康文雄 Wenxiong Kang

教授/Professor

华南理工大学 自动化科学与工程学院

Image Processing and Pattern Recognition , Biometrics , Computer Vision , Machine learning

简介  ABOUT

动态   NEWS

学术   ACADEMIC

康文雄,博士,华南理工大学自动化科学与工程学院&未来技术学院教授,博导,智能科学与技术系副主任,广东省智能金融企业重点实验室副主任;华工-奔流电力人工智能联合实验室主任,华南理工大学生物特征识别与智能感知实验室(BIPLAB)负责人,曾挂职广东石油化工学院自动化学院院长(2018.12-2022.01)。目前为中国计算机学会(CCF)杰出会员,中国人工智能学会(CAAI)/中国图象图形学学会(CSIG)高级会员,IEEE/IAPR会员,中国人工智能学会模式识别专委会委员,中国人工智能学会智能交互专委会委员,自动化学会模式识别与机器智能专委会委员,自动化学会混合智能专业委员会,中国图象图形学学会视觉大数据专委会,中国人工智能学会教育工作委员会第二届委员会委员, 广州市天河区科协第七届委员会常务委员。2009.9-2010.6以及2016.11-2017.12分别作为研究人员和访问学者到瑞士苏黎世联邦高等工业大学和澳大利亚悉尼大学进行访问研究。目前主要研究兴趣:图像处理与模式识别 , 计算机视觉,自然语言处理 , 生物特征识别 , 深度学习。 

科研成果:近年来在多种IEEE 汇刊,Pattern Recognition,中国科学、自动化学报等国内外重要专业期刊以及AAAI,ECCV,ICCV,IJCB, ICASSP,ICPR等国内外人工智能,计算机视觉和生物特征识别的重要专业会议上发表及录用论文80多篇,其中JCR 一区期刊论文30篇,8篇论文获得最佳论文奖、杰出论文奖和优秀论文奖,主编书籍1本。申请国际发明专利6项,授权国际专利4项,申请国家发明专利和实用新型专利50多项,授权30余项,转让专利16项,获得软件著作权9项。受邀组织,主持和参加了多个本领域的国内外学术会议,并担任了IEEE T-PAMI,IEEE T-IP,IEEE T-IFS,Pattern Recognition计算机学报,自动化学报中英文版等国内外重要学术期刊的审稿人,以及ECCV,ICPR, IJCB, PRCV,ISBA,DICTA,ACMMM,中国控制会议和中国生物特征识别会议等国内外会议的领域主席,程序委员会委员,分会主持和审稿人,此外还担任国家、广东省、山东省以及厦门市的自然科学基金通讯评议专家和科技奖励评审专家等。

科研项目:近年来主持国家自然科学基金3项、广东省自然科学基金,广东省科技计划项目,广东省教育部产学研结合项目等省部级项目10余项,中央高校基本科研业务费自主选题项目4项,参与科技部重点研发计划、国家自然科学基金重点项目和广东省粤港关键领域重点突破项目等项目多项,研究内容包括:指静脉和掌静脉识别,手势估计和自由手势认证,在线签名识别,多生物特征识别和仿冒攻击检测,目标检测、视频分析和理解。 此外与海康威视、海信电子、广电运通、南方电网以及广东机场等十多家企事业单位开展了项目合作,研究内容包括:电力场景和民航机场中的智能视频分析,现场作业人员的智能检测,识别和跟踪文档图像分析与识别,3D手势估计和3D人体姿态估计,生物特征识别系统研发,嵌入式机器视觉应用,智能视觉传感器开发等。

本科教学:承担了本科生课程《图像处理与机器视觉》,《机器视觉与智能检测相关创新实践》,研究生课程《模式识别与机器视觉实践课》,《系统分析与集成》等;指导本科生参加各类专业竞赛,取得了包括国家级一等奖在内的多个奖项,包括第七届中国计算机学会服务计算学术会议软件服务创新大赛二等奖;泛珠三角大学生计算机作品赛总决赛金奖和最佳创新奖,第十一届全国大学生电子商务“创新、创意及创业”挑战赛国家一等奖和广东省特等奖;此外,近几年指导的本科毕业生中10余人获得校级“优秀本科毕业设计”。

