胡伟鹏

副教授

E-mail：huwp7@mail.sysu.edu.cn

研究方向：人工智能、计算机视觉、智能交通、低空智能感知、数字人认知、视觉可控生成、多模态信息处理、世界模型等

个人主页：http://scholar.google.com/citations?user=zo6ni_gAAAAJ

简介

胡伟鹏，博士，副教授，博士生导师。2022年6月获中山大学电子与信息工程学院工学博士学位；2022年10月至2026年1月于新加坡南洋理工大学电气与电子工程学院CARTIN实验室担任Research Fellow；2026年2月至今任中山大学智能工程学院副教授。主要从事人工智能和计算机视觉研究，已发表研究领域内权威期刊及会议论文30余篇（含中科院JCR一区TOP期刊、CCF-A类22篇）；其中作为一作/通讯作者论文20篇，包括IEEE T-PAMI、T-IP、T-IFS、T-MM、T-CSVT、CVPR等。担任多媒体领域国际会议IEEE ICME 2026 领域主席（Area Chair），以及机器视觉国际会议BMVC 2026 领域主席（Area Chair），并长期受邀担任多个权威期刊和会议审稿人。

电子邮箱：huwp7@mail.sysu.edu.cn，个人网站：scholar.google.com/citations?user=zo6ni_gAAAAJ

 

学科方向

研究方向是人工智能、计算机视觉、智能交通、低空智能感知、数字人认知、视觉可控生成、多模态信息处理、世界模型等。

硕/博招生专业：交通运输工程（学术博士）、电子信息（专业博士）、交通运输工程（学术硕士）、交通运输（专业硕士）。

欢迎热爱科研、具备编程基础的本科生（保研/考研）、研究生、直博生、实习生及研究人员加入，有意请邮件联系。

 

科研项目

1. 中山大学引进人才科研启动经费，2026年-2028年，在研，主持

2. 新加坡国家研究基金会，Learning for Human Behaviour Recognition and Intention Understanding，2022-2026，结题，主要参与

3. 国家自然科学基金委员会，鲁棒图像描述关键技术研究，2021-2024，结题，主要参与

4. 国家自然科学基金委员会，面向复杂场景的视频行为表达、识别与密集描述，2020-2023，结题，主要参与

5.国家重点研发计划课题，面向交通治理的跨媒体交通情景智能感知与深层理解，2019-2022，结题，主要参与

 

部分代表性论文

  1. Jiun Tian Hoe, Weipeng Hu (通讯作者), Xudong Jiang, Yap-Peng Tan, Chee Seng Chan, OneHOI: Unifying Human-Object Interaction Generation and Editing, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), accepted, 2026. (计算机顶会, CCF A)

  2. Weipeng Hu, Jiun Tian Hoe, Jianhui Li, Haifeng Hu, Xudong Jiang, Yap-Peng Tan, Cascaded Dynamic Memory Refinement and Semantic Alignment for Exo-to-Ego Cross-view Video Generation, IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), vol. 47, pp. 7490-7505, 2025. (中科院一区, TOP期刊, CCF A, IF:18.6)

  3. Weipeng Hu, Yiming Yang, Haifeng Hu, Pseudo Label Association and Prototype-based Invariant Learning for Semi-supervised NIR-VIS Face Recognition, IEEE Trans. on Image Processing (TIP), vol. 33, pp. 1448-1463, 2024. (中科院一区, TOP期刊, CCF A, IF:13.7)

  4. Jiun Tian Hoe, Xudong Jiang, Chee Seng Chan, Yap-Peng Tan, Weipeng Hu (通讯作者), InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6180-6189, 2024. (计算机顶会, CCF A)

  5. Weipeng Hu, Wenjun Yan, Haifeng Hu, Dual Face Alignment Learning Network for NIR-VIS Face Recognition, IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), vol.32, no.4, pp. 2411-2424, 2022. (中科院一区, TOP期刊, IF:11.1) (ESI高被引)

  6. Weipeng Hu, Haifeng Hu, Domain-private Factor Detachment Network for NIR-VIS Face Recognition, IEEE Trans. on Information Forensics and Security (TIFS), vol. 17, pp. 1435-1449, 2022. (中科院一区, TOP期刊, CCF A, IF:8.0)

  7. Weipeng Hu, Bohong Liu, Haitang Zeng, Yanke Hou, Haifeng Hu, Adversarial Decoupling and Modality-invariantRepresentationLearningforVisible-InfraredPersonRe-identification, IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), vol. 32, no. 8, pp. 5095-5109, 2022. (中科院一区, TOP期刊, IF:11.1)

  8. WeipengHu, HaifengHu, Adversarial Disentanglement Spectrum Variations and Cross-modality Attention Networks for NIR-VIS Face Recognition, IEEE Trans. on Multimedia (TMM), vol. 23, no. 1, pp. 145-160, 2021. (中科院一区, TOP期刊, CCF A, IF:9.7)

  9. Weipeng Hu, Haifeng Hu, Orthogonal Modality Disentanglement and Representation Alignment Network for NIR-VISFaceRecognition, IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), vol. 32, no. 6, pp. 3630-3643, 2021. (中科院一区, TOP期刊, IF:11.1)

  10. Weipeng Hu, Haifeng Hu, Dual Adversarial Disentanglement and Deep Representation Decorrelation for NIR-VISFaceRecognition, IEEE Trans. on Information Forensics and Security (TIFS), vol. 16, pp. 70-85, 2021. (中科院一区, TOP期刊, CCF A, IF:8.0)

