: Congratulation to Shizhan Zhu for receiving the Adrian Hao Yin Ü Gateway Fellowship for UC Berkeley.
07/2017: We won the DAVIS Challenge 2017 as champion. Congratulation to Xiaoxiao Li and the team. Check lixx on the leaderboard and the technical report.
07/2017: We won the NTIRE 2017 Challenge on Single Image Super-Resolution as first runner-up. Congratulation to Xintao Wang and the team. Check the technical report.