首页 >> 研究生培养 >> 硕导介绍 >> 正文

邓欣

作者:       发布: 2020-08-31      来源:

打印

邓欣 Xin Deng

      

副教授

       

博士

       

15210836016

新主楼F930

       

网络空间安全学院

       

 

电子信箱

cindydeng@buaa.edu.cn

       

 

个人主页

 

  学习经历

2009.09-2013.06    北京航空航天大学     电子信息工程                      学士

2013.09-2016.01    北京航空航天大学     电子与通信工程                  硕士

2016.08-2020.03    伦敦帝国理工学院     电子与电气工程                  博士

  工作经历

2020.04至今      北京航空航天大学网络空间安全学院,副教授

  研究领域

图像处理与机器视觉,可解释性神经网络,图像与视频内容安全

  开授课程

本科生课程《图像处理与信息隐藏技术》

  荣誉与奖励

2020年北航“卓越百人”计划副教授

2016年帝国理工-CSC联合奖学金获得者

  科研成果

长期致力于图像视频处理和可解释性神经网络方向的研究工作,取得了重要理论和技术突破。解决了高倍率图像复原过程中无法兼顾图像主观和客观质量的问题;同时针对现有神经网络可解释性差的问题,提出基于卷积稀疏表示的可解释性神经网络架构,在保证准确度的同时显著提高网络的可解释性和鲁棒性。近5年来在人工智能顶级期刊TPAMI、图像处理顶级期刊TIP、视频编码权威期刊TCSVT,计算机视觉领域顶级会议ICCVECCV等发表论文20余篇。谷歌学术引用400 余次,单篇最高引用94

发表的主要论文如下:

  字典学习和可解释性神经网络

[1] Xin Deng, and   Pier Luigi Dragotti, “ Deep Convolutional Neural Network for Multi-modal   image restoration and fusion”, IEEE Transactions on Pattern Analysis and   Machine Intelligence (TPAMI)2020. 期刊论文 (录用)SCI

[2] Xin Deng and   Pier Luigi Dragotti, “Deep Coupled ISTA Network for Multi-modal Image   Super-resolution”, IEEE Transactions on Image Processing (TIP), vol   29, pp 1683 –1698, 2019.  期刊论文 (已发表) SCI

[3] Xin Deng, and   Pier Luigi Dragotti, “Coupled ISTA Network for Multi-modal Image   Super-resolution”, IEEE International Conference on Acoustics, Speech and   Signal Processing (ICASSP), pp 1862-1866, 2019. 会议论文 (已发表)EI

[4] Xin Deng,   Junjie Huang, Mengying Liu, and Pier Luigi Dragotti, “An FRI-based Single   Image Super-Resolution Algorithm and an Application in Image Compression”,   IEEE International Conference on Acoustics, Speech and Signal Processing   (ICASSP), pp 1807-1811, 2018. 会议论文 (已发表)EI

 

  视频压缩和显著性模型

[5] Mai Xu, Tianyi   Li, Zulin Wang, Xin Deng, Ren Yang, “Reducing complexity of HEVC: A   deep learning approach”. IEEE Transactions on Image Processing TIP, 2018, 27(10):   5044-5059. 期刊论文 (已发表)SCI

[6] Tianyi Li, Mai   Xu, Xin Deng, Liquan Shen, “Accelerate CTU Partition to Real Time for HEVC Encoding   with Complexity Control”. IEEE Transactions on Image   Processing TIP, 2020, DOI10.1109/TIP.2020.3003730

[7] Mai   Xu, Xin Deng, Shengxi Li, and Zulin Wang, “Region-of-Interest Based   Conversational HEVC Coding with Hierarchical Perception Model of Face”   IEEE Journal of Selected Topics in Signal Processing (JSTSP) , vol 8,   pp 475-489, 2014. 期刊论文 (已发表)SCI

[8] Xin   Deng, Mai Xu, Lai Jiang, Xiaoyan Sun, and   Zulin Wang, “Subjective-driven Complexity Control Approach for HEVC”, IEEE   Transactions on Circuits and Systems for Video Technology (TCSVT), vol   26, pp 91-106, 2016. 期刊论文 (已发表)SCI

[9] Xin   Deng and Mai Xu, “Hierarchical Complexity   Control of HEVC for Live Video Encoding”, IEEE Access, vol 4, pp 7014-7027,   2016. 期刊论文 (已发表)SCI

[10] Shengxi   Li, Mai Xu, Xin Deng, and Zulin Wang, “Weight-based r-λ rate control   for perceptual HEVC coding on conversational videos,” Signal Processing:   Image Communication, vol 38, pp 127-140, 2015 期刊论文 (已发表)SCI

[11] Xin   Deng, and Mai Xu, “Complexity Control of   HEVC for Video Conferencing”, IEEE International Conference on Acoustics,   Speech and Signal Processing (ICASSP), pp 1552-1556, 2017 会议论文 (已发表)EI

[12] Xin   Deng, Mai Xu, Shengxi Li and Zulin Wang,   “Complexity Control of HEVC Based on Region-of-Interest Attention Model”Visual   Communications and Image Processing Conference (VCIP), pp 225-228, 2014 会议论文 (已发表)EI

 

  图像视频超分辨与质量提升

[13] Jianyi   Wang, Xin Deng, Mai Xu, Congyong Chen and Yuhang Song, Multi-level   Wavelet-based Generative Adversarial Network for Perceptual Quality   Enhancement of Compressed Video, IEEE European   Conference on Computer Vision (ECCV), 2020 会议论文 (已接收)EI

[14] Xin   Deng, Ren Yang, Mai Xu and Pier Luigi   Dragotti, “Wavelet Domain Style Transfer for an Effective   Perception-distortion Tradeoff in Single Image Super-resolution”, IEEE   International Conference on Computer Vision (ICCV) oral, pp   3076-3085, 2019  会议论文 (已发表)EI

[15] Xin   Deng, “Enhancing Image Quality via Style   Transfer for Single Image Super-Resolution”, IEEE Signal Processing Letters,   vol. 25, pp 571-575, 2018.  期刊论文 (已发表)SCI

[16] Pingfan Song,   Xin Deng (共同一作),    Joao F.C. Mota, Nikos Deligiannis, Pier Luigi Dragotti, and Miguel R.D.   Rodrigues,“Multimodal Image Super-resolution via Joint Sparse Representations   induced by Coupled Dictionaries”, IEEE Transactions on Computational Imaging   (TCI), vol 6pp   57-72, 2020.  期刊论文 (已发表)SCI

[17] Xin Deng,   Pingfan Song, Miguel R. D. Rodrigues and Pier Luigi Dragotti, “RADAR: Robust   Algorithm for Depth Image Super Resolution Based on FRI Theory and Multimodal   Dictionary Learning”, IEEE Transactions on Circuits and Systems for Video Technology   (TCSVT), 2019. 期刊论文 (录用)SCI

 

  学术及社会服务

IEEE会员, CCF会员,担任多个会议和期刊的审稿人,Journal   of Selected Topics in Signal Processing (JSTSP), IEEE Transactions on Image   Processing (TIP)IEEE Transactions on Circuits and   Systems for Video Technology (TCSVT), IEEE Internet of Things Journal, IEEE   Transctions on Industrial Electronics (TIE), IEEE Transactions on   Computational Imaging (TCI).