H
Hong Liu
Researcher at Peking University
Publications - 121
Citations - 4997
Hong Liu is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 27, co-authored 102 publications receiving 3060 citations. Previous affiliations of Hong Liu include Chongqing University of Technology & Central South University.
Papers
More filters
Posted Content
Weakly-supervised Cross-view 3D Human Pose Estimation.
TL;DR: In this article, a weakly-supervised cross-view 3D human pose estimation method is proposed, which uses U-shaped graph convolutional networks (UGCN) to refine the coarse 3D poses.
Proceedings ArticleDOI
Virtual adversarial training for semi-supervised breast mass classification
Xuxin Chen,Ximing Wang,Kai Zhang,Kar Ming Fung,Theresa C. Thai,Kathleen N. Moore,Robert S. Mannel,Hong Liu,Bin Zheng,Yuchen Qiu +9 more
TL;DR: The experimental results suggest that the VAT-based CAD scheme can effectively utilize meaningful knowledge from unlabeled data to better classify mammographic breast mass images.
Proceedings ArticleDOI
Collaboration of spatial and feature attention for visual tracking
Hong Liu,Weiwei Wan,Ying Shi +2 more
TL;DR: Experiments under various real-world conditions show that this algorithm is able to track an object influenced by dramatic distracters while is of comparable time efficiency with meanshift.
Journal ArticleDOI
The influences of α-hemolytic Streptococcus on class switching and complement activation of human tonsillar cells in IgA nephropathy.
TL;DR: In this paper, the authors explored the association between α-hemolytic streptococcus (α-HS) infection and complement activation in human tonsillar mononuclear cells (TMCs) in IgAN.
Proceedings ArticleDOI
GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose
TL;DR: Zhang et al. as discussed by the authors proposed a novel solution, called GATOR, that contains an encoder of Graph-Aware Transformer (GAT) and a decoder with Motion-Disentangled Regression (MDR) to explore these multiple relations.