郑慧诚
副教授
联系邮箱： zhenghch@mail.sysu.edu.cn
教师简介:
jbo竞博电竞官方网站博士研究生导师。于法国里尔一大获博士学位，期间短期访问Johns Hopkins大学。曾获欧洲信息学与数学研究联盟（ERCIM）的MUSCLE Fellowship，在France Telecom和Trinity College Dublin进行博士后研究。研究成果发表在IEEE TIP、TNNLS、TCSVT、CVPR、AAAI、NeurIPS等重要期刊和会议上。主持两项国家自然科学基金面上项目、若干省市级科技计划项目与横向项目。发明专利“一种基于稀疏编码的人脸识别方法”为中大首个获实施的开放许可专利。曾指导学生获CCBR最佳学生论文奖。
作为项目负责人承担教育部产学合作协同育人项目“《信号与系统》课程虚拟仿真资源建设”、广东省精品资源共享课《信号与系统》等多项教学项目。从基础理论、实际应用、前沿拓展三个层次上建立具有计算机专业特色的《信号与系统》理论与实践教学体系，发表7篇教研论文。
研究领域:
图像理解与计算机视觉、人工神经网络、稀疏表示、机器学习及其在行为理解、视频描述、目标检测、人脸识别、表情识别等方面的应用。
欢迎对相关研究感兴趣，勇于创新、不惧挑战的本科生、博硕士研究生、博士后加入！
获奖及荣誉:
入选中国教师发展基金会“2022-2023年度高校计算机专业优秀教师奖励计划”
负责校级一流课程“信号与系统”
在CVPR 2020 ActivityNet Challenge中获Dense Event Captioning（密集事件描述）任务第2名（全文链接：https://arxiv.org/abs/2006.11693）
CCBR 2013最佳学生论文（本人为指导教师兼唯一通信作者）
科研项目:
近年主持的科研项目:
1. 国家自然科学基金面上项目，面向复杂场景的视频行为表达、识别与密集描述，2020.1-2023.12
2. 国家自然科学基金面上项目，基于分布摄像机的目标跟踪与行为分析若干关键问题研究，2012.1-2015.12
3. 广东省自然科学基金面上项目，面向复杂场景的鲁棒人脸表情识别若干关键问题研究，2023.1-2025.12
4. 广东省自然科学基金面上项目，面向复杂环境的目标特征表达与鲁棒检测方法研究，2019.10-2022.9
5. 广州市科技计划重点项目——民生科技攻关计划项目，基于无人机巡航视频水域河道异常场景检测识别与示范应用，2018.4-2020.3
6. 广东省科技计划项目——研发与产业化项目，密集人流智能统计系统，2013.12-2016.12（合作单位负责人）
7. 广州市科技计划重大项目——产业关键共性技术研究项目，面向金融服务的用户身份认证可信计算平台研发及产业化，2014.12-2016.11（合作单位负责人）
8. 广州市科技计划项目，面向智能网络视频监控的目标跟踪与行为分析关键技术研究，2014.1-2016.6
近年主持的教研项目:
1.《信号与系统》课程虚拟仿真资源建设，教育部产学合作协同育人项目，2021.3–2022.2
2. jbo竞博电竞官方网站本科教学质量工程类项目，面向拔尖创新人才培养的专业课程教改探索与实践——以“数字图像处理”为例，2020.3-2022.2
3. 广东省精品资源共享课，信号与系统，2013.8-2016.11
4. jbo竞博电竞官方网站教学改革研究项目，2+2 课程教改实践研究——以“信号与系统”为例，2011.9-2013.8
代表性论著:
[30] Jisheng Dang, Huicheng Zheng, Xiaohao Xu, Longguang Wang, Qingyong Hu, Yulan Guo, “Adaptive sparse memory networks for efficient and robust video object segmentation,” IEEE Transactions on Neural Networks and Learning Systems, early access, online Jan. 2024. https://doi.org/10.1109/TNNLS.2024.3357118
[29] Jisheng Dang, Huicheng Zheng, Xiaohao Xu, Yulan Guo, “Unified spatio-temporal dynamic routing for efficient video object segmentation,” IEEE Transactions on Intelligent Transportation Systems, early access, online Dec. 2023. https://doi.org/10.1109/TITS.2023.3341457
[28] Ge Yuan, Xiaodong Cun, Yong Zhang, Maomao Li, Chenyang Qi, Xintao Wang, Ying Shan, Huicheng Zheng, “Inserting anybody in diffusion models via celeb basis,” Neural Information Processing Systems, 2023, pp. 1-13.