研究生指导:目前指导博士后2名,在读博士生8名,硕士生10余名,指导的研究生多次获得国家/校长奖学金,广东省优秀研究生,以及华南理工大学优秀硕士学位论文。此外,在各类专业竞赛中,指导的研究生取得了包括国家级一等奖在内的多个奖项,如:第七届中国国际“互联网+”大学生创新创业大赛国赛铜奖,全国研究生智慧城市技术与创意设计大赛跨摄像头行人跟踪任务一等奖,中国研究生电子设计竞赛华南区一等奖,Interspeech2021 个性化语音唤醒挑战赛冠军,第六届和第八届广东省数字图像图形创作大赛一等奖。硕士研究生毕业后基本去往华为,百度,阿里,腾讯,京东,英伟达,字节跳动,海康威视,CVTE,网易等企业的研究院(或研究部门)从事计算机视觉,图像处理,模式识别,机器学习等方面的算法研究工作,以及留在本实验室,或是前往香港和国外攻读博士学位。   

目前每年的博士后,博士和硕士招生情况:
博士后:模式识别与智能系统 1-2名
博士生:模式识别与智能系统(学术型) 电子与信息 (工程型) 2-3名
硕士生:模式识别与智能系统(学术型)电子与信息(专业型) 4-6名   
联系邮箱:auwxkang@scut.edu.cn

   
近几年的主要论文 (*通讯作者)
    
