黄晟

19/03/27 11:20:12 作者: 点击:[] [小] [中] [大]

1D4C4

黄晟

职称:副教授,博士生/硕士生导师

职务:大数据智能研究所副所长

研究方向:模式识别、机器学习、计算机视觉、智能工业检测

邮箱:huangsheng@cqu.edu.cn



简介-Bio

黄晟,大数据与软件学院副教授,主要从事少样本/零样本学习,深度生成学习、超图/图学习、子空间学习、多标签图像分类等研究,目前主持或参与国家自然科学基金、重庆自然科学基金面上项目、重庆市重点产业共性关键技术创新专项等国家和省部级项目等8项。近年来已经在CVPRAAAITIPTIFSTMITCSVT、软件学报等国内外权威刊物上发表论文40余篇,荣获2018年度ACM重庆分会学术新星奖。现为中国计算机学会-计算机视觉专委会委员、中国图像图形学会-视觉大数据专委会委员、中国图像图形学会-成像探测与感知专委会委员、中国人工智能学会-模式识别专委会委员、中国自动化学会-模式识别与机器智能专委会委员,担任CVPRICCVECCV、NeurIPS、AAAITPAMITIPArtificial Intelligence等数十个国外权威刊物的审稿人。

欢迎报考博士研究生、学术型硕士研究生、专业型硕士研究生、接收校内外相关专业推免研究生!


教育工作经历-Resume

2006.09-2010.06,重庆大学软件学院(现大数据与软件学院),获工学学士学位

2010.09-2015.06,重庆大学计算机学院,获工学博士学位

2012.11-2014.11,美国罗格斯大学计算机科学系,CSC公派博士生

2015.07-2017.08,重庆大学大数据与软件学院,讲师

2017.09-至今,重庆大学大数据与软件学院,副教授


动态-News

[2022/06] 三篇论文被CCF-A会议ACM MM长文录用

[2022/04] 一篇论文被CCF-A会议IJCAI长文录用(录用率~15%)

[2022/04] 被邀请担任PRCV2022 Area Chair

[2022/03] 被邀请为NeurIPS2022审稿人

[2022/03] 一篇论文被IEEE TCYB(JCR-Q1 CCF-B 影响因子19.118)录用

[2022/03] 一篇论文被PR(JCR-Q1 CCF-B)录用

[2022/03] 被邀请为ECCV2022审稿人

[2022/01] 被邀请为ICME2022审稿人

[2021/11] 一篇论文被IEEE TCSVT(JCR-Q1 CCF-B)录用

[2021/09] 获得重庆市自然科学基金面上项目资助

[2021/09] 获得国家自然科学基金面上项目资助

[2021/09] 被邀请为CVPR2022审稿人

[2021/08] 被邀请为AAAI2022审稿人

[2021/08] 被邀请为WACV2022审稿人

[2021/07] 一篇论文被CCF-A类会议ACM MM长文录用。


主要课题-Funds

[1]主持国家自然科学基金面上项目 《少样本学习特征生成与鲁棒性关键技术研究》(No. 62176030)

[2]主持国家自然科学基金青年项目《基于超图的大数据属性学习研究》 (No. 61602068)

[3]主持重庆市自然科学基金面上项目《文本描述协同的双向生成式少样本学习研究》

[4]主持重庆市科技计划项目基础科学与前沿技术研究专项一般项目 《高性能超图正则化属性学习算法研究》 (No. cstc2016jcyjA0458)

[5]主持中央高校基金学院科技专项与中央高校基金启动经费各一项 (No. 106112015CDJRC091101)

[6]主研国家自然科学基金面上项目《深度形状语义网络表示机理及其结构保留机制与判别性研究》排名第3

[7]主研国家自然科学基金青年基金《基于特征融合与字典选择的代表模式发现研究》排名第3

[8]主研国家自然科学基金面上项目《分数阶系统的脉冲混沌动力学及稳定性》排名第7

[9]主研重庆市科技计划项目重点产业共性关键技术创新专项主题专项项目《跨媒体智能计算关键技术及典型应用平台研发和示范》重庆大学部分680万排名第4

[10]主研重庆市科技计划项目基础科学与前沿技术研究专项一般项目《结构化稀疏的视觉数据浓缩方法研究》排名第3

[11]主研教育部高等学校博士学科点科研基金《基于多特征和多标记流形学习的人体年龄估计方法研究》排名第4


代表性论文-Selected Publications

[10] Wenhao Tang, Sheng Huang*, Xiaoxian Zhang, Luwen Huangfu. "PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification". ACM  International Conference on Multimedia (ACM MM) 2022,录用. (CCF-A)