[27] Jisheng Dang, Huicheng Zheng, Jinming Lai, Xu Yan, Yulan Guo, “Efficient and robust video object segmentation through isogenous memory sampling and frame relation mining,” IEEE Transactions on Image Processing, vol. 32, pp. 3924-3938, Jul. 2023.
[26] 陈殷齐, 郑慧诚, 严志伟, 林峻宇, “基于单应性扩散约束的二步网格优化视差图像对齐,” 自动化学报, early access, online Sep. 2022. https://doi.org/10.16383/j.aas.c210966
[25] Ge Yuan, Huicheng Zheng, Jiayu Dong, “MSML: Enhancing occlusion-robustness by multi-scale segmentation-based mask learning for face recognition,” in Proc. AAAI Conference on Artificial Intelligence, 2022, pp. 3197-3205. (Oral)
[24] Yinqi Chen, Huicheng Zheng, Yiyan Ma, Zhiwei Yan, “Image stitching based on angle-consistent warping”, Pattern Recognition, vol. 117, Article 107993, Sep. 2021.
[23] Lvran Chen, Huicheng Zheng, Zhiwei Yan, Ye Li, “Discriminative region mining for object detection,” IEEE Transactions on Multimedia, vol. 23, pp. 4297-4310, Nov. 2021.
[22] Teng Wang, Huicheng Zheng, Mingjing Yu, Qian Tian, Haifeng Hu, “Event-centric hierarchical representation for dense video captioning,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 5, pp. 1890-1900, May 2021. Code
[21] Huicheng Zheng, Dajun Lin, Lina Lian, Jiayu Dong, and Peipei Zhang, “Laplacian-Uniform mixture-driven iterative robust coding with applications to face recognition against dense errors,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 9, pp. 3620 – 3633, Sep. 2020. Appendices. Code
[20] Huicheng Zheng, Jiajie Chen, Lvran Chen, Ye Li, and Zhiwei Yan, “Feature enhancement for multi-scale object detection,” Neural Processing Letters, vol. 51, no. 2, pp. 1907-1919, Apr. 2020.
[19] Mingjing Yu, Huicheng Zheng, Zhifeng Peng, Jiayu Dong, Heran Du, “Facial expression recognition based on a multi-task global-local network,” Pattern Recognition Letters, vol. 131, pp. 166 – 171, Jan. 2020. Code
[18] Ye Li, Huicheng Zheng, Zhiwei Yan, and Lvran Chen, “Detail preservation and feature refinement for object detection,” Neurocomputing, vol. 359, pp. 209 – 218, Sep. 2019. Code
[17] Bo Ke, Huicheng Zheng, Lvran Chen, Zhiwei Yan, and Ye Li, “Multi-object tracking by joint detection and identification learning,” Neural Processing Letters, vol. 50, no. 1, pp. 283 – 296, Aug. 2019.
[16] 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, vol. 29, no. 3, pp. 787 – 799, Mar. 2019. Dataset: EBP
[15] Jiayu Dong, Huicheng Zheng, and Lina Lian, “Low-rank Laplacian-uniform mixed model for robust face recognition,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 11889-11898.
[14] Chengkun Zhang, Huicheng Zheng, and Jianhuang Lai, “Dual-codebook learning and hierarchical transfer for cross-view action recognition,” Journal of Electronic Imaging, vol. 27, no. 4, pp. 043044-1 – 043044-20, Jul./Aug. 2018.
[13] Jiayu Dong, Huicheng Zheng, and Lina Lian, “Dynamic facial expression recognition based on convolutional neural networks with dense connections,” in Proc. International Conference on Pattern Recognition, 2018, pp. 3433-3438.
[12] 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.
[11] 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.
[10] 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.
[8] 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.
[7] 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.
[6] 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.
[5] 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.
[4] 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.
[3] 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.
[2] Bruno Jedynak, Huicheng Zheng, and Mohamed Daoudi, “Skin detection using pairwise models,” Image and Vision Computing, vol. 23, no. 13, pp. 1122 – 1130, 2005.
[1] 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.