主要期刊论文
2022年
[1] W.Tang, M. Shakeel,J Luo,H. Wan,W. Kang*, DDAD: Detachable Crowd Density Estimation Assisted Pedestrian Detection. IEEE Transactions on Intelligent Transportation Systems. (SCI IF=9.551,JCR Q1)Accept
[2] W.Tang, M. Shakeel,Z Chen,H. Wan,W. Kang*, Target-Category Agnostic Knowledge Distillation with Frequency Domain Supervision. IEEE Transactions on Industrial Informatics. (SCI IF=11.648,JCR Q1)Accept
[2] W. Song, W. Kang*, L.Wang, Z. Lin, M. Gan. Video Understanding Based Random Hand Gesture Authentication. IEEE Transactions on Biometrics, Behavior, and Identity Science. Accept.
[3] W.Yang, Z.Chen, J.Huang, W.Kang* . A Novel System and Experimental Study for 3D Finger Multi-Biometrics. IEEE Transactions on Biometrics, Behavior, and Identity Science. Accept
[4] F.Lian, J. Huang, J. Liu, G. Chen, J.Zhao, W. Kang*.  FedFV: A Personalized Federated Learning Framework for Finger Vein Authentication. Machine Intelligence Research. Accept
[5] J.Huang, W.Luo,W.Yang,  A. Zheng,F. Lian,  W. Kang*.  FVT: Finger Vein Transformer for Authentication. IEEE Transactions on Instrumentation and Measurement, 71, 1-13.(SCI IF=5.332,JCR Q1)Accept
[6] Nie, L., Chen, T., Wang, Z., Kang, W., & Lin, L.  Multi-label image recognition with attentive transformer-localizer module.Multimedia Tools and Applications, 81, 7917-7940.
[7] Gu, R., Wu, Q., Li, Y., Kang, W., Ng, W.W., & Wang, Z. Enhanced local and global learning for rotation-invariant point cloud representation. IEEE MultiMedia.Accept 
[8] Nie, L., Liu, L., Wu, Z., & Kang, W. Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark. Neurocomputing.Accept 
2021年
[1] Y. Zhang, X. Wang, M. Shakeel, H.  Wan, W. Kang*,  Learning Upper Patch Attention using Dual-branch training strategy for Masked Face Recognition, Pattern Recognition, Accept  (SCI IF=8.518,JCR Q1)
[2] J. Huang, M. Tu, W. Yang and W. Kang*, Joint Attention Network for Finger Vein Authentication.  IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-11, 2021, (SCI IF=5.332,JCR Q1).
[3] Z. Zhang, F. Zhong and W. Kang*, Study on Reflection-Based Imaging Finger Vein Recognition, IEEE Transactions on Information Forensics and Security, (SCI IF=7.231,JCR Q1) doi: 10.1109/TIFS.2021.3093791.
[4] W. Jia, W. Xia, B. Zhang, Y. Zhao, L. Fei, W. Kang, D. Huang, G. Guo, A survey on dorsal hand vein biometrics,Pattern Recognition 120, 108122 (SCI IF=8.518,JCR Q1)
[5] H. Xu, L. Wang, Q. Wu, W. Kang*. PVLNet: Parameterized-View-Learning neural network for 3D shape recognition. Computers & Graphics. 98: 71-81 (2021)
[6] H. Xu, W. Yang, Q. Wu, W. Kang*,Endowing Rotation Invariance for 3D Finger Shape and Vein Verification,Frontiers of Computer Science, Accept (SCI )
[7]J.Xu, H. Tian , Z. Wang, Y. Wang, W. Kang, F.Chen,Joint Input and Output Space Learning for Multi-Label Image Classification.  IEEE Transactions on Multimedia. 23: 1696-1707 (2021) (SCI IF=8.182,JCR Q1) 
[8] C. Liu , Y. Yang, X. Liu, L. Fang, and W. Kang*, Dynamic Hand Gesture Authentication Dataset and Benchmark, IEEE Transactions on Information Forensics and Security, 2021(16): 1550-1562. (SCI IF=7.231,JCR Q1)
2014年-2020年
[1] W. Yang, W. Luo, W. Kang*, Z. Huang and Q. Wu, FVRAS-Net: An Embedded Finger-Vein Recognition and AntiSpoofing System Using a Unified CNN. IEEE Transactions on Instrumentation & Measurement, 2020(69)11: 8690-8701.
[2] G. Chen, G. Pan, Y. Zhou, W. Kang*, J. Hou, F. Deng, Correlation Filter Tracking via Distractor-aware Learning and Multi-Anchor Detection, IEEE Transactions on Circuits and Systems for Video Technology,2020(30)12: 4810-4822 (SCI IF=5.859,JCR Q1)
[3] W. Kang*, H. Liu, W. Luo, F. Deng, Study of a Full-View 3D Finger Vein Verification Technique, IEEE Transactions on Information Forensics and Security, (2020)15(1): 1175-1189  广东省计算机学会优秀论文一等奖
[4] L. Fang, N. Liang, W. Kang*, Z. Wang, D. Feng, Real-time hand posture recognition using hand geometric features and Fisher Vector, Signal Processing: Image Communication, 2020.(82):115729, (SCI IF=3.453. JCR Q2)
[5] W. Kang*, Yuting Lu, Dejian Li, Wei Jia, From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition, IEEE Transactions on Information Forensics & Security, (2019)14(4): 858-869.
[6] S. Tang, S. Zhou, W.Kang*,Q.Wu, F.Deng, Finger Vein Verification using a Siamese Convolutional Neural Network, IET Biometrics, Mar (2019) :1-12 (SCI IF=1.836,JCR Q2)
[7] G. Pan, G. Chen, W. Kang*, and J. Hou, Correlation filter tracker with siamese: A robust and real-time object tracking framework, Neurocomputing, 2019.358: 33–43 (SCI IF=5.779,JCR Q1).
[8] X. Qiu, W. Kang*, S. Tian, W.Jia and Z. Huang, Finger Vein Presentation Attack Detection Using Total Variation Decomposition, IEEE Transactions on Information Forensics & Security, (2018)13(2):465-477.
[0] L. Tang, W. Kang*, Y. Fang, Information Divergence-based Matching Strategy for Online Signature Verification, IEEE Transactions on Information Forensics & Security, 2018.13(4): 861-873.
[10] N. Liang, G.Wu, W. Kang*, Z. Wang, David D. Feng,Real-Time Long-Term Tracking With Prediction-Detection-Correction, IEEE Transactions on Multimedia, 2018.(99):1-12,
[11] L. Fang, G. Wu, W. Kang*, Q. Wu , Z. Wang, David D. Feng,Feature Covariance Matrix based Dynamic Hand Gesture Recognition, Neural Computing and Applications. Sep (2018) :1-14 (SCI IF=4.215,JCR Q1)
[12] Y.Fang, W. Kang*, Q.Wu, A novel finger vein verification system based on two-stream convolutional network learning, Neurocomputing, 2018.290: 100-107,
[13] 王浩, 康文雄*, 陈晓鹏. 基于视频的掌纹掌脉联合识别系统研究, 光学学报. 2018,38(2):0215004. (EI 核心),被评为2018年第2期“优秀论文”
[14] Y.Fang, W. Kang*, Q. Wu and L. Tang,A Novel Video-based System for In-air Signature Verification, Computers & Electrical Engineering, 2017. 57: 1–14, (SCI IF=1.747,JCR Q2).
[15] G.Wu, W. Kang*,Vision-Based Fingertip Tracking Utilizing Curvature Points Clustering and Hash Model Representation, IEEE Transactions on Multimedia,2017.19(8): 1730-1741,
[16] R.Shi, G.Wu, W. Kang*, Z. Wang, David D. Feng,Visual Tracking Utilizing Robust Complementary Learner and Adaptive Refiner,Neurocomputing,2017. 260: 367-377.
[17] G.Wu, W.Kang*, Exploiting Superpixel and Hybrid Hash for Kernel-Based Visual Tracking, Pattern Recognition,2017. 68: 175-190
[18] X. Zhuang, W. Kang*, Q. Wu, Real-time Vehicle Detection with Foreground-based Cascade Classifier, IET Image Processing, 2016.10 (4):289-296, (SCI IF=1.401,JCR Q3).
[19] G.Wu, W. Kang*, Robust Fingertip Detection in a Complex Environment, IEEE Transactions on Multimedia, 2016.18(6): 978-987
[20] W. Kang*, X. Chen, Fast Representation Based on a Double Orientation Histogram for Local Image Descriptors, IEEE Transactions on Image Processing,2015;24 (10):2915-2927, (SCI IF=5.072,JCR Q1).
[21] W.Kang, X.Chen, and Q. Wu, The biometric recognition on contactless multi-spectrum finger images. Infrared Physics & Technology, 2015. 68(10): 19-27. (SCI IF=1.851,JCR Q2).
[22] X. Yan, W. Kang*, F. Deng, and Q. Wu, Palm vein recognition based on multi-sampling and feature-level fusion. Neurocomputing, 2015. 151, Part 2(0): 798-807.
[23] Z. Huang, W. Kang*, Q. Wu, and X. Chen, A new descriptor resistant to affine transformation and monotonic intensity change. Computer Vision and Image Understanding, 2014. 120(0): 117-125. (SCI IF=2.391,JCR Q2).
[24] W. Kang*, and Q.Wu, Contactless Palm Vein Recognition Using a Mutual Foreground-Based Local Binary Pattern. IEEE Transactions on Information Forensics and Security, 2014. 9(11): 1974-85,(SCI IF=5.824,JCR Q1)
[25] W. Kang*, and Q. Wu, Pose-Invariant Hand Shape Recognition Based on Finger Geometry. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2014. 44(11): 1510-21 .   
 
