Hongguang Zhang (张洪广) PhD Assistant Professor at Systems Engineering Institute, AMS Computer Vision, Machine Learning, Transfer Learning Email: zhang.hongguang@outlook.com [Publications] [Education] [Awards] [Activities]

I am an assistant professor at Systems Engineering Institute, AMS.

I obtained the PhD from CECS of Australian National University (ANU) and Data61/CSIRO in 2020. Before this, I graduated from Shanghai Jiao Tong University (SJTU) for B.Eng in Electrical Engineering and Automation in 2014, then obtained the M.Eng from National University of Defense Technology (NUDT) in 2016.

My main research topics are computer vision and machine learning. Specifically, I am currently doing research works on zero-shot learning, few-shot learning, federated learning with deep learning approaches. I am also interested in some low-level vision tasks, e. g. image and video deblurring.

Publications [Google Scholar]

• LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification
  Chun Liu*, Hongguang Zhang*, Kainan Zhao, Xinghai Ju, Lin Yang.
  ACL 2024
[bib][paper]



• Fake News Detection via Multi-scale Semantic Alignment and Cross-modal Attention
  Jiandong Wang*, Hongguang Zhang*, Chun Liu, Xiongjun Yang.
  SIGIR 2024
[bib][paper]



• The Principle and Typical Implementation of Foundation Model-based Intelligent Aided Decision Making System
  Hongguang Zhang, Lin Yang, Xiongjun Yang, Linru Ma, Hao Dai.
  JC2 2024
[bib][paper]



• Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
  Wenxiao Deng, Wenbin Li, Tianyu Ding, Lei Wang, Hongguang Zhang, Kuihua Huang, Jing Huo, Yang Gao.
  CVPR 2024
[bib][paper]



• Saliency-guided Meta-Hallucinator for Few-shot Learning
  Hongguang Zhang, Chun Liu, Jiandong Wang, Linru Ma, Piotr Koniusz, Philip H. S. Torr, Lin Yang.
  SCIS 2024
[bib][paper]



• Event-guided Multi-Patch Network with Self-supervision for Non-uniform Motion Deblurring
  Hongguang Zhang, Limeng Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz.
  IJCV 2023

    @article{zhang2022event,
     title={Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring},
     author={Zhang, Hongguang and Zhang, Limeng and Dai, Yuchao and Li, Hongdong and Koniusz, Piotr},
     journal={International Journal of Computer Vision},
     pages={1--18},
     year={2022},
     publisher={Springer}}
  

[bib][paper]



• Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer
  Hongguang Zhang, Piotr Koniusz, Philip H. S. Torr.
  ACCV 2022

  @InProceedings{Zhang_2022_ACCV,
    author    = {Zhang, Hongguang and Torr, Philip H. S. and Koniusz, Piotr},
    title     = {Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer},
    booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)},
    month     = {December},
    year      = {2022},
    pages     = {1298-1315}}
  

[bib][paper]



• Multi-level Second-order Few-shot Learning
  Hongguang Zhang, Hongdong Li, Piotr Koniusz.
  TMM 2022

    @ARTICLE{9681205,
      author={Zhang, Hongguang and Li, Hongdong and Koniusz, Piotr},
      journal={IEEE Transactions on Multimedia}, 
      title={Multi-level Second-order Few-shot Learning}, 
      year={2022},
      volume={},
      number={},
      pages={1-1},
      doi={10.1109/TMM.2022.3142955}}
  

[bib][paper]



• Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
  Hongguang Zhang, Piotr Koniusz, Songlei Jian, Hongdong Li, Philip H. S. Torr.
  CVPR 2021

    @article{zhang2020rethinking,
      title={Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning},
      author={Zhang, Hongguang and Koniusz, Piotr and Jian, Songlei and Li, Hongdong and Torr, Philip HS},
      journal={arXiv preprint arXiv:2001.03919},
      year={2020}
    }
  

[bib][paper]



• Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
  Liyuan Pan, Shah Chowdhury, Richard Hartley, Miaomiao Liu, Hongguang Zhang, Hongdong Li.
  CVPR 2021 (Oral)

    @article{pan2020dual,
      title={Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration},
      author={Pan, Liyuan and Chowdhury, Shah and Hartley, Richard and Liu, Miaomiao and Zhang, Hongguang and Li, Hongdong},
      journal={arXiv preprint arXiv:2012.00301},
      year={2020}
    }
  

[bib][paper]



• Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
  Piotr Koniusz*, Hongguang Zhang*.
  TPAMI 2021

    @article{koniusz2020power,
      title={Power normalizations in fine-grained image, few-shot image and graph classification},
      author={Koniusz, Piotr and Zhang, Hongguang},
      journal={arXiv preprint arXiv:2012.13975},
      year={2020}
    }
  

[bib][paper]



• Few-shot Action Recognition with Permutation-invariant Attention
  Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip H. S. Torr, Piotr Koniusz.
  ECCV 2020 (Spotlight)

    @inproceedings{zhang2020few,
      title={Few-shot action recognition with permutation-invariant attention},
      author={Zhang, H and Zhang, L and Qi, X and Li, H and Torr, PHS and Koniusz, P},
      booktitle={Proceedings of the European Conference on Computer Vision (ECCV 2020)},
      volume={12350},
      year={2020},
      organization={Springer}
    }
  

[bib][paper][code]



• One-shot Video-based Person Re-Identification with Variance Subsampling Algorithm
  Jing Zhao, Wenjing Yang, Mingliang Yang, Wanrong Huang, Qilong Yang, Hongguang Zhang.
  CAVW 2020

