葡京3522新地址

李建军 

教授

博士生导师

计算机科学与技术

深度学习,计算机视觉,视频编解码,多媒体,微电子技术与应用

Email
jianjun.li@hdu.edu.cn
Phone
19258150201
  • 李建军,博士,教授,博士生导师,人工智能与微电子技术专家,在包括人工智能、多源信息融合和信号处理与设计等方面成绩显著,特别是在国际视频标准、图形图像处理、生物特征识别与医学图像处理、计算机视觉智能分析检测与识别以及微电子以及传感器设计领域从事研究工作30余年。著有英文、中文专著各一部、在国内国际期刊上发表论文70余篇,发明专利20余项。

    先后工作于国内大型研究所(CETC)、加拿大国家听觉实验室(NCA)、美国三菱研究院(MERL)、瑞士洛桑理工(EPFL)、土耳其比尔肯特大学(Bilkent University)和安卡拉大学(Ankara University)等五个国家六个组织,归国前任安卡拉大学长聘助理教授。

    在国外工作期间,曾担任国际视频标准化MPEG-RVC专家组成员,解决了视频压缩转码过程中块匹配、帧映射、优化率控制的三个核心问题,先后提出三个提案被接受,并以研究员身份主要参与了欧盟FP-7 3DPhone项目的研发工作,归国前任安卡拉大学全职教授。解决了可重构编码中变长编码困扰多年的路径优化问题,并被国际标准化视频组织(MPEG)收录。提出基于GPU和CPU协同优化的高性能运算框架,并成功的运用在欧盟3DPHONE项目中。

    2011年回国,先后入选 “浙江省千人计划”创新人才浙江省政府特聘专家、浙江省“钱江学者”特聘教授、“浙江省3D产业关键技术重点科技创新团队”首席科学家。现任杭州电子科技大学计算机学院图形图像所所长。在学术和科研上,担任国际期刊编委、多个国际期刊的特约审稿人和多个国际会议的大会主席和特约嘉宾。

    2011年,同时入选中科院“百人计划”人才,兼职于中国科学院深圳先进技术研究院并担任广州先进院智能中心主任,先后培养了“珠江新星”创新人才一名,硕士多名,发表论文10余篇,授权专利10余项。由于在杭州电子科技大学工作任务繁重,两地距离较远,2016年后主要在杭州工作,与中科院先进技术研究院主要以合作方式进行工作。

    回国后,主持和参与了多项重大国际性和国内项目。包括主持国家自然科学基金、浙江省重点研发计划、国防基础科研计划、军委装发项目、中电科重点实验室开放课题、中科院科研合作以及其他横向科研项目10余项,总项目金额超过1000万元。在人工智能算法、传感器设计、机器视觉、云计算等方面有较强的科研基础。 项目内容涵盖人工智能、传感器、计算机视觉、立体视频实时处理、运动图像在不同标准下的压缩及转换、以及听觉能力的评估等多媒体领域的多个方面。

工程师         1990.09~2001.04    中国电子科技集团(CETC)             中国

助理研究员     2001.03~2002.04    GAO Research Inc                     Canada

讲师           2002.05~2003.04    BBT Science & Technology College     Canada

助理研究员     2003.05~2004.04    The University of Western Ontario    Canada

助理研究员     2005.05~2006.05    University of Windsor                Canada

项目研究开发   2006.06~2007.01    Mitsubishi Electronic Research Lab   U.S.A

标准研发     2007.01~2007.12  École Polytechnique Fédérale de Lausann  Switzerland

软件工程师     2008.01~2009.12    Ambrado Inc.  Dallas                 U.S.A

研究员         2010.01~2011.04    Bilkent University                   Turkey

助理教授       2011.05~2012.08    Ankara University                    Turkey

特聘教授       2012.09~2016.06    杭州电子科技大学                     中国

  • Image processing.
  • Microprocessor

  • Algorithm and language.
  • Programming

  • Innovation and Practice

  • Computer fundamentals.
  • Deep learning

  1. Books:
    • Jianjun Li, Guojun Dai, “Algorithms and Implementation of Advanced Video Coding Standards” LAP, LAMBERT Academic Publishing, Germany, 2011. (ISBN: 978-3844383386).
    • 李建军(Jianjun Li)、王希铭、潘勉等,“深度学习与TesnsorFlow实战”,人民邮电出版社, 3 (ISBN : 978-7-115-47884-9)

 

  1. Journals:
  • Jianjun Li*; Jialuo Fei; Shichao Cheng, Tang, Zheng, Hui, Guobao: TSG-Net: A Residual-based Informing Network for 3D Gaze Estimation, Multimed Tools Accepted.  https://doi.org/10.1007/s11042-021-10793-4.
  • Shichao Cheng, Bocheng Zhang, Jianjun Li*, Zheng Tang, Korhan Cengiz:

Appearance Based Gaze Estimation Using Eye Region Landmarks and Math Approach

Journal of Internet Technology, vol. 21, no. 6 , pp. 1717-1724, Nov. 2020.

IEEE Access 7: 142947-142962 (2019)

(SCI, IF=3.242)

IEEE Access 7: 150444-150452 (2019)

(SCI,IF=3.242)

IEEE Access 7: 167401-167408 (2019)

(SCI,IF=3.242).

  • Jianjun Li, Wang, Z. H. Wang, H. J. Li, C. C. Chang and H. Wang:

New Secret Sharing Scheme Based on Faster R-CNNs Image Retrieval. 

IEEE Access 6: 49348-49357 (2018)

(SCI,IF=3.242).

Fabrication of catalyst coated membrane with screen printing method in a proton exchange membrane fuel cell.

International Journal of Hydrogen Energy, Volume 40, Issue 13, 13 April 2015, Pages 4649–4658.

(SCIIF=3.584).

Multi-Instance Sketch to Image Synthesis With Progressive Generative Adversarial Networks. 

IEEE Access 7: 56683-56693 (2019).

(SCI, IF=3.242).

  • Jianjun Li, Wang C, Chen X, et al. :

A selective encryption scheme of CABAC based on video context in high efficiency video coding. Multimedia Tools and Appl (2018). Vol.77: 12837-12851.

(SCI, IF=2.101).

  • Jun Xin, Jianjun Li,Anthony Vetro, Shun-ichi Sekiguchi:

Motion Mapping and Mode Decision for MPEG-2 to H.264/AVC Transcoding.

Multimedia Tools and Appl.35(2): 203-223 (2007).

(SCI, IF=1.131).

  • Jianjun Li, E.A.Raheem:

Efficient Rate Control Schemes for H.264/AVC Intra Frame.

IEEE Transactions on Consumer Electronics, Vol. 56, No. 2, pp.1043-1048, May 2010.

(SCI, IF=2.083).

  • Jianjun Li, Juxian Wang, Chin-Chen Zhang, Zhuo Tang, Zhenxing Luo:

Multiple Task-driven Face Detection Based on Super-resolution Pyramid Network.

Journal of Internet Technology Volume 20, pp 1263-1272. (2019). No.4.  DOI: 10.3966/160792642019072004024.

(SCI, IF=0.715).

  • Jianjun Li, Kai Zheng, , Zhenxing Luo, Zhuo Tang, Ching-Chun Chang:

A Dual-branch CNN Structure for Deformable Object Detection.

Accepted by Journal of Internet Technology, 2020 .

(SCI,IF=0.715).

  • Li, Jianjun*; Peng, Kangjian; Chang, Chin-Chen:

An Efficient Object Detection Algorithm Based on Compressed Networks.

Symmetry 10, no. 7: 235 (2018).

(SCI, IF=2.143).

  • Jianjun Li,Jie Yu, Lanlan Xu, Xiaoyang Mao, Junfeng Hu:

A cascaded algorithm for image quality assessment and image denoising based on CNN for image security and authorization.

Security and Communication Networks 2018: 8176984:1-8176984:13 (2018) 

(SCI, IF=1.376).

  • Jianjun Li, Susu Fan, Zhihui Wang, Haojie Li and Chin-Chen Chang:

An Optimized CLBP Descriptor Based on a Scalable Block Size for Texture Classification.  

KSII Transactions on Internet and Information Systems, vol. 11, no. 1, pp. 288-301, 2017.   

(SCI, IF=0.611).

  • JianJun Li ; LanLan Xu ; ZhiHui Wang ; Chin-Chen Chang:

No-Reference Image Quality Assessment for Multiple Distortions Using Saliency Map Based on Dual-Convolutional Neural Networks.

Journal of Internet Technology, Vol.18, no.7, pp.1701 – 1710, Dec. 2017.

(SCI, IF=1.213).

  • Ya-Feng Di, Chin-Feng Lee, Zhi-Hui Wang, Chin-Chen Chang, Jianjun Li:

A Robust and Removable Watermarking Scheme Using Singular Value Decomposition.

TIIS 10(12): 5268-5285 (2016).

(SCI, IF=0.611).

  • Zhi-Hui Wang, Qian Mao, Chin-Chen Chang, Qiong Wu, Jianjun Li:

A Data Lossless Message Hiding Scheme without Extra Information.

Journal of Internet Technology, Vol. 15 No. 4, PP. 657-670, 7 2014.

(SCI, IF=1.015).

  • Xiaoling Wu,Hoon Heo ,Guangcong Liu,Bangwon Lee,Jianjun Li:

Touchware: a software-based technique for high-resolution multi-touch sensing devices.

Int. J. Ad Hoc and Ubiquitous Computing, Vol. 3, No. 11, 2013.

(SCI, IF=0.705).

Energy-Efficient Routing Algorithms Based on OVSF Code and Priority in Clustered Wireless Sensor Networks.

International Journal of Distributed Sensor Networks, Vol.2013,Article ID:620945,8 pages, 2013.

(SCI, IF=1.239).

  • Jianjun Li,A.Raheem:

Fast Implementation of H.264 4×4 Intra Prediction.  

IEICE Electronics Express, vol. 7, no. 5, pp. 332-338, Mar. 2010.

(SCI, IF=0.586).

  • Zhi-Hui Wang, Ya-Feng Di, Jianjun Li*, Chin-Chen Chang, Hui Liu:

Progressive secret image sharing scheme using meaningful shadows.

Security and Communication Networks, 9(17): 4075-4088 (2016).

(SCI, IF=1.376).

  • Shanqing Zhang, Jianjun Li*,Zhihui Wang, Kunlong Zhang:

A Texture Segmentation Model Driven by the Simplified Cauchy-Schwarz Divergence.

Journal of information science and engineering 31, 1185-1197 (2015).

(SCI, IF=0.468).

  • Li J J, Wu Y H, Lee C F, et al.:

Generalized PVO-K embedding technique for reversible data hiding.

International Journal of Network Security, 2018, 20(1):65-77.

(EI).

  • Qiong Wu, Chen Zhu,Jianjun Li*, Chin-Chen Chang, Zhi-Hui Wang:

A magic cube-based information hiding scheme of large payload.

  1. Inf. Sec. Appl. 26: 1-7 (2016).

(EI).

  • 付晓峰; 付晓鹃; ; 余正生, 李建军:

视频序列中基于多尺度时空局部方向角模式直方图映射的表情识别,

计算机辅助设计与图形学学报, 2015(6): 1060~1066。

(EI).

 

  1. Conferences:

(CCF A).

 

Discriminative Feature-oriented Gaussian Mixture Model for Fine-grained Image Recognition.

Accepted by IEEE Conference on Computer Vision and Pattern Recognition (CVPR2020).

(CCF A).

Graph-propagation based Correlation Learning for Weakly Supervised Fine-grained Image Classification. 

The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-2020).

(CCF A).

Weakly Supervised Fine-grained Image Classification via Correlation-guided Discriminative Learning. 

The 27th ACM International Conference on Multimedia (ACM Multimedia 2019): 1851-1860.

(CCF A).

Learning to Segment Unseen Category Objects using Gradient Gaussian Attention. 

ICME 2019: 1636-1641.

(CCF B).

An Efficient Algorithm of Facial Expression Recognition by TSG-RNN Network. 

MMM (2) 2020: 161-174.

(CCF C).

(CCF C).

Accurate Detection for Scene Texts with a Cascaded CNN Networks.

Multimedia Modelling 2018: 36-47.

(CCF C).

Parameter Selection for Denoising Algorithms Using NR-IQA with CNN

Multimedia Modelling 2018: 381-392.

(CCF C).

  • Zhihui Wang, Ai Chen, Jianjun Li*,Ye Yao, Zhongxuan Luo:

1D Barcode Region Detection Based on the Hough Transform and Support Vector Machine. International Conference on Multimedia Modeling , 2016, pp 79-90.

(CCF C).

  • Chuancai Li, Jiayi Xu, Jianjun Li, Xiaoyang Mao: Suggesting the Appropriate Number of Observers for Predicting Video Saliency with Eye-Tracking Data.

CGI 2018: Pages 233-237, DOI:10.1145/3208159.3208193.

(CCF C).

  • Jianjun Li, Kai Zheng, Zhenxing Luo, Zhuo Tang, Ching-chun Chang, Peiqi Tang:

A Dual-Branch CNN Structure for Deformable Object Detection. In: Yang CN., Peng SL., Jain L. (eds) Security with Intelligent Computing and Big-data Services.

SICBS 2018. Advances in Intelligent Systems and Computing, vol 895. Springer, Cham.

(EI).

  • Jianjun Li, Qiang Zhao, Xu Tan, Zhenxing Luo, Zhuo Tang:

Using deep convolutional net for robust 1D barcode detection.

the 2nd International Conference on Intelligent and Interactive Systems and Applications (IISA2017), June 17-18,2017, Beijing, China.

(EI).

  • Jianjun Li,Juxian Wang, Chin-Chen Zhang, Zhuo Tang, Zhenxing Luo:

Face Detection in a Complex Background Using Cascaded Conventional Networks.

2017 International Conference on Security with Intelligent Computing and Big-data Services. (SICBS 2017).

(EI).

  • Jianjun Li,Wu, N. Wang, Z.*, Du, J., Fu, X. and Chang, C. C.:

Enhancement of the Quality of Images Based on Multiple Threshold Segmentation and Adaptive Gamma Correction.

The Eleventh International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP 2015), pp. 93-96, 2015-09. Adelaide, Australia.

(EI).

  • Jianjun Li,Meng, L. Wang, Z.*, Du, J., Fu, X. and Chang, C. C.

A Modified IMM-CSRF Algorithm for Passive Tracking of Maneuvering Targets

The Eleventh International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP 2015), pp. 89-92, 2015-09. Adelaide, Australia.

(EI).

  • Chuancai Li, Jiayi Xu,Jianjun Li, Xiaoyang Mao:

Determining the Appropriate Number of Observers in EyeTracking Based Video Saliency Computation.

NICOGRAPH International 2018.

(EI).

  • Lee C F, Chang C C, Li J J, et al.:

A Survey of Reversible Data Hiding Schemes Based on Pixel Value Ordering.

Nicograph International. IEEE, 2016, pp:68-74.

(EI).

  1. 李建军,张恒,羊丹,骆振兴,宋朱刚: 一种基于LOGO匹配和OCR的元器件检测方法, 7
  2. 李建军,张恒,骆振兴,唐卓,宋朱刚: 一种基于运动背景下的动目标检测和跟踪方法,2
  3. 李建军,张恒,骆振兴,唐卓,宋朱刚:笛卡尔坐标系下基于转换瑞利滤波器的机动目标跟踪方法,3
  4. 李建军、王慰、钟乐;柔性力敏传感器”,授权时间:10. 专利号: ZL2012201177110.9。
  5. 李建军、崔杨、孟利娟、高志刚、张善卿、王佛荣;“一种便携式可编程多通道心理声学测听仪”,授权时间:2. 专利号:ZL201310498860.8。
  6. 李建军、薛鑫营、郭辉、虞杰、王智慧、李豪杰,“一种基于深度学习的图像分类方法”,申请号:Z0;
  7. 李平; 李黎; 李建军;“一种基于泛函映射的多模态图像分割方法;” 授权时间: 1.27. 专利号:ZL201510040592.4.
  • National Science Fund of China, “Research on Key Technologies of Deep Learning Network Optimization Based on Compression and Fusion”,2019–2022。
  • Search Fund of Military, China,“Research on Signal Intelligence Mining Technology Based on Deep Learning”,2017–2019。
  • NationalScience Fund of China, “Research on Cooperative Traffic Flow Grooming Control Method Based on Node Traffic Data Anomaly Detection” , 2017–2019。
  • The sub-project of the National Defense Basic Research Program: “Intelligent Analysis and Fault Diagnosis Technology Agreement of Data Link Test Data”,2019 –2020。
  • Province project, “3D multimedia virtual mission system”, 2014—2017.
  • Chinese Academy of Sciences project, “Key Technology Research of Computer Vision in Smart Home Application”,2015–2018。
  • Cooperation projectSkin Test System Development”,2016—2018。
  • Cooperation project,”Image automatic detection and recognition of terminal samples (PCB board and appearance)”, 2018–2019。