Zhizheng Zhang

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.

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).

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.

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.

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.