    @article{zhao2020one,
      title={One-shot video-based person re-identification with variance subsampling algorithm},
      author={Zhao, Jing and Yang, Wenjing and Yang, Mingliang and Huang, Wanrong and Yang, Qiong and Zhang, Hongguang},
      journal={Computer Animation and Virtual Worlds},
      volume={31},
      number={4-5},
      pages={e1964},
      year={2020},
      publisher={Wiley Online Library}
    }
  

[bib][paper]



• Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
  Hongguang Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz.
  CVPR 2019

@article{zhang2019deep,
  title={Deep Stacked Hierarchical Multi-patch Network for Image Deblurring},
  author={Zhang, Hongguang and Dai, Yuchao and Li, Hongdong and Koniusz, Piotr},
  journal={arXiv preprint arXiv:1904.03468},
  year={2019}
}
  

[bib][paper][code]



• Few-shot Learning via Saliency-guided Hallucination of Samples
  Hongguang Zhang, Jing Zhang, Piotr Koniusz.
  CVPR 2019

@article{zhang2019few,
  title={Few-shot Learning via Saliency-guided Hallucination of Samples},
  author={Zhang, Hongguang and Zhang, Jing and Koniusz, Piotr},
  journal={arXiv preprint arXiv:1904.03472},
  year={2019}
}
  

[bib][paper][code]



• Power Normalizing Second-order Similarity Network for Few-shot Learning
  Hongguang Zhang, Piotr Koniusz.
  WACV 2019 (Oral)

@inproceedings{zhang2019power,
  title={Power normalizing second-order similarity network for few-shot learning},
  author={Zhang, Hongguang and Koniusz, Piotr},
  booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  pages={1185--1193},
  year={2019},
  organization={IEEE}
}
  

[bib][paper] [code]



• Model Selection for Generalized Zero-shot Learning
  Hongguang Zhang, Piotr Koniusz.
  ECCV 2018

@inproceedings{zhang2018model,
  title={Model selection for generalized zero-shot learning},
  author={Zhang, Hongguang and Koniusz, Piotr},
  booktitle={European Conference on Computer Vision},
  pages={198--204},
  year={2018},
  organization={Springer}
}
  

[bib] [paper]



• Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond
  Piotr Koniusz*, Yusuf Tas*, Hongguang Zhang, et al.
  ECCV 2018 (Oral)

@InProceedings{Koniusz_2018_ECCV,
  author = {Koniusz, Piotr and Tas, Yusuf and Zhang, Hongguang and Harandi, Mehrtash and Porikli, Fatih and Zhang, Rui},
  title = {Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond},
  booktitle = {The European Conference on Computer Vision (ECCV)},
  month = {September},
  year = {2018}
}
  

[bib] [paper][download]



• Zero-shot Kernel Learning
  Hongguang Zhang*, Piotr Koniusz*.
  CVPR 2018

@InProceedings{Zhang_2018_CVPR,
  author = {Zhang, Hongguang and Koniusz, Piotr},
  title = {Zero-Shot Kernel Learning},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2018}
}
  

[bib] [paper] [code]



• A Deeper Look at Power Normalizations
  Piotr Koniusz*, Hongguang Zhang*.
  CVPR 2018

@InProceedings{Koniusz_2018_CVPR,
  author = {Koniusz, Piotr and Zhang, Hongguang and Porikli, Fatih},
  title = {A Deeper Look at Power Normalizations},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2018}
}
  

[bib] [paper]

• 2016.10 - 2020.05: Ph.D., Australian National University, Supervisor: Dr. Piotr Koniusz, Prof. Hongdong Li
• 2019.08 - 2019.12: Academic Visitor, University of Oxford, Torr Vision Group, Supervisor: Prof. Philip H. S. Torr
• 2014.09 - 2016.06: M.Eng, National University of Defense Technology
• 2010.09 - 2014.06: B.Eng, Shanghai Jiao Tong University

• Beijing Nova Program, Beijing Municipal Science and Technology Commission, 2022-2025
• Youth Science Fund Project, NSFC, 2022-2024

• Fellow of Beijing Nova Program, 2022
• ECCV Outstanding Reviewer, 2022
• Peng Cheng Laboratory (PCL) Overseas Youth Talents Forum, 2020
• ANU CECS Dean's Travel Award, 2019
• ANU Vice-Chancellor's Travel Grant, 2019
• Data61/CSIRO Scholarship, 2018
• ICML Travel Grant, 2017
• China Scholarship Council PhD Scholarship, 2016
• Merit Postgraduate Student Innovation Fellowship, NUDT, 2016
• Kuang-hua Fellowship, NUDT, 2015
• Outstanding Graduate Award, SJTU, 2014
• Shanghai Government Scholarship, SJTU, 2013
• Shanghai Second-class Award of National Undergraduate Electronic Design Contest, SJTU, 2013
• Academic Excellence Fellowship, SJTU, 2013
• National Endeavor Fellowship, SJTU, 2013
• Merit Student, SJTU, 2012-2013

• Co-organized ACCV 2018 Workshop: Museum Exhibit Identification Challenge (Open MIC) for Domain Adaptation and Few-Shot Learning.
• Conference Review: CVPR'20-21, NeruIPS'20, ICML'20-21, ICLR'20-21, ECCV'20, ICCV'19-21, AAAI'20, ACCV'20, BMVC'19-20, WACV'19-20
• Journal Review: TPAMI, IJCV, TIP, TMM, TCSVT, IMAVIS, KNOSYS
• Tutor for ENG4528 Computer Vision Semester 1 2019.

• The Leader of Graduation Oath, SJTU Graduation Ceremony, 2014
• First-class Award of 1st "In the Name of Youth" Graduation Speech Contest, SJTU, 2014
• The Anchor of NUDT News, NUDT, 2014-2016
• First-class Award of NUDT Speech Contest, NUDT, 2014
• Top 20 Billiards Players of SJTU.