  11. Weipeng Hu, Haifeng Hu, Disentangled Spectrum Variations Networks for NIR-VIS Face Recognition, IEEE Trans. on Multimedia (TMM), vol. 22, no. 5, pp. 1234-1248, 2020. (中科院一区, TOP期刊, CCF A, IF:9.7)

  12. Weipeng Hu, Jiun Tian Hoe, Runzhong Zhang, Yiming Yang, Haifeng Hu, Yap-Peng Tan, Motion-Guided Token Prioritization and Semantic Degradation Fusion for Exo-to-Ego Cross-view Video Generation, Information Fusion, vol. 123, pp. 103273, 2025. (中科院一区, TOP期刊, IF:15.5)

  13. Xingyue Wang, Weipeng Hu (通讯作者), Jiun Tian Hoe,Jianhui Li,Ping Hu, Yap-Peng Tan, Progressive Temporal Compensation and Semantic Enhancement for Exo-to-Ego Video Generation, Information Fusion, vol. 130, pp. 104117, 2026. (中科院一区, TOP期刊, IF:15.5)

  14. Yiming Yang, Weipeng Hu, Haifeng Hu, Dynamic Modality-Camera Invariant Clustering for Unsupervised Visible-Infrared Person Re-identification, IEEE Trans. on Neural Networks and Learning Systems (TNNLS), vol.36, no. 9,pp.16774-16787,2025. (中科院一区, TOP期刊, IF:8.9)

  15. Yiming Yang, Weipeng Hu, Haifeng Hu, Progressive Cross-modal Association Learning for Unsupervised Visible-Infrared Person Re-Identification, IEEE Trans. on Information Forensics and Security (TIFS), vol.20,pp.1290-1304,2025. (中科院一区, TOP期刊, CCF A, IF:8.0)

  16. Yiming Yang, Weipeng Hu, Haifeng Hu, Unsupervised NIR-VIS Face Recognition via Homogeneousto-Heterogeneous Learning and Residual-invariant Enhancement, IEEE Trans. on Information Forensics and Security (TIFS), vol. 19, pp. 2112-2126, 2024. (中科院一区, TOP期刊, CCF A, IF:8.0)

  17. Yiming Yang, Weipeng Hu, Haiqi Lin, Haifeng Hu, Robust Cross-domain Pseudo-labeling and Contrastive Learning for Unsupervised Domain Adaptation NIR-VIS Face Recognition, IEEE Trans. on Image Processing (TIP), vol. 32, pp. 5231-5244, 2023. (中科院一区, TOP期刊, CCF A, IF:13.7)

  18. Yiming Yang, Weipeng Hu, Haifeng Hu, Neutral Face Learning and Progressive Fusion Synthesis Network for NIR-VIS Face Recognition, IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), vol. 33, no. 10, pp. 5750-5763, 2023. (中科院一区, TOP期刊, IF:11.1)

  19. Wei Zhou, Kang Lin, Weipeng Hu, Chao Xie, Tao Su, Haifeng Hu, Yap-Peng Tan, Snippet-inter Difference Attention Network for Weakly-supervised Temporal Action Localization, IEEE Trans. on Multimedia (TMM), vol. 27, pp. 3610-3624, 2025. (中科院一区, TOP期刊, CCF A, IF:9.7)

  20. Ronghao Lin, Shuai Shen, Weipeng Hu, Qiaolin He, Aolin Xiong, Li Huang, Haifeng Hu, Yap-peng Tan, E3RG: Building Explicit Emotion-driven Empathetic Response Generation System with Multimodal Large Language Model, Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 14006-14013, 2025. (计算机顶会, CCF A)

  21. Runzhong Zhang, Yueqi Duan, Yang Chen, Weipeng Hu, Chen Cai, Suchen Wang, Yap-Peng Tan, Boundary Voting Network for Ambiguity-aware Timestamp-supervised Action Segmentation, IEEE Trans. on Circuits and Systems for Video Technology (TCSVT), vol. 35, no. 11, pp. 11323-11336, 2025. (中科院一区, TOP期刊, IF:11.1)

  22. Chao Xie, Linfeng Fei, Huanjie Tao, Yaocong Hu, Wei Zhou, Jiun Tian Hoe, Weipeng Hu, Yap-Peng Tan, Residual Quotient Learning for Zero-Reference Low-Light Image Enhancement,IEEE Trans. on Image Processing (TIP), vol. 34, pp. 365-378, 2025. (中科院一区, TOP期刊, CCF A, IF:13.7)

 

部分专利

1. 一种行人重识别匹配边界阈值设置方法、装置及相关组件，专利号：CN202011577571.3，授权日期：2024-11-22

2. 一种基于双线性联合CNN的人脸验证方法，专利号：201610399704X，授权日期：2020-10-23

3. 一种基于分层网络流图的多目标跟踪方法，专利号：CN201610382781.4，授权日期：2019-07-07

 

主要兼职

担任多媒体领域国际会议IEEE ICME 2026 领域主席(Area Chair)；担任机器视觉国际会议BMVC 2026 领域主席（Area Chair）；CSIG图像智能边缘计算专委会委员；担任T-PAMI, T-IP, T-NNLS, T-IFS, T-MM, T-CSVT, Pattern Recognition, AAAI, ACM MM等高水平期刊会议审稿人。

 

联系方式

电子邮箱： huwp7@mail.sysu.edu.cn