Assistant Professor (Research) Hongguang Zhu


Assistant Professor (Research) Hongguang Zhu

 

Dr. Hongguang Zhu

Assistant Professor (Research) Master Supervisor

Email: hgzhu@cityu.edu

Tel: (853) 8590 2383

Office Address: St. S504, Ho Hong-Leen, Ho Hong Xin's House, City University, Macau

 

Education

2019-2024 Information and Communication Engineering, PhD, Beijing Jiaotong University, China

2015-2019 Communication Engineering, Bachelor's degree, China University of Petroleum (East China), China

 

Current

Assistant Professor of Computer Science Research, Urban University of Macau

 

Research direction

Multimodal alignment, multimodal generation, continuous learning, concept erasing

 

Research and publishing

  1. Jiao, S.*, Zhu, H.*, Huang, J., Zhao, Y., Wei, Y., & Shi, H. (2024). Collaborative vision-text representation optimizing for open-vocabulary segmentation. European Conference on Computer Vision (ECCV). (計算機視覺頂會,CCF-B,Oral,*同等貢獻)
  2. Zhu, H., Wei, Y., Liang, X., Zhang, C., & Zhao, Y. (2023). CTP: Towards vision-language continual pretraining via compatible momentum contrast and topology preservation. IEEE/CVF International Conference on Computer Vision (ICCV).(計算機視覺頂會,CCF-A)
  3. Zhu, H., Zhang, C., Wei, Y., Huang, S., & Zhao, Y. (2023). ESA: External space attention aggregation for image-text retrieval. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).(IF=8.4, CCF-B)
  4. Zhu, H., Wei, Y., Zhao, Y., Zhang, C., & Huang, S. (2023). AMC: Adaptive multi-expert collaborative network for text-guided image retrieval. ACM Transactions on Multimedia Computing, Communications and Applications (TOMM).(IF=5.1, CCF-B)
  5. He, L., Zhu, H., Li, F., Bai, H., Cong, R., Zhang, C., ... & Zhao, Y. (2021). Towards fast and accurate real-world depth super-resolution: Benchmark dataset and baseline. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).(計算機視覺頂會, CCF-A)

 

Patent

  1. Wei Yunchao, Jiao Siyu, Zhu Hongguang, Zhao Yao. Open vocabulary segmentation method and system for multimodal model characterization optimization. Actual review stage. No.2024109574560.
  2. Wei Yunchao, Zhu Hongguang, Jiao Siyu, Fang Yan, Wang Mengyu, Huang Jiannan, Zhao Yao. Concept erasure method of literary graph diffusion model based on semantic enhancement and collaborative retention. Actual review stage. No.2024113502692.

 

Scientific research projects

  1. The National Natural Science Foundation of China’s “Joint Fund Project”, General AIGC forged content detection methods and key technologies, participated. (2024-2028)
  2. National Key R&D Plan, research on the intelligent recognition technology of three-dimensional image of security inspection under the complex background of civil aviation contraband, participated. (2022-2025)
  3. Technological Innovation 2030 New Generation Artificial Intelligence Major Project, Continuous Learning Theory and Methods, Participation. (2021-2024)
  4. The National Natural Science Foundation of China project is based on the classification of small samples and fine-grained image of convolutional networks based on multi-perspective correlation graphs. (2021-2024)
  5. Enterprise cooperation projects, Huawei technical cooperation ToF depth map super-scoring and edge optimization, participate. (2019-2020)