计算机视觉、多模态理解与生成、视觉合成与安全、图像恢复和增强

每年招收硕士研究生一名，欢迎具有自驱力、致力于发表高水平文章、解决实际科研问题的同学联系。

081104-模式识别与智能系统
081203-计算机应用技术

模式识别，计算机视觉

2019-06   中国科学院大学   博士
2016-01   北京航空航天大学   硕士
2012-07   西安交通大学   学士

2021-04~现在, 中国科学院自动化研究所, 副研究员
2019-07~2021-04,中国科学院自动化研究所, 助理研究员

1. 北京图象图形学学会理事

2. 中国图象图形学学会视觉大数据专委会委员

3. IEEE T-BIOM期刊编委

4. NeurIPS、PRCV等学术会议领域主席

5. TPAMI、IJCV、TIP、NeurIPS、ICML、ICLR、CVPR、ICCV等期刊和会议审稿人

（1） 北京市科技新星, 省级, 2023
（2） 吴文俊人工智能科学技术奖技术发明奖, 一等奖, 其他, 2023
（3） 中国科学院青年创新促进会, , 院级, 2022
（4） 北京市科协青年人才托举工程, , 其他, 2020
（5） 北京市优秀毕业生, , 省级, 2019
（6） 中国科学院院长优秀奖, 院级, 2019
（7） ICME研讨会最佳学生论文奖, 其他, 2019

（ 1 ） 基于随机小波注意力的图像处理方法、装置、设备及介质, 发明专利, 2023, 第 2 作者, 专利号: CN202310215782.X

（ 2 ） 基于几何先验的鸟瞰图语义分割方法、装置、设备及介质, 发明专利, 2023, 第 2 作者, 专利号: CN202310041741.3

（ 3 ） 基于无源领域自适应的图像超分辨率方法及装置, 发明专利, 2022, 第 2 作者, 专利号: CN202211690099.3

（ 4 ） 基于递归Transformer的动态图像复原方法, 发明专利, 2023, 第 3 作者, 专利号: CN115631115A

（ 5 ） 图像处理方法、装置、电子设备及存储介质, 发明专利, 2022, 第 2 作者, 专利号: CN115062673A

（ 6 ） 一种视听伪造检测方法及装置, 发明专利, 2022, 第 2 作者, 专利号: CN114596609A

（ 7 ） 一种基于多线索的双流视频人脸伪造检测方法及系统, 发明专利, 2022, 第 2 作者, 专利号: CN114596608A

（ 8 ） 基于因果推断的高泛化人脸替换方法、装置和电子设备, 发明专利, 2021, 第 2 作者, 专利号: CN113627404A

（ 9 ） 人脸图像盲修复方法及系统, 发明专利, 2021, 第 2 作者, 专利号: CN113763268A

（ 10 ） 基于视觉语义信息的人脸伪造检测方法和装置, 发明专利, 2021, 第 2 作者, 专利号: CN113627233A

（ 11 ） 基于选择性机制注意力机制的雨图去雨方法、系统及设备, 发明授权, 2022, 第 2 作者, 专利号: CN112862875B

（ 12 ） 漫画风格图像转换模型的训练方法、图像生成方法及装置, 发明专利, 2021, 第 6 作者, 专利号: CN112232485A

（ 13 ） 一种基于注意力机制的图像补全方法及装置, 发明专利, 2021, 第 4 作者, 专利号: CN112184582A

（ 14 ） 一种注意力机制人体图像关键点姿态估计方法及系统, 发明专利, 2020, 第 2 作者, 专利号: CN112149563A

（ 15 ） 基于双向Ladder结构的人脸属性分类系统, 专利授权, 2019, 第 3 作者, 专利号: CN109886072A

近几年在人工智能领域国际权威期刊和会议发表论文共计60余篇，其中CCF-A类论文37篇，包含TPAMI 2篇、IJCV 6篇、NeurIPS 8篇、CVPR 8篇、ICCV 3篇；出版Springer专著1部。以第一作者和通讯作者身份发表TPAMI 1篇、IJCV 2篇、NeurIPS 5篇、CVPR 4篇、ICCV 1篇。

全部论文列表参考：谷歌学术

1. Junxian Duan, Yuang Ai, Jipeng Liu, Shenyuan Huang, Huaibo Huang, Jie Cao, Ran He. Test-time Forgery Detection with Spatial-Frequency Prompt Learning. International Journal of Computer Vision (IJCV). 2024. (IF: 19.5，CCF-A，人工智能领域顶级期刊)

