Zhihui Hu

Zhihui Hu

Auto-generated profile, based on publicly available information

Zhihui Hu

Hikvision Research Institute, Hangzhou, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 October 2023
Verified
Conference Paper
Open access
ZHZhihui Hu
Zhihui Hu
YFYao Fu
Yao Fu
HZHong Zhao
Hong Zhao
XCXiaoyu Cai
Xiaoyu Cai
WJWeihao Jiang
Weihao Jiang
SPShiliang Pu
Shiliang Pu
Graph Convolutional Networks (GCNs) have made outstanding achievements in many tasks on graphs in recent years, but their success relies on sufficient training data. In practice, sparsely labeled graphs widely exist in the real world so self-training methods have become popular approaches by adding pseudo labeled nodes to enhance the performance of GCNs. However, we observe that most selected high-confidence pseudo labeled nodes by the existing methods would surround the true labeled nodes. It is what we called pseudo label over-dependence, which could lead to the non-uniform pseudo label distribution. Furthermore, a thorough experiment shows that the classification accuracy changes significantly under different label densities and the label-sparse regions show great potential improvement in the model performance. Based on the above findings, we theoretically analyze the constraint factors in the label-sparse regions and further propose reducing the feature distribution difference between the label-dense regions and label-sparse regions can effectively decrease the classification error. Thus, in this paper, we propose a novel Graph Label Information Migration framework (GLIM) to liberate pseudo labels from over-dependence. Specifically, we first propose a training dynamics module (TDM) that uses abundant training process information to find more reliable node labels and improve the model robustness against label noise. Then we propose a label migration module (LMM) that migrates label information from label-dense regions to label-sparse regions by a spectral based graph matching algorithm. These migrated labels are like the glimmers in the darkness, providing the supervision signals for the unlabeled nodes in label-sparse regions. Finally, we conduct extensive experiments to demonstrate the effectiveness of the proposed GLIM.

1 June 2013
Verified
Conference Paper
Closed access
ZHZhihui Hu
Zhihui Hu
AZAnd Yu Zhou
And Yu Zhou
IEEE1588 standard Precision Time Protocol (PTP) is proposed to solve the high precision time synchronization problems in the application field. This technique will be ported to LINUX + inhibits PTP program POWERPC platform, makes it with the support of hardware timestamp of 100 ns level timing accuracy. We tested and analyzed software and hardware timestamp that affects the performance of GPS clock timing system.

23 February 2022 in Scientific Programming
Verified
Journal Article
Open access
PDF file
XLXiaofeng Li
Xiaofeng Li
ZHZhihui Hu
Zhihui Hu
HGHaiyan Gu
Haiyan Gu
TYTing Yang
Ting Yang
QLQinghua Lei
Qinghua Lei
ZYZhisheng You
Zhisheng You
The aim of multiprojector interreflection compensation is to modify input images to remove complex physical stray-light effects (interreflection) from a multiprojector immersive system. This is an important but often ignored problem, which can lead to degradation of a projection image. Traditional methods usually address this problem by computing a matrix inversion. These traditional methods often ignore issue of the clarity of the generated images. In this paper, we describe a method for learning the inversion using a deep convolutional neural network (CNN), named Superresolution Compensation Net (SRCN). SRCN consists of four convolution layers to learn interactions of global light, six convolution layers, and two transposed convolution layers to extract multilevel features and generate compensation images. We also used a subpixel convolution layer to increase the resolution. To make compensation images more consistent with human visual perception, we used a perceptual loss, which compares the differences between feature maps on the VGG16 network. We implemented an immersive projector-camera display prototype (Pro-Cam) and calculated the quality index of the compensation images and the projection results. Our method achieved better results than previous methods in both objective evaluations and subjective visual perception.

8 August 2026
Verified
Conference Paper
Open access
WJWeihao Jiang
Weihao Jiang
HWHuizhao Wang
Huizhao Wang
ZHZhihui Hu
Zhihui Hu
WHWenyu Hu
Wenyu Hu
YFYao Fu
Yao Fu
JXJun Xiao
Jun Xiao