96 citations · 191 across the 9 of their papers we have counts for
10 papers
MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
Shengyu Zhang, Donghui Wang, Zhou Zhao +3
In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance. Existing methods for text-t…
Quantum algorithms for graph problems with cut queries
Troy Lee, Miklos Santha, Shengyu Zhang
Let be an -vertex graph with edges. When asked a subset of vertices, a cut query on returns the number of edges of that have exactly one endpoint in . We…
Adaptive Double-Exploration Tradeoff for Outlier Detection
Xiaojin Zhang, Honglei Zhuang, Shengyu Zhang +1
We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold…
Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Shengyu Zhang, Tan Jiang, Qinghao Huang +7
In this paper, we present an approach, namely Lexical Semantic Image Completion (LSIC), that may have potential applications in art, design, and heritage conservation, among severa…
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Pengfei Chen, Benben Liao, Guangyong Chen +1
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Mos…
Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
Pengfei Chen, Weiwen Liu, Chang-Yu Hsieh +2
Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during wh…