Z
Zhizheng Zhang
Researcher at University of Science and Technology of China
Publications - 55
Citations - 1454
Zhizheng Zhang is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Image compression. The author has an hindex of 11, co-authored 44 publications receiving 562 citations.
Papers
More filters
Proceedings ArticleDOI
Relation-Aware Global Attention for Person Re-Identification
TL;DR: This work proposes an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning and proposes to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions together to learn the attention with a shallow convolutional model.
Proceedings ArticleDOI
Densely Semantically Aligned Person Re-Identification
TL;DR: Zhang et al. as discussed by the authors proposed a two-stream network that consists of a main full image stream (MF-Stream) and a densely semantically-aligned guiding stream (DSAG-Stream).
Journal ArticleDOI
Region Normalization for Image Inpainting
TL;DR: It is shown that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and a spatial region-wise normalization named Region Normalization (RN) is proposed to overcome the limitation.
Journal ArticleDOI
Causal Contextual Prediction for Learned Image Compression
TL;DR: In this article, a causal context model is proposed that separates the latent space across channels and makes use of channel-wise relationships to generate highly informative adjacent contexts, and a causal global prediction model is used to find global reference points for accurate predictions of undecoded points.
Book ChapterDOI
Learning to Run Challenge Solutions: Adapting Reinforcement Learning Methods for Neuromusculoskeletal Environments
Łukasz Kidziński,Sharada P. Mohanty,Carmichael F. Ong,Zhewei Huang,Shuchang Zhou,Anton Pechenko,Adam Stelmaszczyk,Piotr Jarosik,Mikhail Pavlov,Sergey Kolesnikov,Sergey M. Plis,Zhibo Chen,Zhizheng Zhang,Jiale Chen,Jun Shi,Zhuobin Zheng,Chun Yuan,Zhihui Lin,Henryk Michalewski,Piotr Milos,Blazej Osinski,Andrew Melnik,Malte Schilling,Helge Ritter,Sean F. Carroll,Jennifer L. Hicks,Sergey Levine,Marcel Salathé,Scott L. Delp +28 more
TL;DR: This work presents eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policyoptimization, to make it run as fast as possible through an obstacle course.