W
Wilson Y. F. Yuen
Publications - 7
Citations - 143
Wilson Y. F. Yuen is an academic researcher. The author has contributed to research in topics: Deep learning & Convolutional neural network. The author has an hindex of 5, co-authored 7 publications receiving 66 citations.
Papers
More filters
Journal ArticleDOI
SSIM-Based Global Optimization for CTU-Level Rate Control in HEVC
Mingliang Zhou,Xuekai Wei,Shiqi Wang,Sam Kwong,Chi-Keung Fong,Peter H. W. Wong,Wilson Y. F. Yuen,Wei Gao +7 more
TL;DR: This paper establishes the SSIM-based rate-distortion model based on the divisive normalization scheme, which is applied to the CTU-level rate control and transformed into a global optimization problem solved by convex optimization.
Journal ArticleDOI
A Novel Patch Variance Biased Convolutional Neural Network for No-Reference Image Quality Assessment
Lai-Man Po,Mengyang Liu,Wilson Y. F. Yuen,Yuming Li,Xuyuan Xu,Chang Zhou,P.H.W. Wong,Kin Wai Lau,Hon-Tung Luk +8 more
TL;DR: The conventional CNN-based NR-IQA algorithm is enhanced to avoid homogenous patches for the network training and quality score estimation and a variance-based weighting average is used to bias the final image quality score to the patches with complex structure.
Journal ArticleDOI
Data-Driven Rate Control for Rate-Distortion Optimization in HEVC Based on Simplified Effective Initial QP Learning
TL;DR: The proposed LIQP method outperforms the latest HM-16.14 by achieving significant gains on R-D performance, quality smoothness, and more stable buffer occupancy control, and can also work well for scene change cases.
Journal ArticleDOI
Global Rate-Distortion Optimization-Based Rate Control for HEVC HDR Coding
TL;DR: An HDR-Visual Difference Predictor (VDP)-2-based rate-distortion (R-D) model to improve the coding performance and a new model parameter estimation method to further reduce the RC errors is proposed.
Journal ArticleDOI
Angular Deep Supervised Hashing for Image Retrieval
Chang Zhou,Lai-Man Po,Wilson Y. F. Yuen,Kwok-Wai Cheung,Xuyuan Xu,Kin Wai Lau,Yuzhi Zhao,Mengyang Liu,Peter H. W. Wong +8 more
TL;DR: The proposed Angular Deep Supervised Hashing (ADSH) method can generate high-quality and compact binary codes, which can achieve state-of-the-art performance as compared with conventional image hashing and deep learning-based hashing methods.