发布日期:2024-05-03 浏览次数:次
更新日期:2024年3月29日 姓 名 曾德炉 性 别 男 出生年月 籍贯 廣東廣州 民 族 汉族 政治面貌 最后学历 博士研究生 最后学位 工学博士 技术职称 教授 导师类别 博、硕导 行政职务 Email DL+FamilyName(at)scut.edu.cn (Pls. delete'+') 工作单位 华南理工大学电子与信息学院 邮政编码 510640 通讯地址 广州天河区五山路381号 单位电话 020-87114008 个人主页 https://scut-dacim.github.io/ 个人简介 曾德炉,博士,教授,博士生导师/硕士生导师。擅长数学与信息等交叉理论及应用研究。曾在相关领域发表论文80+篇,包括如IEEE Trans. Neural Networks and Learning Systems, IEEE Trans. Image Processing, IEEE Geoscience and Remote Sensing Letters等著名会刊,, 及ICML,AAAI,IJCAI,ICCV,CVPR,ICASSP等机器学习与视频处理模式识别顶级会议。主持国家及省部级项目多项:包括国家自然科学基金项目3项,中国博士后基金项目等;参与国家及省部级项目多项等;主持横向项目多项。 学术义务工作:广东计算数学学会常务理事,ACM会员,CCF会员,IEEE会员,参与NSFC评审等;并参与多个国际期刊审稿,包括IEEE TIP,IEEE ITS,IEEE TNNLS,IEEE TII, IEEE TEI,IEEE TMM,IEEE SMCb,Neural Networks,Neurocomputing等。Google Scholar引用近4000次,300次以上4篇,1000次以上1篇。(1)博士招收方向 计算智能与机器学习,微分方程应用,图像目标分割与识别,场景分析。(2)硕士招收方向图像目标识别及场景分析,大数据分析,经济金融信息,人工智能和机器学习等一般领域的数学建模。更多信息请关注---1)课题组GitHub主页:https://scut-dacim.github.io/2)学院信息主页:3)Google Scholar主页:https://scholar.google.com/citations?hl=en&user=08RCdoIAAAAJ&view_op=list_works&sortby=pubdate 工作经历 重要相关学术工作经历如下:--> 2022.02–现在, 华南理工大学,电子与信息学院,教授;--> 2018.09–2021.1, 华南理工大学,数学学院信息与计算科学系,教授;--> 2019.11–2020.11, 加拿大滑铁卢大学IVC,访问学者;--> 2018.11–2019.11, 美国哥伦比亚大学数据科学学院DSI,访问学者;--> 2018.08–2018.09, 芬兰奥卢大学 CMVS,研究科学家(访问学者);--> 2017.07–2017.09, 美国哥伦比亚大学数据科学学院,访问学者;--> 2016.07–2018.08, 华南理工大学,数学学院信息与计算科学系,副教授;--> 2013.04–2016.07, 厦门大学,信息科学与技术学院,副教授;--> 2010.02–2013.03, 华南理工大学,电子与信息学院,博士后(2011.09获副高资格)。 教育经历 ->2005.09 - 2009.12, 华南理工大学,信号与信息处理,博士研究生 (研究方向为迭代学习理论,控制理论,信号与信息处理等);->2003.09 - 2005.07, 华南理工大学,应用数学,硕士研究生 (研究方向为非线性发展方程及应用);->2005.07-2005.09, 中山大学,全国数学暑期学习班, 非学历培训 (学习主题为偏微分方程与微分几何);->1999.09 - 2003.07, 华南理工大学,数学与应用数学,本科/学士; 获奖、荣誉称号 1) 2020 年度广东省科学技术奖科技进步奖二等奖,面向复杂场景的视频内容服务关键技术研发与产业化应用。2) 2020年Signal Processing 信号处理社区Best Paper (5年内最佳)。 社会、学会及学术兼职 IEEE 会员,CCF 会员,ACM 会员 研究领域 ->主要领域:(统计)机器学习,图像处理与模式识别,(大)数据理解与生成,微分方程应用,优化方法;->其他涉及领域:工程数学建模,人工智能与感知推理,最优化理论及应用,情感计算,通信/生物医学信息处理,物联网及软定义网络等。 科研项目 (主要科研项目如下,其他横向未列出。)1). 国家自然科学基金面上项目,基于PDE的鲁棒视觉显著性目标感知先验的图像分割(61571005)、2016/01-2019/12,主持。(备注:信息与数学领域交叉类项目)2). 国家自然科学基金青年项目,目标检测与提取变分模型的关键问题研究(61103121)、2012/01-2014/12,主持。3). 国家自然科学基金项目,目标分割中的视觉显著先验的同质性描述(61811530271),在研,主持。4). 中央高校基本科研业务费,基于统计先验和变分框架下的图像去雾霾方法研究,在研,主持,2018.09-2020.08。5). 广州市产业技术重大攻关计划现代产业技术专题项目,基于深度学习的企业大脑关键技术研发与产业化, 2017/09-2020/10, 60/400万,单位内主持(企业联合申报)。6). 广州市科技计划一般项目,图像去雨雾问题的大数据与深度架构逆问题建模, 2018/04-2021/03,主持。7). 厦门大学校长基金,结合贝叶斯框架的偏微分方程图像目标分割鲁棒性方法(20720150093),2015/01-2016/12,主持。8). 中国博士后基金,变分法图像分割有效实现的几个关键问题研究(20100470923)、2010/02-2012/02,主持。9). 国家自然科学基金青年项目,变结构向量场下活动轮廓模型的研究(61003170)、2011/01-2013/12,第一参与。 发表论文 ----------------------------------------------------------------------------------------------------------------------------------------------------*****<详细论文信息可查询Google Scholar:https://scholar.google.com/citations?hl=en&user=08RCdoIAAAAJ&view_op=list_works&sortby=pubdate>*****----------------------------------------------------------------------------------------------------------------------------------------------------[>43] 待更新。