Q
Qinghua Hu
Researcher at Tianjin University
Publications - 534
Citations - 21690
Qinghua Hu is an academic researcher from Tianjin University. The author has contributed to research in topics: Rough set & Feature selection. The author has an hindex of 62, co-authored 472 publications receiving 14060 citations. Previous affiliations of Qinghua Hu include Hebei Normal University & Huazhong University of Science and Technology.
Papers
More filters
Journal ArticleDOI
Skeleton Neural Networks via Low-rank Guided Filter Pruning
TL;DR: In this paper , a low-rank guided pruning scheme was proposed to obtain skeleton neural networks by alternatively training and pruning CNNs, which achieved a higher pruning rate and better classification performance compared to state-of-the-art compression methods.
Journal ArticleDOI
Causal-Trivial Attention Graph Neural Network for Fault Diagnosis of Complex Industrial Processes
Book ChapterDOI
A Multilevel Inference Mechanism for User Attributes over Social Networks
TL;DR: Zhang et al. as discussed by the authors proposed a cross-level model called IWM based on the theory of maximum entropy which collects attribute information by mining the global graph structure and propose a correction method based on a predefined hierarchy to realize the mutual correction between different layers of attributes.
Posted Content
Temporal-attentive Covariance Pooling Networks for Video Recognition.
TL;DR: Zilin Gao et al. as mentioned in this paper proposed a temporal attentive covariance pooling (TCP), which is inserted at the end of deep architectures, to produce powerful video representations.
Journal ArticleDOI
Discovery of Selective P2Y6R Antagonists with High Affinity and In Vivo Efficacy for Inflammatory Disease Therapy.
Yifan Zhu,Mengze Zhou,Xiangyu Cheng,Hui Wang,Yehong Li,Yueyue Guo,Yaxuan Wang,Sheng Tian,Zhoudong Zhang,Duxin Li,Qinghua Hu,Huan-Qiu Li +11 more
TL;DR: In this article , a hierarchical strategy that combines virtual screening, bioassays, and chemical optimization was presented to identify a potent P2Y6R antagonist (compound 50) which possesses excellent antagonistic activity (IC50 = 5.914 nM) and high selectivity.