2. Xiaoqiang Zhou, Chaoyou Fu, Huaibo Huang, Ran He. Dynamic Graph Memory Bank for Video Inpainting. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024. (IF: 8.4, CCF-B, 视频处理领域权威期刊)

3. Xiaoqiang Zhou, Huaibo Huang, Zilei Wang, Ran He. RISTRA: Recursive Image Super-resolution Transformer with Relativistic Assessment. IEEE Transactions on Multimedia (TMM), 2024. (IF: 7.3, CCF-B, 多媒体领域权威期刊)

4. Huaibo Huang, Mandi Luo, Ran He. Memory Uncertainty Learning for Real-World Single Image Deraining. Trans. Pattern Analysis and Machine Intelligence (TPAMI), 2023. (IF: 23.6，CCF-A，人工智能领域顶级期刊)

5. Chaoyou Fu, Xiang Wu, Yibo Hu, Huaibo Huang, Ran He. DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition. Trans. Pattern Analysis and Machine Intelligence (TPAMI), 2022. (IF: 23.6，CCF-A，人工智能领域顶级期刊)

6. Jianze Wei, Huaibo Huang, Yunlong Wang, Ran He, Zhenan Sun. Towards More Discriminative and Robust Iris Recognition by Learning Uncertain Factors. IEEE Transactions on Information Forensics & Security (TIFS), 2022. (IF: 6.8，CCF-A，信息安全领域顶级期刊)

7. Jianze Wei, Yunlong Wang, Huaibo Huang, Ran He, Zhenan Sun, Xingyu Gao. Contextual Measures for Iris Recognition. IEEE Transactions on Information Forensics & Security (TIFS), 2022. (IF: 6.8，CCF-A，信息安全领域顶级期刊)

8. Mandi Luo, Haoxue Wu, Huaibo Huang, Weizan He, Ran He. Memory-Modulated Transformer Network for Heterogeneous Face Recognition. IEEE Transactions on Information Forensics & Security (TIFS), 2022. (IF: 6.8，CCF-A，信息安全领域顶级期刊)

9. Aijing Yu, Haoxue Wu, Huaibo Huang, Zhen Lei, Ran He. LAMP-HQ: A Large-Scale Multi-Pose High-Quality Database for NIR-VIS Face Recognition. International Journal of Computer Vision (IJCV), 2021. (IF: 19.5，CCF-A，人工智能领域顶级期刊)

10. Huaibo Huang, Aijing Yu, Zhenhua Chai, Ran He, Tieniu Tan. Selective Wavelet Attention Learning for Single Image Deraining. International Journal of Computer Vision (IJCV), 2021. (IF: 19.5，CCF-A，人工智能领域顶级期刊)

11. Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Gengyun Jia, Zhenhua Chai, Xiaolin Wei.  Contrastive Attention Network with the Dense Field Estimation for Face Completion. Pattern Recognition (PR), 2021.  (IF: 8，CCF-B，模式识别领域权威期刊)

12. Yi Li#, Huaibo Huang#, Jie Cao, Ran He, Tieniu Tan. Disentangled Representation Learning of Makeup Portraits in the Wild. International Journal of Computer Vision (IJCV), 2020, 128: 2166–2184. (Co-first author)(IF: 19.5，CCF-A，人工智能领域顶级期刊）

13. Xin Zheng, Yanqing Guo, Huaibo Huang, Yi Li, Ran He. A Survey to Deep Facial Attribute Analysis. International Journal of Computer Vision (IJCV), 2020. (IF: 19.5，CCF-A，计算机视觉领域顶级期刊)

14. Xin Zheng, Huaibo Huang, Yanqing Guo, Ran He.  BLAN: Bi-directional Ladder Attentive Network for Facial Attribute Prediction. Pattern Recognition (PR), 2020. (IF: 8，CCF-B，模式识别领域权威期刊)

15. Huaibo Huang, Ran He, Zhenan Sun, Tieniu Tan. Wavelet Domain Generative Adversarial Network for Multi-scale Face Hallucination. International Journal of Computer Vision (IJCV), 127(6-7): 763-784, 2019. (IF: 19.5，CCF-A，人工智能领域顶级期刊)

1. ​Yuang Ai, Xiaoqiang Zhou, Huaibo Huang*, Xiaotian Han, Zhengyu Chen, Quanzeng You, Hongxia Yang. DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation. Neural Information Processing Systems (NeurIPS), 2024. （CCF-A，机器学习领域顶级会议）