主要会议论文
[1] A.Deng, S.Wang, W.Kang, F.Deng, On the Importance of Different Frequency Bin for Speaker Verification, ICASSP 2022, Accept
[1] H.Xu, Z.Zhou, Y.Wang, W.Kang, B. Sun, H.Li, Y. Qiao, Digging into Uncertainty in Self-supervised Multi-view Stereo, ICCV 2021, Accept
[2] W.Song, W.Kang*, Y.Yang, L.Fang, C.Liu, X,Liu, TDS-Net: Towards Fast Dynamic Random Hand Gesture Authentication via Temporal Difference Symbiotic Neural Network,IJCB 2021, Accept as best paper(最佳论文奖)
[3] W.Yang, Z.Chen, J.Huang, L.Wang, W.Kang*, LFMB-3DFB: A Large-scale Finger Multi-Biometric Database and Benchmark for 3D Finger Biometrics,IJCB 2021, Accept as best paper(最佳论文奖)
[4] C.Luo, W.Kang*, J.Zhao, X.Guo, A.Deng, W.Xu, Learning Discriminative Speaker Embedding by Improving Aggregation Strategy and Loss Function for Speaker Verification,IJCB 2021, Accept as short oral
[5] H.Xu, Z.Zhou, Y.Qiao, W.Kang, Q.Wu, Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation, AAAI 2021, