郑慧诚

所属研究所、院系: 
智能科学与技术研究所
职称: 
副教授
E-mail: 
zhenghch@mail.sysu.edu.cn
教师简介: 

郑慧诚,博士,博士后,副教授,博士生导师,IEEE 会员

Email: zhenghch@mail.sysu.edu.cn

 

研究领域: 

图像理解与计算机视觉,神经网络,机器学习等相关领域

 

 

 

教育背景: 

2001.12 - 2004.11:法国里尔一大博士生

 

工作经历: 

2016.1-至今, 中山大学, 数据科学与计算机学院, 副教授

2010.6-2015.12, 中山大学, 信息科学与技术学院, 副教授

2007.3-2010.6, 中山大学, 信息科学与技术学院, 讲师

2005.3-2006.9, France Telecom与Trinity College Dublin, 博士后, 合作导师: Christophe Laurent与Padraig Cunningham

海外经历: 

2005.03 - 2006.09:先后在法国、爱尔兰从事博士后研究,获欧洲信息学与数学研究联盟MUSCLE博士后奖学金。

第一阶段2005.03 - 2005.11:法国电信研发中心

第二阶段2006.01 - 2006.09:都柏林三一学院

2004.05 - 2004.06:美国约翰·霍普金斯大学访问学者

 

科研项目: 

目前已主持并完成一项国家自然科学基金面上项目,主持并完成教育部留学回国人员科研启动基金项目、教育部高等学校博士学科点专项科研新教师基金项目和广东高校优秀青年创新人才培育项目等,另作为高校方负责人参与并完成一项广东省及两项广州市科技计划项目。曾参与欧盟委员会项目MUSCLE NoE(No. FP6-507752)、法国国家科学研究中心项目Math-STIC 2004及由欧盟委员会提供部分资助的项目Internet Action Plan POESIA(IAP 2117/27572)。

 

教授课程: 

本科:信号与系统、概率论与数理统计、数字图像处理、计算机视觉、数值方法等

研究生:模式识别

 

代表性论著: 

期刊论文
[1] Huicheng Zheng, Zijian Lin, Jiepeng Cen, Zeyu Wu, and Yadan Zhao, “Cross-line pedestrian counting based on spatially-consistent two-stage local crowd density estimation and accumulation,” IEEE Transactions on Circuits and Systems for Video Technology, Early Access, DOI: 10.1109/TCSVT.2018.2807806
[2] Chengkun Zhang, Huicheng Zheng, and Jianhuang Lai, “Cross-view action recognition based on hierarchical view-shared dictionary learning,” [J] IEEE Access, pp. 1-13, Accepted, DOI: 10.1109/ACCESS.2018.2815611
[3] Jing Wang, Huicheng Zheng, Jiepeng Cen, and Jinyu Gao, “Cross-view action recognition based on a statistical translation framework,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 26, no. 8, pp. 1461-1475, Aug. 2016.
[4] Yunong Zhang, Bingguo Mu, Huicheng Zheng, “Link between and comparison and combination of Zhang neural network and quasi-Newton BFGS method for time-varying quadratic minimization,” IEEE Transactions on Cybernetics, vol. 43, no. 2, pp. 490-503, 2013
[5] Huicheng Zheng, Wei Shen, Qionghai Dai, Sanqing Hu, and Zheming Lu, “Learning nonlinear manifolds based on mixtures of localized linear manifolds under a self-organizing framework,” Neurocomputing, vol. 72, no. 13-15, pp. 3318-3330, 2009.
[6] Huicheng Zheng, Christophe Laurent, and Grégoire Lefebvre, “Fast-learning adaptive-subspace self-organizing map: An application to saliency-based invariant image feature construction,” IEEE Transactions on Neural Networks, vol. 19, no. 5, pp. 746-757, 2008.
[7] 郑慧诚, 沈伟, “一种局部化的线性流形自组织映射,” 自动化学报, vol. 34, no. 10, pp. 1298-1304, 2008.
[8] Huicheng Zheng, Pádraig Cunningham, and Alexey Tsymbal, “Learning multiple linear manifolds with self-organizing networks,” International Journal of Parallel, Emergent and Distributed Systems, vol. 22, no. 6, pp. 417-426, 2007.
[9] Bruno Jedynak, Huicheng Zheng, and Mohamed Daoudi, “Skin detection using pairwise models,” Image and Vision Computing, vol. 23, no. 13, pp. 1122-1130, 2005.
[10] Huicheng Zheng, Mohamed Daoudi, and Bruno Jedynak, “Blocking adult images based on statistical skin detection,” Electronic Letters on Computer Vision and Image Analysis, vol. 4, no. 2, pp. 1–14, 2004.