[9] Sheng Huang*, Jingkai Lin, Luwen Huangfu, Yun Xin, Junlin Hu, Dianel Dajun Zeng. "Adaptively Weighted k-tuple Metric Network for Kinship Verification". IEEE Transactions on Cybernetics (TCYB) 2022,录用 . (JCR-1, CCF-B, 2022-IF=19.118)

[8] Jiazhi Xu, Sheng Huang*, Luwen Huangfu, Dianel Dajun Zeng, Bo Liu, "Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation". International Joint Conference on Artificial Intelligence (IJCAI) 2022,录用. (CCF-A, 录用率~15%)

[7] Fengtao Zhou, Sheng Huang*,  Bo Liu, Dan Yang. "Multi-label Image Classification via Category Prototype Compositional Learning". IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2021,录用 . (JCR-1, CCF-B)

[6] Yi Zhang, Sheng Huang*, Fengtao Zhou, "Generally Boosting Few-Shot Learning with HandCrafted Features". ACM  International Conference on Multimedia (ACM MM) 2021:3143-3152. (CCF-A)

[5] Wenhao Tang, Sheng Huang*,  Qiming Zhao, Ren Li, Luwen Huangfu. "An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection". IEEE Transactions on Intelligent Transportation Systems (TITS) 2021,录用 . (JCR-1, CCF-B)

[4] Fengtao Zhou, Sheng Huang*, and Yun Xin. "Deep semantic dictionary learning for multi-label image classification ."AAAI Conference on Artificial Intelligence (AAAI), 35(4), 2021:3572-3580. (CCF-A, 录用率~21%)

[3] Sheng Huang*, Yang Yu, Dan Yang, Ahmed Elgammal, and Dong Yang. "Collaborative Graph Embedding: A Simple Way to Generally Enhance Subspace Learning Algorithms." IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)26, no. 10 (2016): 1835-1845. (JCR-1CCF-B)

[2] Sheng Huang, Ahmed Elgammal, Jiwen Lu, and Dan Yang*. "Cross-speed gait recognition using speed-invariant gait templates and globality–locality preserving projections." IEEE Transactions on Information Forensics and Security (TIFS) (2015): 10(10), pp.2071-2083. (JCR-1CCF-A)

[1] Sheng Huang, Mohamed Elhoseiny, Ahmed Elgammal, and Dan Yang. "Learning hypergraph-regularized attribute predictors." IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 409-417. 2015. (CCF-A)


会议论文-Conference Papers

[20] Wenhao Tang, Sheng Huang*, Xiaoxian Zhang, Luwen Huangfu. "PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification". ACM  International Conference on Multimedia (ACM MM) 2022,录用. (CCF-A)

[19] Wei Zhang, Xiaohong Zhang*, Sheng Huang, Yuting Lu, Kun Wang. "PixelSeg: Pixel-by-Pixel Stochastic Semantic Segmentation for Ambiguous Medical Images". ACM  International Conference on Multimedia (ACM MM) 2022,录用. (CCF-A)

[18] Wei Zhang, Xiaohong Zhang*, Sheng Huang, Yuting Lu, Kun Wang. "A Probabilistic Model for Controlling Diversity and Accuracy of Ambiguous Medical Image Segmentation". ACM  International Conference on Multimedia (ACM MM) 2022,录用. (CCF-A)

[17] Jiazhi Xu, Sheng Huang*, Luwen Huangfu, Dianel Dajun Zeng, Bo Liu, "Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation". International Joint Conference on Artificial Intelligence (IJCAI) 2022,录用. (CCF-A, Acceptance ratio~=15%)

[16] Yi Zhang, Sheng Huang*, Fengtao Zhou, "Generally Boosting Few-Shot Learning with HandCrafted Features". ACM  International Conference on Multimedia (ACM MM) 2021:3143-3152. (CCF-A)

[15] Guixin Huang, Sheng Huang*, Luwen Huangfu, Dan Yang, "Weakly Supervised Patch Label Inference Network with Image Pyramid for Pavement Diseases Recognition in the Wild.", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021:7978-7982. (CCF-B)

[14] Wei Chen, Qiuli Wang, Sheng Huang, Xiaohong Zhang, Yucong Li, Chen Liu, "DFDM: A Deep Feature Decoupling Module For Lung Nodule Segmentation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021:1120-1124. (CCF-B)

[13] Zeyu Wang, Sheng Huang*, Zhongxin Liu, Meng Yan*, Xin Xia, Bei Wang Dan Yang"Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network." IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2021:458-469. (CCF-B, Acceptance ratio~=25%)

[12] Fengtao Zhou, Sheng Huang*, and Yun Xin. "Deep semantic dictionary learning for multi-label image classification ."AAAI Conference on Artificial Intelligence (AAAI), 35(4), 2021:3572-3580. (CCF-A, Acceptance ratio~=21%)

[11] Kun Wang, Xiaohong Zhang, Sheng Huang, Qiuli Wang, and Feiyu Chen. "CTF-Net: Retinal Vessel Segmentation via Deep Coarse-To-Fine Supervision Network." In IEEE 17thInternational Symposium on Biomedical Imaging(ISBI), 2020pp. 1237-1241.

[10] Xing, Yun, Sheng Huang*, Luwen Huangfu, Feiyu Chen, and Yongxin Ge. "Robust Bidirectional Generative Network For Generalized Zero-Shot Learning." In IEEE International Conference on Multimedia and Expo (ICME),2020, pp. 1-6.(CCF-B)

[9] Kun Wang, Xiaohong Zhang, Sheng Huang."KGZNet: Knowledge-Guided Deep Zoom Neural Networks for Thoracic Disease Classification". IEEE International Conference on Bioinformatics and Biomedicine(BIBM) 2019: 1396-1401(CCF-B)

[8] Xingpeng Zhang, Sheng Huang, Xiaohong Zhang*, Wei Wang, Qiuli Wang, Dan Yang, “Residual Inception: A New Module Combining Modified Residual With Inception To Improve Network Performance”IEEE International Conference on Image Processing(ICIP), 2018

[7] Cheng Peng, Yongxin Ge, Mingjian Hong, Sheng Huang, Dan Yang, "Robust face alignment with cascaded coarse-to-fine auto-encoder network".IEEE International Conference on Image Processing(ICIP) 2017: 1477-1481,

[6] Sheng Huang*, Mohamed Elhoseiny, Ahmed Elgammal, and Dan Yang. "Learning Hypergraph-Regularized Attribute Predictors." In IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 409-417, 2015. (CCF-A)

[5] Sheng Huang, Mingchen Gao, Dan Yang*, Xiaolei Huang, Ahmed Elgammal, and Xiaohong Zhang. "Unbalanced graph-based transduction on superpixels for automatic cervigram image segmentation." In IEEE International Symposium on Biomedical Imaging(ISBI), 2015. 1556-1559.Oral Presentation,

[4] Mohamed Elhoseiny, Sheng Huang, Ahmed Elgammal, "Weather Classification with deep Convolutional Neural Networks", IEEE International Conference on Image Processing(ICIP), 2015, In Press, Oral Presentation.

[3] Sheng Huang*, Ahmed Elgammal, Luwen Huangfu, Dan Yang, and Xiaohong Zhang. "Globality-locality preserving projections for biometric data dimensionality reduction." InIEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), pp. 15-20, 2014.

[2] Sheng Huang*, Mohamed Elhoseiny, Ahmed Elgammal, and Dan Yang. "Improving non-negative matrix factorization via ranking its bases." InIEEE International Conference on Image Processing (ICIP), pp. 5951-5955, 2014.

[1] Sheng Huang*,Dan Yang, Ahmed Elgammal. "Learning Speed Invariant Gait Template via Thin Plate Spline Kernel Manifold Fitting". British Machine Vision Conference (BMVC), 2013.

期刊论文-Journal Papers

[22] Sheng Huang*, Jingkai Lin, Luwen Huangfu, Yun Xin, Junlin Hu, Dianel Dajun Zeng. "Adaptively Weighted k-tuple Metric Network for Kinship Verification". IEEE Transactions on Cybernetics (TCYB) 2022,录用 . (JCR-1, CCF-B, 2022-IF=19.118)

[21] Kun Wang, Xiaohong Zhang*, Xiangbo Zhang, Yuting Lu, Sheng Huang, Dan Yang. "EANet: Iterative Edge Attention Network for Medical Image Segmentation". Pattern Recognition (PR) 127 (2022): 108636. (JCR-1, CCF-B)

[20] Fengtao Zhou, Sheng Huang*,  Bo Liu, Dan Yang. "Multi-label Image Classification via Category Prototype Compositional Learning". IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2021,录用 . (JCR-1, CCF-B)

[19]  Wenhao Tang, Sheng Huang*,  Qiming Zhao, Ren Li, Luwen Huangfu. "An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection". IEEE Transactions on Intelligent Transportation Systems (TITS) 2021,录用 . (JCR-1, CCF-B)

[18] Qiuli Wang, Xiaohong Zhang, Wei Zhang, Mingchen Gao, Sheng Huang, Jian Wang, Jiuquan Zhang, Dan Yang, Chen Liu."Realistic Lung Nodule Synthesis with Multi-Target Co-Guided Adversarial Mechanism". IEEE Transactions on Medical Imaging  (TMI2021, 录用 . (JCR-1, CCF-B)

[17] 黄晟*,杨万里,张译,张小洪,杨丹. 一种基于间接域适应特征生成的直推式零样本学习方法[J].软件学报. 2021已录用(CCF-A中文期刊)

[16] Xiaolei Qin, Yongxin Ge, Jinyuan Feng, Dan Yang, Feiyu Chen,Sheng Huang, Ling Xu."DTMMN: Deep transfer multi-metric network for RGB-D action recognition". Neurocomputing 406(2020): 127-134 . (JCR-1)

[15] Sheng Huang*, Lin Jingkai, and Luwen Huangfu. "Class-Prototype Discriminative Network for Generalized Zero-Shot Learning." IEEE Signal Processing Letters (SPL)27 (2020): 301-305. (JCR-2)

[14] Shizheng Zhang,Sheng Huang*, Zhifeng Zhang, Heng Wang, Junxia Ma, Pu Li. "Corner detection based on tangent-to-point distance accumulation technique". Multimedia Tools and Applications (MTA). 78(18): 25685-25706 (2019). (JCR-2)

[13] Zhou, Daoxiang, Dan Yang, Xiaohong Zhang, Sheng Huang, and Shu Feng. "Discriminative Probabilistic Latent Semantic Analysis with Application to Single Sample Face Recognition." Neural Processing Letters (NPL) (2019): 49(3): 1273-1298 . (JCR-2)

[12] Sheng Huang*, Hongxin Wang, Yongxin Ge, et al. "Improved hypergraph regularized Nonnegative Matrix Factorization with sparse representation".P attern Recognition Letters (PRL), 2018, 102: 8-14. (JCR-2)

[11] Dan Yang, Chenqiu Zhao, Xiaohong Zhang,Sheng Huang. "Background Modeling by Stability of Adaptive Features in Complex Scenes." IEEE Transactions on Image Processing(TIP), 2018, 27(3): 1112-1125. (JCR-1, CCF-A)

[10] Sheng Huang*, Ahmed Elgammal, and Dong Yang."On the effect of hyperedge weights on hypergraph learning. ",Image and Vision Computing (IVC), 2017, 57: 89-101. (JCR-1)

[9] Shizheng Zhang, Dan Yang,Sheng Huang, Xiaohong Zhang, Liyun Tu, Zemin Ren, "Robust corner detection using the eigenvector-based angle estimator. "Journal of Visual Communication and Image Representation (JVCIR) , 2017, 45: 181-193. (JCR-2)

[8] Sheng Huang*,Yang Yu, Dan Yang, Ahmed Elgammal, and Dong Yang."Collaborative Graph Embedding: A Simple Way to Generally Enhance Subspace Learning Algorithms.",IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016, 26(10): 1835-1845. ((JCR-1, CCF-B)

[7] Sheng Huang*, Dan Yang, Yongxin Ge, and Xiaohong Zhang. "Discriminant Hyper-Laplacian Projections and its scalable extension for dimensionality reduction." Neurocomputing 173 (2016): 145-153. (JCR-1)

[6] Yongxin Ge, Cheng Peng, Jianhong Ming,Sheng Huang, Dan Yang,”Joint Local Regressors Learning for Face Alignment”. Neurocomputing, 2016, 208:262-268. (JCR-1)

[5] Sheng Huang, Ahmed Elgammal, Jiwen Lu, and Dan Yang*. "Cross-Speed Gait Recognition Using Speed-Invariant Gait Templates and Globality–Locality Preserving Projections."IEEE Transactions on Information Forensics and Security (TIFS), 10, no. 10 (2015): 2071-2083. ((JCR-1, CCF-A)

[4] Sheng Huang*, Yu Yang, Dan Yang, Luwen Huangfu, and Xiaohong Zhang. "Class specific sparse representation for classification." Signal Processing 116 (2015): 38-42. (JCR-1)

[3] Sheng Huang*, Dan Yang, Ge Yongxin, and Xiaohong Zhang. "Combined supervised information with PCA via discriminative component selection." Information Processing Letters (IPL), 115, no. 11 (2015): 812-816. (JCR-4)

[2] Sheng Huang, Dan Yang*, Jia Zhou, and Xiaohong Zhang. "Graph regularized linear discriminant analysis and its generalization." Pattern Analysis and Applications (PAAA), 2015, 18(3):639-650. (JCR-3)

[1] Sheng Huang, Dan Yang*, Haopeng Zhang, Luwen Huangfu, and Xiaohong Zhang. "Shape primitive histogram: low-level face representation for face recognition." IET Biometrics3, no. 4 (2014): 325-334. (JCR-3)


毕业生-Alumni

2018级硕士生:

林静凯(SPL'2020):花旗银行;邢云(ICME'2020):加拿大University of Alberta攻博

2019级硕士生:

周锋涛(AAAI'2021, TCSVT'2021, 合作ACM MM'2021):香港科大攻博;杨万里(软件学报'2021):位图;王泽宇(SANER'2021):昌平区经济与信息化局;吕欢欢(在职硕士):重庆市高速公路集团。




学术兼职-Social Activities

ACM会员,

IEEE会员,

中国计算机学会(CCF)会员,

    中国计算机学会-计算机视觉专委会执行委员

    中国计算机学会-多媒体专委会执行委员

中国图象图形学会(CSIG)会员,

    中国图像图形学会-视觉大数据专委会执行委员

    中国图像图形学会-成像探测与感知专委会执行委员

中国自动化学会(CAA)会员,

    中国自动化学会-模式识别与机器智能专委会执行委员

中国人工智能学会(CAAI)会员

    中国人工智能学会-模式识别专委会执行委员



担任审稿人(IF means the 2018 reported impact factor of journal)

IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI,CCF-A,IF 8.329)

IEEE Transactions on Image Processing(TIP,CCF-A,IF 4.828)

IEEE Transactions on Neural Networks and Learning System (TNNLS,CCF-B,IF 6.108)

IEEE Transactions on Cybernetics(TYC,CCF-B,IF 7.384)

IEEE Transactions on Circuits and Systems for Video Technology(TCSVT,CCF-B,IF 3.599)

IEEE Transactions on Systems, Man and Cybernetics: Systems(IF 2.35)

IEEE Signal Processing Letters (SPL,CCF-C, IF 2.528)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR,CCF-A)

IEEE International Conference on Computer Vision(ICCV, CCF-A)

IEEE International Conference on Multimedia and Expo (ICME,CCF-B)

IEEE Winter Conference on Applications of Computer Vision (WACV)

Elsevier Artificial Intelligence (AI,CCF-A, IF 4.797)

Elsevier Pattern Recognition (PR,CCF-B,IF 4.582)

Elsevier Pattern Recognition Letters (PRL,CCF-C, IF 1.995)

Elsevier Image and Visual Computing (IVC,CCF-C, IF 2.671)

Elsevier Knowledge-based Systems (KBS,CCF-C, IF 4.529)

Elsevier Neurocomputing (CCF-C, IF 3.317)

Elsevier Signal Processing(CCF-C, IF 3.470)

Elsevier Journal of Visual Communication and Image Representation (CCF-C2.164)

Springer European Conference on Computer Vision (ECCV,CCF-B)

Springer Signal, Image and Video Processing (IF 1.102)

Springer Artificial IntelligenceReview (IF 2.267)

Springer BMC bioinformatics (IF 2.213)

IET Biometrics (IF 1.382)

IET Computer Vision (CCF-C IF 0.878 )

Taylors&Francis Journal of Experimental & Theoretical Artificial Intelligence (CCF-C IF 1.011)

International Conference on Learning Representation (ICLR)

Annual Conference on Neural Information Processing System (NeurIPS)

AAAI Conference on Arificial Intelligence(AAAI, CCF-A)

British Machine Vision Conference (BMVC, CCF-C)

上一条: 周魏

下一条: 雷晏