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
Proceedings ArticleDOI
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
TL;DR: The Efficient Channel Attention (ECA) module as discussed by the authors proposes a local cross-channel interaction strategy without dimensionality reduction, which can be efficiently implemented via 1D convolution, which only involves a handful of parameters while bringing clear performance gain.
Posted Content
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
TL;DR: This paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain, and develops a method to adaptively select kernel size of 1D convolution, determining coverage of local cross-channel interaction.
Journal ArticleDOI
Neighborhood rough set based heterogeneous feature subset selection
TL;DR: A neighborhood rough set model is introduced to deal with the problem of heterogeneous feature subset selection and Experimental results show that the neighborhood model based method is more flexible to deals with heterogeneous data.
Journal ArticleDOI
Generalized Latent Multi-View Subspace Clustering
TL;DR: This work proposes a novel subspace clustering model for multi-view data using a latent representation termed Latent Multi-View Subspace Clustering (LMSC), which explores underlying complementary information from multiple views and simultaneously seeks the underlying latent representation.
Journal ArticleDOI
Neighborhood classifiers
Qinghua Hu,Daren Yu,Zongxia Xie +2 more
TL;DR: The experimental results show that neighborhood-based feature selection algorithm is able to delete most of the redundant and irrelevant features and the classification accuracies based on neighborhood classifier is superior to K-NN, CART in original feature spaces and reduced feature subspaces, and a little weaker than SVM.