2. Haogeng Liu, Quanzeng You, Xiaotian Han, Yongfei Liu, Huaibo Huang*, Ran He, Hongxia Yang. Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model.  Neural Information Processing Systems (NeurIPS), 2024. （CCF-A，机器学习领域顶级会议）

3. Hongbo Wang, Jin Liu, Xiaoqiang Zhou, Jie Cao, Huaibo Huang*, Ran He. Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation. Neural Information Processing Systems (NeurIPS), 2024. （CCF-A，机器学习领域顶级会议）

4. Jin Liu, Huaibo Huang*, Jie Cao, Ran He. ZePo: Zero-Shot Portrait Stylization with Faster Sampling. ACM International Conference on Multimedia (ACM MM). 2024. (CCF-A, 多媒体计算领域顶级会议)

5. Xuannan Liu, Pei Pei Li, Huaibo Huang, Zekun Li, Xing Cui, et al. FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs. ACM International Conference on Multimedia (ACM MM). 2024. (CCF-A, 多媒体计算领域顶级会议)

6. Xing Cui, Zekun Li, Peipei Li, Huaibo Huang, Xuannan Liu, Zhaofeng He. InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser. European Conference on Computer Vision (ECCV), 2024. (CCF-B, 计算机视觉领域顶级会议)

7. Tingkai Liu, Yunzhe Tao, Haogeng Liu, Qihang Fan, Ding Zhou, Huaibo Huang, Ran He, Hongxia Yang. DeVAn: Dense Video Annotation for Video-Language Models. Association for Computational Linguistics (ACL), 2024. (CCF-A，自然语言处理领域顶级会议)

8. Yuang Ai, Huaibo Huang*, Xiaoqiang Zhou, Jiexiang Wang, Ran He. Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration. Computer Vision and Pattern Recognition (CVPR), 2024. （Corresponding author） (CCF-A，计算机视觉领域顶级会议)

9. Yuang Ai, Xiaoqiang Zhou, Huaibo Huang*, Lei Zhang, Ran He. Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer. Computer Vision and Pattern Recognition (CVPR), 2024.（Corresponding author） (CCF-A，计算机视觉领域顶级会议)

10. Qihang Fan, Huaibo Huang, Mingrui Chen, Hongmin Liu, Ran He. RMT: Retentive Networks Meet Vision Transformers. Computer Vision and Pattern Recognition (CVPR), 2024. (CCF-A，计算机视觉领域顶级会议)

11. Zi Wang, Huaibo Huang, Aihua Zheng, Ran He. Heterogeneous Test-time Training for Multi-modal Person Re-identification. AAAI Conference on Artificial Intelligence (AAAI), 2024.（CCF-A，人工智能领域顶级会议）

12. Qihang Fan, Huaibo Huang, Xiaoqiang Zhou, Ran He. Lightweight Vision Transformer with Bidirectional Interaction. Neural Information Processing Systems (NeurIPS), 2023.（CCF-A，机器学习领域顶级会议）

13. Rui Wang, Pei Pei Li, Huaibo Huang, Chunshui Cao, Ran He, Zhaofeng He. Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification. Neural Information Processing Systems (NeurIPS), 2023.（CCF-A，机器学习领域顶级会议）

14. Xiaoqiang Zhou, Huaibo Huang, Zilei Wang, Jie Hu, Ran He, Tieniu Tan. MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition. International Conference on Computer Vision (ICCV), 2023. (CCF-A，计算机视觉领域顶级会议)

15. Peipei Li, Rui Wang, Huaibo Huang, Ran He, Zhaofeng He. Pluralistic Aging Diffusion Autoencoder. International Conference on Computer Vision (ICCV), 2023. (CCF-A，计算机视觉领域顶级会议)

16. Huaibo Huang, Xiaoqiang Zhou, Jie Cao, Ran He, Tieniu Tan. Vision Transformer with Super Token Sampling. Computer Vision and Pattern Recognition (CVPR), 2023. (CCF-A，计算机视觉领域顶级会议)

17. Huaibo Huang, Xiaoqiang Zhou, Ran He. Orthogonal Transformer: An Efficient Vision Transformer Backbone with Token Orthogonalization. Neural Information Processing Systems (NeurIPS), 2022. (CCF-A，机器学习领域顶级会议)

18. Gengyun Jia, Huaibo Huang, Chaoyou Fu, Ran He. Rethinking Image Cropping: Exploring Diverse Compositions from Global Views. Computer Vision and Pattern Recognition (CVPR), 2022. (CCF-A，计算机视觉领域顶级会议)

