胡晰远

职称职务:教授,博士生导师

E-mail:huxiyuan@bjut.edu.cn

个人简介

胡晰远,男,2011年博士毕业于中国科学院自动化研究所,之后留所工作,历任助理研究员、副研究员(硕士生导师),期间于20122014年分别在台湾中央研究院和美国哈佛大学任访问学者。2024年入职北京工业大学计算机学院,任教授,博士生导师。

在深度生成模型、低质量图像和视频处理、信号自适应分解理论及应用等领域开展研究工作,出版专著两部(科学出版社,清华大学出版社),牵头/参与制订多项国家标准和公安行业标准。在Nature Communications, IJCVIEEE T-IIIEEE T-MMIEEE T-SPIEEE JBHI, Signal ProcessingCVPRACM MMICASSP等国际主流期刊和会议中发表论文100余篇,授权发明专利10余项,2020年获公安部科学技术奖一等奖,2019年获中国感光学会青年科技奖,2019年获中国计算机学会(CCF)科技进步优秀奖。


学术兼职

中国感光学会,理事

中国刑事科学技术协会,物证鉴定质量管理技术专业委员会,常务委员

International Journal of Intelligent NetworksAssociate Editor

International Conference on Data Science and Advanced Analytics (DSAA 2024,CCF-C)Special Session Program Chair


科研项目

1、北京市自然基金-顺义联合创新基金、基于粒度对齐和区域蒸馏的跨模态视觉注意力高效提升方法研究(L247034)、2024/11-2027/10、主持。

2、国家自然科学基金面上项目、融合多模态学习的视频中深度伪造人脸取证技术研究(62172227)、2022/01-2025/12、主持。

3、国家重点研发计划课题、基于大数据贝叶斯方法的伪造视频人像量化检验关键技术研究(2021YFF0602101)、2021/12-2024/11、主持。

4、国家自然科学基金面上项目、基于算子的鲁棒的信号自适应分解算法研究及其应用(61571438)、2016/01-2019/12、主持。

5、国家重点研发计划子课题、伪造图像分析检测与检验关键技术研究(2018YFC0807306-2)、2018/07-2021/06、主持。

6、国家自然科学基金青年基金、混沌信号的自适应分解算法研究及其应用(61201375)、2013/01-2015/12、主持。

7、国家高技术研究发展计划(863计划)课题、面向视频侦查的视频内容可辨识度实时增强技术研究(2013AA014602)、2013/01-2015/12、第二完成人(已获得公安部成果认定,本单位排名第一)。


代表性研究成果

[1] 《警用影像处理技术手册》,胡晰远,科学出版社,2017.

[2] 《小波与滤波器组设计:理论及其应用》,彭思龙、李保滨、胡晰远,清华大学出版社,2017.

[3] Yuan Wang, Chen Chen, Ning Zhang, Xiyuan Hu*. “WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection”, International Journal of Computer Vision, 2024. (中科院1区,CCF-A,IF:19.5)

[4] Lingzhen Kong, Kangkang Liu, Xiyuan Hu*, Ning Zhang, et. al., “Gender Classification Based on Spatio-Frequency Feature Fusion of OCT Fingerprint Images in the IoT Environment”, IEEE Internet of Things Journal, 2024.(中科院1区,IF:10.6)

[5] Xiangrui Li, Dongxu Wei, Xiyuan Hu*, Liming Zhang, et. al., “Statistical guaranteed noisy tensor recovery by fusing low-rankness on all orientations in frequency–original domains”, Information Fusion, vol.106:102262, pp.1-16, 2024.(中科院1区,IF:18.6)

[6] Yuan Wang, Kun Yu, Chen Chen*, Xiyuan Hu, Silong Peng. “Dynamic Graph Learning with Content-guided Spatial-Frequency Relation Reasoning for Deepfake Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.(CCF-A,计算机视觉顶会)

[7] Zhenfeng Fan, Xiyuan Hu*, Chen Chen, Silong Peng. “A Landmark-free Approach for Automatic , Dense and Robust Correspondence of 3D Faces”, Pattern Recognition, vol.133:108971, 2023. (中科院1区,CAA-A,IF:8.0)

