教师简介:
中山大学副教授，博士生导师。在国际顶级会议（CVPR、ICCV、NeurIPS等）和一区期刊（IEEE TPAMI等）发表论文60余篇，获广东省杰出青年基金、中山大学优秀指导教师、广东省科学技术奖自然科学奖二等奖、中国图象图形学学会优秀博士学位论文奖（全国仅4篇）、CVPR Workshop 2021 Person In Context Challlenge 最佳论文奖，获国际顶级会议ACM MM 2022 Workshop 跨模态视频-语言定位竞赛和国际顶级会CVPR2018大规模行为识别等比赛冠军。指导的24届毕业生谭超镭同学获中山大学优秀硕士学位论文奖（论文题目：基于自然语言描述的视频内容定位），全学院仅4人入选。已毕业学生多数去腾讯、阿里妈妈、科大讯飞、南方电网、中移动和字节等大厂或重要国企，或升学读博（境外/海外名校或留本团队）。
26级硕士生可选研究方向：多模态视频理解与定位，可控视频生成/编辑，3D运动视频生成，大模型微调，模型攻击与安全，持续学习（偏机器学习），视觉语言动作模型（VLA，Vision-Language-Action）和其它自选方向。其中视觉语言动作模型方向与郑伟诗教授的机器人团队一起合作。
26级博士生可选研究方向：物理规律引导的视频生成，多模态视频理解与定位。
硕士要求：具有较强的编程能力，英语基础好（过4、6级），勤奋，有自驱力。
博士要求：有扎实的科研基础和能力，具有较强的自驱力，热爱科研。
指导方式：导师+海外博士师兄+组内师兄师姐联合指导，每周固定讨论1-2次，有机会安排到一流企业和科研团队进行科研实习。
实验室计算资源充足，欢迎2026年9月入学的夏令营/保研和读博同学联系，发送简历至 hujf5@mail.sysu.edu.cn，并抄送 2296495708@qq.com.
 |  |
研究领域:
计算机视觉，视频内容理解，多模态大模型，智慧海洋等
教育背景:
- 2010年9月～2016年12月：中山大学数学学院硕博连读
- 2015年9月～2016年9月：新加坡南洋理工大学访问学生
- 2006年9月～2010年6月：中山大学数学与应用数学 本科
工作经历:
- 2019年11月至今：中山大学计算机学院 副教授
- 2017年1月2019年10月：中山大学数据科学与计算机学院 副研究员
获奖及荣誉:
- 2022年 国际顶级会议ACM MM Workshop 跨模态视频-语言定位竞赛冠军
- 2020年 广东省科学技术奖自然科学奖 二等奖
- 2017年 中国图象图形学学会优秀博士学位论文
- 2017年 微软亚洲研究院青年学者铸星计划
- 2018年 CVPR大规模行为识别比赛MiniTrack 冠军
科研项目:
- 国家自然科学基金面上项目，跨模态视频-文本匹配与生成研究，项目负责人
- 广东省基础与应用基础研究基金杰出青年项目，面向复杂动态场景的视频解析研究，项目负责人
- 国家自然科学基金面上项目，多源视频结构化特征提取方法研究及其在行为分析的应用，项目负责人
- 国家自然科学基金青年科学基金，基于多模态时间序列异质特征学习的行为前期预测研究，项目负责人
- CCF-腾讯犀牛鸟科研基金项目，基于多模态动态融合的视频动作识别及意图预测，项目负责人
- 企业横向项目（与微信合作），基于多层次特征动态融合学习的视频动作识别，项目负责人
教授课程:
本科生课程：数学分析、数值最优化
研究生课程：模式识别、最优化理论与方法
代表性论著:
(*) 表示为通讯作者，指导学生发表论文
- Jianwei Tang(指导的硕士生), Hong Yang, Tengyue Chen, and Jian-Fang Hu*, Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic, IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2025. [CCF A，计算机视觉顶级会议]
- Fuxing Liu(指导的硕士生), Chaolei Tan, Xiaotong Lin, Yonggang Qi, Jinxuan Li, Jian-FangHu*, "SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection", Association for the Advancement of Artificial Intelligence (AAAI), 2025. [CCF A，人工智能顶级会议]
- Tianming Liang(指导的博士生), Linhui Li, Jian-FangHu*, Xiangyang Yu, Wei-Shi Zheng, and Jianhuang Lai. "Rethinking Temporal Context in Video-QA: A Comprehensive Study of Single-frame Static Bias", IEEE Transactions on Multimedia (TMM), 2024.