会议论文
[1] Jiayu Dong, Huicheng Zheng, and Lina Lian, “Activation-based weight significance criterion for pruning deep neural networks,” in Proc. International Conference on Image and Graphics, 2017, pp. 62-73.
[2] Jiajie Chen, Huicheng Zheng, Na He, Ziquan Luo, and Rui Zhu, “Object detection by learning oriented gradients,” in Proc. International Conference on Image and Graphics, 2017, pp. 86-96.
[3] Lvran Chen, Huicheng Zheng, Zijian Lin, Dajun Lin, and Bo Ke, “Adaptive patch quantization for histogram-based visual tracking,” in Proc. International Conference on Image and Graphics, 2017, pp. 38-50.
[4] Lina Lian, Huicheng Zheng, and Jiayu Dong, “Robust face recognition based on iterative sparse coding and pixel selection,” in Proc. IEEE International Conference on Image Processing, 2017, pp. 1782-1786.
[5] Zijian Lin, Huicheng Zheng, Bo Ke, and Lvran Chen, “Online multi-object tracking based on hierarchical association and sparse representation,” in Proc. IEEE International Conference on Image Processing, 2017, pp. 655-659.
[6] Shuai Yuan, Huicheng Zheng, and Dajun Lin, “Image classication based on discriminative dictionary pair learning,” in Proc. Chinese Conference on Biometric Recognition, 2015, pp. 176-185.
[7] Chengkun Zhang, Huicheng Zheng, and Jianhuang Lai, “Cross-view action recognition via dual-codebook and hierarchical transfer framework,” in Proc. Asian Conference on Computer Vision, 2014, pp. 579-592.
[8] Zhaoyu Lu, Ziqi Luo, Huicheng Zheng, Jikai Chen, and Weihong Li, “A Delaunay-based temporal coding model for micro-expression recognition,” in Proc. ACCV Workshops, 2014, pp. 698-711.
[9] Yuanchang Ou, Huicheng Zheng, Shuyue Chen, and Jiangtao Chen, “Vehicle logo recognition based on a weighted spatial pyramid framework,” in Proc. IEEE International Conference on Intelligent Transportation Systems, 2014, pp. 1238-1244.
[10] Dajun Lin, Huicheng Zheng, and Donghong Ma, “Robust visual tracking using local salient coding and PCA subspace modeling,” in Proc. IEEE International Workshop on Information Forensics and Security, 2013, pp. 25-30.
[11] Peipei Zhang, Huicheng Zheng, and Chun Yang, “Robust face recognition based on spatially-weighted sparse coding,” in Proc. Chinese Conference on Biometric Recognition, 2013, pp. 16-25.
[12] Dandan Xu and Huicheng Zheng, “Person re-identification by multi-resolution saliency-weighted color histograms and local structural sparse coding,” in Proc. International Conference on Image and Graphics, 2013, pp. 477-482.
[13] Zeyu Wu, Huicheng Zheng, and Jing Wang, “Pedestrian counting based on crowd density estimation and Lucas-Kanade optical flow,” in Proc. International Conference on Image and Graphics, 2013, pp. 471-476.
[14] Jing Wang and Huicheng Zheng, “Cross-view action recognition based on statistical machine translation,” in Proc. Chinese Conference on Biometric Recognition, 2012, pp. 260-267.
[15] Jing Wang and Huicheng Zheng, “View-robust action recognition based on temporal self-similarities and dynamic time warping,” in Proc. IEEE International Conference on Computer Science and Automation Engineering, 2012, pp. 498-502.
[16] Huicheng Zheng, “Mixture of subspace learning with adaptive dimensionality: A self-organizing approach,” in Proc. International Conference on Intelligent Systems and Knowledge Engineering, 2011, pp. 665-672.
[17] Shunbin Liu and Huicheng Zheng, “Motion analysis based on spatial-temporal visual attention,” in Proc. International Conference on Computational Intelligence and Security, 2010, pp. 253-257.
[18] Huicheng Zheng, “Invariant feature set generation with the linear manifold self-organizing map,” in Proc. Asian Conference on Computer Vision, 2010, pp. 677-689.
[19] Xiaohui Cai, Huicheng Zheng, and Bo Zhang, “Matching objects between multiple cameras based on wavelet salient features,” in Proc. International Conference on Information Engineering and Computer Science, 2009, pp. 1568-1571.
[20] Huicheng Zheng, Wei Shen, Qionghai Dai, and Sanqing Hu, “Locally linear online mapping for mining low-dimensional data manifolds,” in Proc. Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2008, pp. 830-838.
[21] Huicheng Zheng, Wei Shen, Qionghai Dai, and Sanqing Hu, “Modeling nonlinear manifolds with mixtures of localized principal subspaces under a self-organizing framework,” in Proc. IEEE International Conference on Networking, Sensing and Control, 2008, pp. 654-659.
[22] Huicheng Zheng, Pádraig Cunningham, and Alexey Tsymbal, “Adaptive offset subspace self-organizing map with an application to handwritten digit recognition,” in Proc. International Workshop on Multimedia Data Mining, in conjunction with ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2006, pp. 29–38.
[23] Huicheng Zheng, Christophe Laurent, and Grégoire Lefebvre, “On the basis updating rule of adaptive-subspace self-organizing map (ASSOM),” in Proc. International Conference on Artificial Neural Networks, 2006, pp. 435–444.
[24] Grégoire Lefebvre, Huicheng Zheng, and Christophe Laurent, “Objectionable image detection by ASSOM competition,” in Proc. International Conference on Image and Video Retrieval, 2006, pp. 201-210.
[25] Huicheng Zheng, Mohamed Daoudi, and Bruno Jedynak, “Graphical models for skin detection,” in Proc. International Workshop of the EU Network of Excellence Delos on Audio-Visual Content and Information Visualization in Digital Libraries, 2005, pp. 184-187.

发明专利
[1] 郑慧诚, 陈佳捷, 欧阳楚旭, 一种基于分段特征选择的虹膜识别方法, 中华人民共和国国家知识产权局, 申请号:201710567044 .6,申请日期:2017.7.12, 公开号:CN107358198A, 公开日期:2017.11.17.
[2] 郑慧诚,陈志宇,袁陶希, 一种基于特征点及邻域特征匹配的掌纹认证方法, 中华人民共和国国家知识产权局, 申请号:201710183736.0,申请日期:2017.3.24, 公开号:CN106951874A, 公开日期:2017.7.14.
[3] 郑慧诚,何娜,陈佳捷,罗子泉, 一种基于方向梯度特征学习的目标检测方法, 中华人民共和国国家知识产权局, 申请号:201710146530.0,申请日期:2017.3.13, 公开号:CN107145894A, 公开日期:2017.9.8.
[4] 郑慧诚,林大钧,林梓健,柯博, 一种结合时空拓扑估计的跨摄像机目标匹配与跟踪方法, 中华人民共和国国家知识产权局, 申请号:201710058711.8,申请日期:2017.1.23, 公开号:CN106846378A, 公开日期:2017.6.13.
[5] 郑慧诚,岑杰鹏,王敬, 一种基于动态时间规整与多核学习的视角无关动作识别方法, 中华人民共和国国家知识产权局, 申请号:201710032607.1,申请日期:2017.1.16, 公开号:CN106845386A, 公开日期:2017.6.13.
[6] 郑慧诚,连丽娜,董佳羽, 一种基于稀疏编码的人脸识别方法, 中华人民共和国国家知识产权局, 申请号:201710011190.0,申请日期:2017.1.6, 公开号:CN106845376A, 公开日期:2017.6.13.
[7] 郑慧诚,袁帅,何娜,陈至宇, 一种鲁棒的车牌、车标识别方法, 中华人民共和国国家知识产权局, 申请号:201611206923.8,申请日期:2016.12.23, 公开号:CN106650731A, 公开日期:2017.5.10.
[8] 郑慧诚, 林梓健, 马东宏, 一种单摄像头的行人跟踪方法, 中华人民共和国国家知识产权局, 申请号:201611004661.7,申请日期:2016.11.15, 公开号:CN106682573A, 公开日期:2017.5.24.
[9] 赵亚丹, 郑慧诚, 一种基于视频分析的人群计数方法, 中华人民共和国国家知识产权局, 申请号:201610080759.4,申请日期:2016.2.4, 公开号:CN105740945A, 公开日期:2016.7.6.
[10] 郑慧诚, 吴泽瑜, 一种基于视频分析的人群密度估计方法与人流量统计方法, 中华人民共和国国家知识产权局, 申请号: 201310136575.1,申请日期:2013.4.18, 公开号:CN103218816A, 公开日期:2013.7.24, 专利号:ZL 2013 1 0136575.1,授权公告日:2016.5.4.
[11] 郑慧诚, 李俊, 一种基于多摄像机信息融合的目标匹配与跟踪系统及方法, 中华人民共和国知识产权局, 申请号:201210048543.1, 申请日期:2012.2.28, 公开号:CN102629385A, 公开日期:2012.8.8, 专利号:ZL 2012 1 0048543.1,授权公告日:2014.9.24.
[12] 郑慧诚, 李茵茵, 赖剑煌, 一种人民币序列号识别方法, 中华人民共和国知识产权局, 申请号:201210237888.1, 申请日期:2012.7.10, 公开号:CN102800148A, 公开日期:2012.11.28, 专利号:ZL 2012 1 0237888.1,授权公告日:2014.3.26.

计算机软件著作权
[1] 软件名称:多目标跟踪系统, 登记号:2017SR029443, 证书号:软著登字第1614727号, 权力范围:全部权利, 日期:2017.2.4.
[2] 软件名称:基于单摄像头的多行人跟踪平台, 登记号:2017SR301793, 证书号:软著登字第1887077号, 权力范围:全部权利, 日期:2017.6.22.