Junchu Huang

Junchu Huang

Auto-generated profile, based on publicly available information

Junchu Huang

School of Electronic and Information Engineering, South China University of Technology, China and Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Ministry of Education, Guangzhou City, Guangdong Province, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
6 December 2022 in Journal on Computing and Cultural Heritage
Verified
Journal Article
Open access
ZZZhiheng Zhou
Zhiheng Zhou
XLXinran Liu
Xinran Liu
JSJunyuan Shang
Junyuan Shang
JHJunchu Huang
Junchu Huang
ZLZhihao Li
Zhihao Li
HJHaiping Jia
Haiping Jia
Inpainting deteriorated regions in digital Dunhuang murals is important for Dunhuang mural content preservation. Algorithms of mural image inpainting help simplify the digital restoration process of the deteriorated murals. Most of the existing algorithms can restore plausible content for homogeneous missing regions in Dunhuang mural images. However, they often fail to fill accurate color in missing regions that contain complex structures, which is mainly due to the neglect of color relevance between positions in the missing structural region and the non-missing color regions. In this article, we propose a deep learning–based, structure-guided inpainting method for the Dunhuang mural image, which utilizes relevant color information in deep features to improve the color inpainting quality for structural regions. Specifically, we design a structure-guided feature refinement module, which explicitly leverages color relevance implied in structure information to select relevant features for refining features in the missing region. In addition, we propose a multi-step scheme for feature refinement to better propagate non-missing region feature information to the missing region. We conduct experiments on Dunhuang660 and Dunhuang No. 7 Grotto datasets. The results demonstrate that our proposed method can achieve improved color inpainting quality for missing structural regions in Dunhuang mural images.

3 April 2020 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZCZengqun Chen
Zengqun Chen
ZZZhiheng Zhou
Zhiheng Zhou
JHJunchu Huang
Junchu Huang
PZPengyu Zhang
Pengyu Zhang
BLBo Li
Bo Li
Pedestrians in videos are usually in a moving state, resulting in serious spatial misalignment like scale variations and pose changes, which makes the video-based person re-identification problem more challenging. To address the above issue, in this paper, we propose a Frame-Guided Region-Aligned model (FGRA) for discriminative representation learning in two steps in an end-to-end manner. Firstly, based on a frame-guided feature learning strategy and a non-parametric alignment module, a novel alignment mechanism is proposed to extract well-aligned region features. Secondly, in order to form a sequence representation, an effective feature aggregation strategy that utilizes temporal alignment score and spatial attention is adopted to fuse region features in the temporal and spatial dimensions, respectively. Experiments are conducted on benchmark datasets to demonstrate the effectiveness of the proposed method to solve the misalignment problem and the superiority of the proposed method to the existing video-based person re-identification methods.

15 October 2022 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
CNChang Niu
Chang Niu
JSJunyuan Shang
Junyuan Shang
JHJunchu Huang
Junchu Huang
JYJunmei Yang
Junmei Yang
YSYuting Song
Yuting Song
GZGuoxu Zhou
Guoxu Zhou

1 December 2018
Verified
Conference Paper
Closed access
CNChang Niu
Chang Niu
JSJunyuan Shang
Junyuan Shang
JHJunchu Huang
Junchu Huang
YWYifan Wang
Yifan Wang
ZZZhiheng Zhou
Zhiheng Zhou
Heterogeneous domain adaptation (HDA), which learns a target classifier using labeled data from different feature and distribution, has shown promising value in knowledge discovery. Yet it is still a challenging problem. Since most of the existing approaches for HDA are in the special case, we propose a generalized method for this problem. We use Principal Components Analysis (PCA) to align the features from source and target domain. Simultaneously, we match the conditional distribution and preserve the local structure, for the purpose of achieving discriminative feature representations. At last, comprehensive experiments verify that our method can significantly outperform state-of-the-art learning methods on several public image datasets.