[43]Guo, Pengfei, Lang He, Shuangyin Liu, Delu Zeng, and Hantao Liu. "Underwater Image Quality Assessment: Subjective and Objective Methods." IEEE Transactions on Multimedia (2021).[42]Bo Pan, Jinxuan Tao, Xianyang Bao, Jie Xiao, Hongsheng Liu, Xiaotong Zhao, and Delu Zeng. "Quantitative study of starch swelling capacity during gelatinization with an efficient automatic segmentation methodology." Carbohydrate Polymers 255 (2021): 117372. [41]Delu Zeng, Minyu Liao, Mohammad Tavakolian, Yulan Guo, Bolei Zhou, Dewen Hu, Matti Pietikäinen, Li Liu. Deep Learning for Scene Classification: A Survey. arXiv preprint arXiv:2101.10531, 2021.[40]Pengfei Guo, Delu Zeng, Yunbo Tian, Shuangyin Liu, Hantao Liu, and Daoliang Li. "Multi-scale enhancement fusion for underwater sea cucumber images based on human visual system modelling." Computers and Electronics in Agriculture 175 (2020): 105608.[39] Qianl Ma, Sen Li, Wanqing Zhuang, Sen Li, Jiabing Wang and Delu Zeng*, "Self-Supervised Time Series Clustering With Model-Based Dynamics," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2020.3016291..[38] Xiangrui Xing, Xian Yu, Wenao Ma, Vue Huang, Delu Zeng, Xinghao Ding. Bindctnet: A Simple Binary Dct Network for Image Classification, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).[37]Yixuan He, Tianyi Hu, Delu Zeng*, Scan-flood Fill (SCAFF): an Efficient Automatic Precise Region Filling Algorithm for Complicated Regions,Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019.[36] Tao Zheng, Bo Li, Delu Zeng, Zhiheng Zhou, Delving into the Impact of Saliency Detector: A GeminiNet for Accurate Saliency Detection,International Conference on Artificial Neural Networks, 2019.[35]. Shulian Cai, Jiabin Huang,Jing Chen, Yue Huang, Xinghao Ding and Delu Zeng*, Prominent edge detection with deep metric expression and multi-scale features, Multimedia Tools and Applications 78 (20), 29121–29135,2019. [34]. Shulian Cai, Jiabin Huang, Delu Zeng*, Ding Xinghao, John Paisley.MEnet: A Metric Expression Network for Salient Object Segmentation, . International Joint Conference of Artificial Intelligence (IJCAI), 2018. [33]. WU Jiawen,LIU Qinting, Delu Zeng, Ding Xinghao, Li Lin. Speech Enhancement Based on Nonparametric Bayesian Method[J], Journal of Xiamen University(Natural Science), 2017,56(03):423-428. [32]. Yun Zhang, Juilee Thakara,David J. Topham, Ann R. Falsey,Delu Zeng and Xing Qiu*.Certain equivalence relationships of regularized regressions, Mathematics for Applications (Accepted). [31]. Xin He, Delu Zeng*.Real-time Pedestrian Warning System on Highway using Deep Learning Methods , ISPACS 2017 - 2017 International Symposium on Intelligent Signal Processing and Communication Systems, Nov. 6-9, 2017 (EI). [30]. Shulian Cai, Jiabin