19. Xin Xie, Yi Li, Huaibo Huang, Haiyan Fu, Wanwan Wang, Yanqing Guo. Artistic Style Discovery With Independent Components. Computer Vision and Pattern Recognition (CVPR), 2022. (CCF-A，计算机视觉领域顶级会议)

20. Huaibo Huang, Aijing Yu, Ran He. Memory Oriented Transfer Learning for Semi-Supervised Image Deraining. Computer Vision and Pattern Recognition (CVPR), 2021. (CCF-A，计算机视觉领域顶级会议)

21. Gege Gao, Huaibo Huang, Chaoyou Fu, Zhaoyang Li, Ran He. Information Bottleneck Disentanglement for Identity Swapping. Computer Vision and Pattern Recognition (CVPR), 2021. (CCF-A，计算机视觉领域顶级会议)

22. Peipei Li#, Huaibo Huang#, Yibo Hu, Xiang Wu, Ran He, Zhenan Sun. Hierarchical Face Aging through Disentangled Latent Characteristics. European Conference on Computer Vision (ECCV), 2020. (Co-first author)(CCF-B, 计算机视觉领域顶级会议)

23. Jie Cao, Huaibo Huang, Yi Li, Jingtuo Liu, Ran He, Zhenan Sun. Informative Sample Mining Network for Multi-Domain Image-to-Image Translation. European Conference on Computer Vision (ECCV), 2020. (CCF-B, 计算机视觉领域顶级会议)

24. Hao Zhu, Huaibo Huang, Yi Li, Aihua Zheng, Ran He. Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning. International Joint Conference on Artificial Intelligence (IJCAI), 2020. (CCF-A，人工智能领域顶级会议)

25. Chaoyou Fu, Xiang Wu, Yibo Hu, Huaibo Huang, Ran He. Dual Variational Generation for Low-Shot Heterogeneous Face Recognition. Neural Information Processing Systems (NeurIPS), 2019.（CCF-A，机器学习领域顶级会议）

26. Weikuo Guo, Huaibo Huang, Xiangwei Kong, Ran He. Learning Disentangled Representation for Cross-Modal Retrieval with Deep Mutual Information Estimation. ACM International Conference on Multimedia (ACMMM), 2019.（CCF-A，人工智能领域顶级会议）

27. Xiang Wu, Huaibo Huang, Vishal Patel, Ran He, Zhenan Sun. Disentangled Variational Representation for Heterogeneous Face Recognition. AAAI Conference on Artificial Intelligence (AAAI), 2019.（CCF-A，人工智能领域顶级会议）

28. Rui Wang, Huaibo Huang, Xufeng Zhang, Jixin Ma, Aihua Zheng. A Novel Distance Learning for Elastic Cross Modal Audio-Visual Matching. Workshops: 2019 IEEE International Conference on Multimedia and Expo (ICMEW), 2019. (Best Student Paper) (CCF-B, 计算机图形学与多媒体领域权威会议)

29. Huaibo Huang, Zhihang Li, Ran He, Zhenan Sun, Tieniu Tan. IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis. Neural Information Processing Systems (NeurIPS), 2018: 52-63. (CCF-A，机器学习领域顶级会议)

30. Huaibo Huang, Ran He, Zhenan Sun, Tieniu Tan. Wavelet-SRNet: A Wavelet-based CNN for Multi-scale Face Super Resolution. International Conference on Computer Vision (ICCV), 2017: 1698-1706. (CCF-A，计算机视觉领域顶级会议)

Yi Li, Huaibo Huang, Ran He, Tieniu Tan. Heterogeneous Facial Analysis and Synthesis. Springer, 2020.

（ 1 ） 基于解耦表达的高保真人脸图像合成理论和方法研究, 负责人, 国家任务, 2021-01--2023-12
（ 2 ） 多媒体混合伪造生成模型的稳定性研究, 负责人, 国家任务, 2020-07--2023-06
（ 3 ） 中国科学院青年创新促进会, 负责人, 中国科学院计划, 2022-03--2025-12
（ 4 ） 人脸增强、旋转与Sketch转换技术, 负责人, 境内委托项目, 2018-12--2024-06
（ 5 ） 面向复杂场景的小样本视频自动生成研究, 负责人, 境内委托项目, 2021-09--2022-08
（ 6 ） 基于MindSpore的视觉内容智能合成与鉴别技术研究, 负责人, 境内委托项目, 2022-11--2023-11
（ 7 ） 北京市科技新星创新新星计划, 负责人, 地方任务, 2023-10--2026-10