[8] Qiwei Xie, Xiyuan Hu*, Lei Ren, Zhao Sun. “A Binocular Vision Application in IoT: Realtime Trustworthy Road Condition Detection System in Passable Area”, IEEE Transactions on Industrial Informatics, vol.19, pp.973-983, 2023. (中科院1区,CAA-A+,IF:12.3)

[9] Xiyuan Hu, Jingpeng Sun, Jingping Dong and Xuyun Zhang, "Auditory Receptive Field Net Based Automatic Snore Detection for Wearable Devices," IEEE Journal of Biomedical and Health Informatics, vol. 27(5): 2255-2263, 2023.(中科院1区,IF:7.7)

[10] Bin He, Yuxin Zhang, Lu Zhao, Zhenwen Sun, Xiyuan Hu, Yanrong Kang, Lei Wang, Zhihui Li, Wei Huang, Zhigang Li, Guidong Xing, Feng Hua, Chengming Wang, Ping Xue* & Ning Zhang*. “Robotic-OCT guided inspection and microsurgery of monolithic storage devices”. Nature Communications, vol. 14, 5701, 2023.(Nature子刊,IF:16.6)

[11] Zhihui Li, Yao Liu, Xiyuan Hu*, Guiqiang Wang. “A new uniform framework of source attribution in forensic science”. Nature: Humanit Soc Sci Commun, vol.9, 260, 2022. (Nature子刊,SCI&SSCI)

[12] Xiyuan Hu, Zhenfeng Fan, Xu Jia, et al., “Towards effective learning for face super-resolution with shape and pose perturbations”, Knowledge-based Systems, vol.220:106938, 2021.(中科院1区,CAA-A,IF:8.8)

[13]        Xiyuan Hu, Silong Peng, Baokui Guo, Pengcheng Xu, “Accurate AM-FM Signal Demodulation and Separation using Nonparametric Regularization Method”, Signal Processing, vol.186, pp.108131, 2021.(中科院2区,IF:4.4)

[14]        Hao Dou, Chen Chen, Xiyuan Hu*, et al., “PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution”, ACM Multimedia Conference (ACM MM), 2020.(CCF-A,多媒体顶会)

[15]        Zhenfeng Fan, Xiyuan Hu*, Silong Peng, Chen Chen, "Boosting Local Shape Matching for Dense 3D Face Correspondence", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.10936-10946, 2019. (CCF-A,计算机视觉顶会)

[16] Zhenfeng Fan, Xiyuan Hu*, Silong Peng, Chen Chen, "Dense Semantic and Topological Correspondence of 3D Face without Landmarks", European Conference on Computer Vision (ECCV), pp.541-558, 2018.(CCF-B,计算机视觉顶会)

[17] Xiyuan Hu, Silong Peng, Wen-Liang Hwang, "Adaptive Integral Operators for Signal Separation," IEEE Signal Processing Letters, vol.22(9):1383-1387, 2015. (中科院2区,IF:3.9)

[18] Xiyuan Hu, Silong Peng, Wen-Liang Hwang. "An integral operator based adaptive signal separation approach", International Conference on Acoustic, Speech and Signal Processing (ICASSP), 2013.(CCF-B,信号处理顶会)

[19] Xiyuan Hu, Silong Peng, Wen-Liang Hwang, "EMD Revisited: A New Understanding of the Envelope and Resolving the Mode-Mixing Problem in AM-FM Signals," IEEE Transactions on Signal Processing, vol.60(3):1075-1086, 2012.(中科院2区top,CAA-A,IF:5.4)

[20] Xiyuan Hu, Weiping Xia, Silong Peng and Wen-Liang Hwang, "Multiple component predictive coding framework of still images," IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2011. (CCF-B)



学校地址:北京市朝阳区平乐园100号
邮政编码:100124

  • 北京工业大学
    研究生招生

  • 北京工业大学
    研究生教育

Copyright © 北京工业大学研究生院版权所有