研究方向为多媒体信息智能化处理、人工智能安全等，近期工作涉及多媒体信息处理，深度伪造生成与鉴别。近年来作为课题负责人/核心骨干承担了国家发改委重大项目、科技部科技创新2030“新一代人工智能”重大项目、北京市科委研究项目等10余项，取得多项研究成果。在CVPR、AAAI、ICME等国际会议上发表论文20余篇，授权国家发明专利10余项。

   

083900-网络空间安全

多媒体信息智能化处理
人工智能安全

多媒体信息处理

1. Shaofei Huang, Zhenwei Shen, Zehao Huang, Zihan Ding, Jiao Dai, Jizhong Han, Naiyan Wang, Si Liu.  Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection. CVPR 2023.
2. Tianrui Hui, Zizheng Xun, Fengguang Peng, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Jiao Dai, Jizhong Han, Si Liu. Bridging Search Region Interaction with Template for RGB-T Tracking. CVPR 2023.
3. Hongchao Gao, Yujia Li, Jiao Dai, Xi Wang, Jizhong Han, Ruixuan Li. Multi-granularity Deep Local Representations for Irregular Scene Text Recognition.  Trans. Data Sci 2021.
4. Weibo Zhang, Fuqing Zhu, Jiao Dai, Songlin Hu, Jizhong Han, Tao Guo. SPL: Exploiting Unlabeled Data for Multi-label Image Classification. ICME 2019.

深度伪造生成与鉴别

1. Jin Liu, Xi Wang, Xiaomeng Fu, Yesheng Chai, Cai Yu, Jiao Dai, Jizhong Han. FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions. ICME 2023.
2. Cai Yu, Peng Chen, Jiao Dai, Xi Wang, Weibo Zhang, Jin Liu, Jizhong Han.Focus by Prior: Deepfake Detection Based on Prior-Attention. ICME 2022.
3. Jin Liu, Peng Chen, Tao Liang, Zhaoxing Li, Cai Yu, Shuqiao Zou, Jiao Dai, Jizhong Han. Li-Net: Large-Pose Identity-Preserving Face Reenactment Network. ICME 2021.
4. Peng Chen, Jin Liu, Tao Liang, Cai Yu, Shuqiao Zou, Jiao Dai, Jizhong Han. DLFMNet: End-to-End Detection and Localization of Face Manipulation Using Multi-Domain Features. ICME 2021.
5. Peng Chen, Jin Liu, Tao Liang, Guangzhi Zhou, Hongchao Gao, Jiao Dai, Jizhong Han. FSSPOTTER: Spotting Face-Swapped Video by Spatial and Temporal Clues. ICME 2020.