- Linhui Li(指导的硕士生), Xiaotong Lin, Yejia Huang, Zizhen Zhang*, and Jian-Fang Hu*, "Beyond Minimum-of-N: Rethinking the Evaluation and Methods of Pedestrian Trajectory Prediction", IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2024.
- Chaolei Tan(指导的硕士生), Zihang Lin, Junfu Pu, Zhongang Qi, Wei-Yi Pei, Zhi Qu, Yexin Wang, Ying Shan, Wei-Shi Zheng, Jian-Fang Hu*, "SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses", ACM Multimedia (ACM MM), 2024. [CCF A，多媒体顶级会议]
- Xiaotong Lin(指导的硕士生), Tianming Liang, Jianhuang Lai, and Jian-Fang Hu*，"Progressive Pretext Task Learning for Human Trajectory Prediction"，European Conference on Computer Vision (ECCV), 2024. [CCF B，计算机视觉顶级会议]
- Tianming Liang(指导的博士生), Chaolei Tan, Beihao Xia, Wei-Shi Zheng, Jian-Fang Hu*, Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels，IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2024. [CCF A，计算机视觉顶级会议]
- Chaolei Tan(指导的硕士生), Jianhuang Lai, Wei-Shi Zheng, Jian-Fang Hu*, Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding，IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2024. [CCF A，计算机视觉顶级会议]
- Jianwei Tang(指导的硕士生), Jiangxin Sun, Xiaotong Lin, Lifang Zhang, Wei-Shi Zheng, Jian-Fang Hu*, "Temporal Continual Learning with Prior Compensation for Human Motion Prediction", Conference on Neural Information Processing Systems (NeurIPS), 2023. [CCF A，计算机视觉顶级会议]
- Zihang Lin(指导的硕士生), Chaolei Tan, Jian-Fang Hu*, Zhi Jin, Tiancai Ye, and Wei-Shi Zheng, " Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [CCF A，计算机视觉顶级会议]
- Chaolei Tan(指导的硕士生), Zihang Lin, Jian-Fang Hu*, Wei-Shi Zheng, and Jianhuang Lai, " Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [CCF A，计算机视觉顶级会议]
- Jiangxin Sun(指导的硕士生), Chunyu Wang, Huang Hu, Hanjiang Lai, Zhi Jin, Jian-Fang Hu*，You Never Stop Dancing: Non-freezing Dance Generation via Bank-constrained Manifold Projection, Conference and Workshop on Neural Information Processing Systems (NeurIPS), 2022. [CCF A，计算机视觉顶级会议]
- Jiangxin Sun(指导的硕士生), Zihang Lin, Xintong Han, Jian-Fang Hu*, Jia Xu, Wei-Shi Zheng, Action-guided 3D Human Motion Prediction, Conference and Workshop on Neural Information Processing Systems (NeurIPS), 2021.
