个人简介

黄文敏，博士，汕头大学数学与计算机学院计算机系讲师。博士毕业于中山大学计算机学院，广东省信息安全技术重点实验室，师从骆伟祺教授，并与IEEE Fellow、国家杰青等团队保持长期稳定的学术合作。主要研究方向为图像生成与编辑、视觉安全等。近年来，在本领域顶级期刊和会议如IEEE TVCG，IEEE TCSVT，IEEE TIFS，AAAI等发表学术论文。担任AAAI 2026、AAAI 2027程序委员会委员，以及IEEE TCSVT期刊审稿人。

研究方向

图像生成与编辑、视觉安全

代表性论文

[1] Wenmin Huang, Weiqi Luo, Xiaochun Cao, and Jiwu Huang, “LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation,” IEEE Transactions on Visualization and Computer Graphics (TVCG-2026, CCF A, IF: 6.5)

[2] Wenmin Huang, Weiqi Luo, Jiwu Huang, and Xiaochun Cao, “SDGAN: Disentangling semantic manipulation for facial attribute editing,” The AAAI Conference on Artificial Intelligence (AAAI-2024, CCF A).

[3] Wenmin Huang, Weiqi Luo, Xiaochun Cao, and Jiwu Huang, “Interactive generative adversarial networks with high-frequency compensation for facial attribute editing,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT-2024, CCF B, 中科院一区top, IF: 11.1).

[4] Wenmin Huang, Shuang Liu, Ruiling Luo, Tongzhen Si, and Zhong Zhang, “Dynamically Occluded Samples via Adversarial Learning for Person Re-identification in Sensor Networks,” Ad Hoc Networks (2021, JCR Q1, IF:4.8).

[5] Shuang Liu, Wenmin Huang, and Zhong Zhang, “Learning Hybrid Relationships for Person Re-identification,” The AAAI Conference on Artificial Intelligence (AAAI-2021, CCF A).

[6] Haobo Wang, Weiqi Luo, Xiaohua Xie, Peijia Zhen, Wenmin Huang, Jiwu Huang, “Adv-Inversion Stealthy Adversarial Attacks via GAN-Inversion for Facial Privacy Protection”, IEEE Transactions on Information Forensics and Security (TIFS-2025, CCF A, IF: 8.7)

代表性项目

1.汕头大学科研启动基金，高保真强可控人脸属性编辑方法研究，主持

代表性专利

1.一种基于潜在引导与参考引导扩散模型的人脸属性编辑和风格操控方法、系统。

2.一种基于局部图卷积网络的行人再识别方法。

ORCID ID/Scopus Author ID/Web of Science ResearcherID

0000-0002-6655-903X