Huang, Xinghao Ding and Delu Zeng*.Semantic Edge Detection Based on Deep Metric Learning , ISPACS 2017 - 2017 International Symposium on Intelligent Signal Processing and Communication Systems, Nov. 6-9, 2017 (EI). [29]. Hong Tang, Delu Zeng*, Xin Liu, Jiabin Huang and Yinghao Liao.Resource Allocation and Optimization Based on Queuing Theory and BP Network , ICONIP 2017 - The 24th International Conference On Neural Information Processing, Nov. 14-18, 2017 (EI). [28]. Jinxuan Tao, Jiabin Huang, Long Yu, Zikang Li, Hongsheng Liu, Bo Yuan, Delu Zeng*. A new methodology combining microscopy observation with Artificial Neural Networks for the study of starch gelatinization ,Food Hydrocolloids (2017), doi: 10.1016/j.foodhyd. 2017.07.037, vol. 74, 2017, pp. 151-158. (JCR1) [27]. X. Fu, J. Huang, D. Zeng, Y. Huang, X. Ding, J. Paisley. "Removing rain from single images via a deep detail network ", IEEE Conference on Vision and Pattern Recognition (CVPR) , vol. x, pp. p1-p2, Honolulu, HI, USA., 2017. [26]. Lin Li, Jiawen Wu, Xinghao Ding, Qingyang Hong, Delu Zeng* . "Speech Enhancement Based on Nonparametric Factor Analysis ", ISCSLP 2016 - The 10th International Symposium on Chinese Spoken Language Processing , vol. 21, pp. p1-p2, 2016 (Accepted, EI). [25]. Xiaobo Shi, Yixue Hao, Delu Zeng*, Lu Wang, M. Shamim Hossain, Sk Md Mizanur Rahman, Abdulhameed Alelaiwi. "Cloud-Assisted Mood Fatigue Detection System", Mobile Networks and Applications, vol. 21, No. 5, pp. 744-752, 2016 (SCI, Doi:10.1007/s11036-016-0757-x). [24]. Delu Zeng, Yuwen Hu, Yue Huang, Zhiliang Xu, Xinghao Ding. "Pan-sharpening with structural consistency and l_1/2 gradient prior", Remote Sensing Letters, vol. 7, No. 12, pp. 1170-1179, 2016 (SCI, JCR3, Doi:10.1080/2150704X.2016.1222098). [23]. Xinghao Ding, Liqin Chen, Yue Huang, Delu Zeng*. "Single image rain and snow removal via guided L0 smoothing filter", Multimedia Tools and Applications, vol. 75, No. 5, pp. 2697-2712, 2016 (SCI, Doi: 10.1007/s11042-015-2657-7). [22]. Xueyang Fu, Delu Zeng, Yue Huang, Yinghao Liao, Xinghao Ding* and John Paisley. "A Fusion-based Enhancing Method for Weakly Illuminated Images", Signal Processing, vol. 129, pp. 82-96, 2016. [21]. Peixian Zhuang, Xueyang Fu,Yue Huang, Delu Zeng and Xinghao Ding. “A Novel Framework Method for Non-Blind Deconvolution Using Subspace Images Priors”, Signal Processing: Image Communication, vol. 46, pp. 17-28, 2016. (SCI, JCR3) [20]. Xueyang Fu, Delu Zeng, Yue Huang, Xiao-ping Zhang and Xinghao Ding. "A weighted variational model for simultaneous reflectance and illumination estimation”, 2016 IEEE Conference on Computer Vision and Pattern Recognition (IEEE CVPR 2016,LAS VEGAs, US), 2016.08. [19]. Tong Zhao, Lin Li, Xinghao Ding, Yue Huang, and Delu Zeng*. "Saliency detection with spaces of background-based distribution”, IEEE Signal Processing Letters, vol. 23, no. 5, pp.683–687, May 2016. [18]. Yiyong Jiang, Xinghao Ding, Delu Zeng, Yue Huang and John Paisley. "Pan-sharpening with a hyper-Laplacian penalty", International Conference on Computer Vision (IEEE ICCV 2015), Santiago, Chile, 2015. [17].Xueyang Fu, J. Wang, Delu Zeng, Yue Huang, Xinghao Ding. "Remote Sensing Image Enhancement using Regularized-Histogram Equalization and DCT", IEEE Geoscience and Remote Sensing Letters, 2015,12(11), 2301-2305. [16].Xueyang Fu, Yinghao Liao, Delu Zeng, Yue Huang, Xiao-ping Zhang and Xinghao Ding, "A Probabilistic Method for Image Enhancement with Simultaneous Illumination and Reflectance Estimation", IEEE Transactions on Image Processing , 2015,24(12), 4965-4977. [15]. Delu Zeng, Zhiheng Zhou, Shengli Xie. "Image Segmentation based on the Poincare Map Method", IEEE Transactions on Image Processing , 21(3):946-957,2012. [14]. Tong Zhao, Jiawen Wu, Lin Li, Delu Zeng*, Zhaoshui He. "Semi-supervised shape classification based on low rank constraint active contour", Mechatronics and Control (ICMC), 2014 International Conference on, Jinzhou, 2014, pp. 1069-1073.. [13].Delu Zeng, Zhiheng Zhou, et al. "Coarse-to-fine Boundary Location with a SOM-like Method", IEEE Transactions on Neural networks, 21(3):481-493, 2010. [12].Shengli Xie, Delu Zeng*, Zhiheng Zhou. "Arranging and Interpolating Sparse Unorganized Feature Points With Geodesic Circular Arc", IEEE Transactions on Image Processing, 18(3):582 - 595, March 2009. [11].Weijun Liu, Jianzhong Lin, Congbo Cai, Delu Zeng and Xinghao Ding. “Fast magnetic susceptibility reconstruction using L0 norm of gradient”, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), South Brisbane, QLD, 2015, pp. 907-911. [10].Yue Huang, Xin Chena, Jun Zhang, Delu Zeng , Dandan Zhang, Xinghao Ding. “Single-trial ERPs denoising via collaborative filtering on ERPs images”, Neurocomputing, Volume 174, Part B, 22 January 2016, Pages 858–865. [9].Peixian Zhuang, Yue Huang, Delu Zeng, Xinghao Ding. “Mixed noise removal based on a novel non-parametric Bayesian sparse outlier model”, Neurocomputing, Volume 174, Part B, 22 January 2016, Pages 858–865. [8].Xueyang Fu, Yue Huang,Delu Zeng, Xiao-Ping Zhang and Xinghao Ding. “A fusion-based enhancing approach for single sandstorm image”, IEEE International Workshop on Multimedia Signal Processing (IEEE MMSP), 2014. [Matlab_code] [7].Xueyang Fu, Delu Zeng, Yue Huang, Xinghao Ding and Xiao-Ping Zhang. “A variational framework for single low light image enhancement using bright channel prior”, IEEE Global Conference on Signal and Information Processing (IEEE GlobalSIP), 2013. [Matlab_code] [6].Xueyang Fu, Qin Lin, Wei Guo, Yue Huang, Delu Zeng and Xinghao Ding. “A novel Retinex algorithm based on alternating direction optimization”, Sixth International Symposium on Precision Mechanical Measurements. International Society for Optics and Photonics, 2013. [5].Delu Zeng, Zhiheng Zhou, Shengli Xie. "Vector bundle constraint for particle swarm optimization and its application to active contour modeling", Progress in Natural Science, 17(10): 1220-1225, 2007. [4].Delu Zeng, Zhiheng Zhou, Shengli Xie. "Construction of Compact RBF Network by Refining Coarse Clusters and Widths", Journal of Systems Engineering and Electronics, 20(6):1309-1315, 2009. [3].Delu Zeng, Shengli Xie, Zhiheng Zhou. "Improved clustering and anisotropic gradient descent algorithm for compact RBF network",13th International Conference on Neural Information Processing (ICONIP 06,HongKong), Lecture Notes in Computer Sciences, vol.4233, pp. 806-813. [2].Delu Zeng, Zhiheng Zhou, et al. "Fast blocking artifacts reduction algorithm based on contrast enhancement technique", International Conference on Communications, Circuits and Systems Proceedings (ICCSP), vol. I, pp. 497-499, 2006. [1].Zhiheng Zhou, Delu Zeng, et al. "RBF neural network and active circles based algorithm for contours extraction". Progress in Natural Science, 17(6), pp. 681-686, 2007. 科研创新 待整理.. 教学活动 教学活动(Courses):1) 优化方法(本科生选修)<正在开设>;2)大数据案例与实践(本科生选修)<正在开设>;3)机器智能与数据科学(研究生选修)<正在开设>;4)机器智能与大数据分析;5)深度架构逼近与变分推断(博士生选修);6)信息论与编码 (本科生必修)<正在开设>;7)统计学习与智能处理方法(本科生选修);8)最优化理论与应用(研究生选修);9)数值计算方法(研究生选修);10)工程数学与建模(本科生课必修,涵盖数学物理方程,复变函数,傅立叶分析);11)微积分(本科生公共课);12)医用高等数学(本科生公共课);13)数理金融(本科生专业选修课);14)计算机软件技术基础(本科生必修);15)数字图像处理(本科生与研究生必修通选课);16)国际数学建模(ACM/ICM)教练。 指导学生情况 一. 课题组在读研究生李嘉诚 (2022级博士)林芷琪(2023级博士)徐箭 (数学-2020级博士);李仕贵(数学-2021级博士);陈炜 (数学-2022级博士);陈 炜 (2021级硕士);温楚梅(2021级硕士);刘曼妮(2022级硕士);刘奕灿(2022级硕士);姜宇豪(2023级硕士);庞宇琪(2023级硕士);蔡建明(2023级硕士-协助指导)二. 已毕业研究生赵彤 (厦大,2013-2016年硕士, 就业单位:华为);吴佳雯(厦大,2014-2017年硕士,就业单位:厦大);胡宇雯(厦大,2014-2017年硕士,就业单位:华为);朱攀 (厦大,2014-2017年硕士, 就业单位:华为);黄佳斌(厦大,2015-2018年硕士,就业单位:今日头条);蔡淑莲(厦大,2015-2018年硕士,就业单位:中国建设银行<厦门>); 唐周 (华工,2016-2019年硕士,就业单位:湖北恩施市委组织部);贺鑫 (华工,2017-2020年硕士,就业单位,中国建设银行<武汉>);赵威 (华工,2020 Research Assistant, 2020.06-2021.02,密歇根大学博士);何奕萱 (华工,2019 Research Assistant, 牛津大学PHD);陈致宏(华工,2018级硕士);就业单位:悉尼科技大学);廖敏瑜(华工,2018级硕士,就业单位:东莞华为);林晨 (华工,2019-2022年硕士;就业单位:华为-武汉);郑铮(华工,2019-2023博士,就业单位:广东第二师范大学);赖瑞丽(华工,2020-2023硕士,就业单位:深圳Tplink);吁孟非(华工,2020-2023硕士,东莞华为)***完成协助指导过2名博士生:傅雪阳(中国科学与技术大学,副教授);庄培显(北京科技大学,讲师)。 我的团队 我们组“DACIM” (DAta and Computation Intelligence Modeling) 主要研究数据科学与计算智能建模相关方法及应用,包括机器学习,偏微分方程应用,贝叶斯理论,人工智能等方法及相关应用。 老话重说,“数学依然是自然科学的皇冠!” 现代数学甚至已经脱离自然科学,探讨得更加深远。但数学不是空中楼阁,高不可攀,我们可以从“点滴”做起,也可以看到她如何转化为生产力。 欢迎未来有志于做数学与工程对话的学生报考(硕士/博士)研究生!您的研究生阶段将涉及数学与工程交叉的各类问题,包括:(1)从工程学科中挖掘和研究各类已知或未知的数学理论问题;(2)把数学工具应用以解决各类实际工程问题。届时希望您在充分体会各类实际工程问题的有趣性(参照本组研究兴趣与方向),同时也希望您能感受支撑自然哲学中这伟大数学学科的魅力! 我们的招生方向为:1)博士招收方向 计算智能与机器学习,大数据处理,图像分割,图像/语音/文本处理,偏微分方程应用;2)硕士招收方向图像/语音/文本处理,多媒体信息处理,大数据分析,经济金融信息,人工智能等一般领域的数学建模。 Btw,已经毕业的学生均找到很好的就业单位,颇受用人单位青睐。在其他985高校研究生毕业生相比,均取得较高的薪酬,平均薪酬均在25万以上,其中有优秀硕士生取得了40万+的年薪。这一切离不开他们在校期间的努力!在校期间,你有机会接触最前沿的理论研究;也有机会参与有意义的具体应用项目;还有机会推荐到国际名校(如哥大,罗切斯特大学,及欧洲一些名校)交流学习。 只要你努力和优秀,总会有发光发热的机会。 老师希望你们一代比一代优秀! 欢迎大家报考!