Y
Yongbing Zhang
Researcher at Tsinghua University
Publications - 160
Citations - 4294
Yongbing Zhang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Load balancing (computing) & Communication channel. The author has an hindex of 22, co-authored 153 publications receiving 2591 citations. Previous affiliations of Yongbing Zhang include University of Tsukuba & MediaTech Institute.
Papers
More filters
Proceedings ArticleDOI
Second-Order Attention Network for Single Image Super-Resolution
TL;DR: Experimental results demonstrate the superiority of the SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality.
Proceedings ArticleDOI
Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks
TL;DR: This work proposes a Cycle-in-Cycle network structure with generative adversarial networks (GAN) as the basic component to tackle the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable.
Journal ArticleDOI
STAT: Spatial-Temporal Attention Mechanism for Video Captioning
Chenggang Yan,Yunbin Tu,Wang Xingzheng,Yongbing Zhang,Xinhong Hao,Yongdong Zhang,Qionghai Dai +6 more
TL;DR: The proposed spatial-temporal attention mechanism (STAT) within an encoder-decoder neural network for video captioning successfully takes into account both the spatial and temporal structures in a video, so it makes the decoder to automatically select the significant regions in the most relevant temporal segments for word prediction.
Book
Optimal Load Balancing in Distributed Computer Systems
TL;DR: Recent research on the problem of optimal static load balancing is clearly and intuitively presented, with coverage of distributed computer system models, problem formulation in load balancing, and effective algorithms for implementing optimization.
Journal ArticleDOI
Residual Highway Convolutional Neural Networks for in-loop Filtering in HEVC.
TL;DR: Experimental results demonstrate that the proposed RHCNN is able to not only raise the PSNR of reconstructed frame but also prominently reduce the bit-rate compared with HEVC reference software.