- Zihang Lin# (指导的硕士生), Jiangxin Sun#（指导的研一学生）, Jian-Fang Hu(*), Qizhi Yu, Wei-Shi Zheng, Jianhuang Lai, Predictive Feature Learning for Future Segmentation Prediction, International Conference on Computer Vision (ICCV) 2021. [CCF A，计算机视觉三大顶级会议之一]
- Xionghui Wang (指导的硕士生), Jian-Fang Hu (*), Jianhuang Lai, Jianguo Zhang, and Wei-Shi Zheng, ``Progressive Teacher-student Learning for Early Action Prediction", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [CCF A，计算机视觉顶级会议]
- Guoliang Pang (指导的硕士生), Xionghui Wang (指导的硕士生), Jian-Fang Hu (*), Qing Zhang, and Wei-Shi Zheng, DBDNet: Learning Bi-directional Dynamics for Early Action Prediction, International Joint Conference on Artificial Intelligence (IJCAI), 2019. (CCF A, 人工智能顶级会议)
- Jiangxin Sun (指导的本科生), Jiafeng Xie (指导的硕士生) , Jian-Fang Hu (*), Zihang Lin (指导的本科生), Wei-Shi Zheng, Jianhuang Lai and Wenjun Zeng, Predicting Future Instance Segmentation with Contextual Pyramid ConvLSTMs, ACM Multimedia, 2019. (CCF A类会议)
- Jian-Fang Hu#, Jiangxin Sun# , Zihang Lin, Jianhuang Lai, Wenjun Zeng, and Wei-Shi Zheng(*). "APANet: Auto-Path Aggregation for Future Instance Segmentation Prediction", IEEE Transaction on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2021. [CCF A, IF=17.73, 人工智能与计算机视觉领域最顶级期刊]
- Jian-Fang Hu, Wei-Shi Zheng(*), Jianhuang Lai, and Jianguo Zhang, "Jointly Learning Heterogeneous Features for RGB-D Activity Recognition", IEEE Transaction on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 39 (11): 2186-2200 (2017). [CCF A, IF=17.73, 人工智能与计算机视觉领域最顶级期刊]
- Jian-Fang Hu, Wei-Shi Zheng(*), Lianyang Ma, Gang Wang, Jianhuang Lai, and Jianguo Zhang. "Early Action Prediction by Soft Regression". IEEE Transaction on Pattern Analysis and Machine Intelligence (IEEE TPAMI), August 3, 2018; DOI: 10.1109/TPAMI.2018.2863279, [CCF A, IF=17.73, 人工智能与计算机视觉领域最顶级期刊]
- Jian-Fang Hu, Wei-Shi Zheng(*), Xiaohua Xie, and Jianhuang Lai, "Sparse Transfer for Facial Shape-from-Shading", Pattern Recognition (PR), 68(8): 272-285 (2017). [IF=3.965, CCF B类期刊论文]
- Jian-Fang Hu, Wei-Shi Zheng(*), Jianhuang Lai, Shaogang Gong, and Tao Xiang, "Exemplar-based Recognition of Human-Object Interactions", IEEE Transaction Circuits System Video Technology (TCSVT). 26(4): 647-660 (2016). [IF=3.599, CCF B类期刊论文]
- Jian-Fang Hu, Wei-Shi Zheng(*), Jiahui Pan, Jianhuang Lai, and Jianguo Zhang, "Deep Bilinear Learning for RGB-D Action Recognition", European Conference on Computer Vision (ECCV), 2018. [计算机视觉三大顶级会议之一]
- Jian-Fang Hu, Wei-Shi Zheng(*), Jianhuang Lai, and Jianguo Zhang, "Jointly Learning Heterogeneous Features for RGB-D Activity Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5344-5352 (2015). [CCF A，计算机视觉顶级会议]
- Jian-Fang Hu, Wei-Shi Zheng(*), Jianhuang Lai, Shaogang Gong, and Tao Xiang, "Recognising Human-Object Interaction via Exemplar based Modelling'', International Conference on Computer Vision (ICCV), 3144-3151 (2013). [CCF A，计算机视觉三大顶级会议之一]
- Jian-Fang Hu, Wei-Shi Zheng(*), Lianyang Ma, Gang Wang, and Jianhuang Lai, "Real-time RGB-D Activity Prediction by Soft Regression", European Conference on Computer Vision (ECCV), 280-296 (2016). [计算机视觉三大顶级会议之一]
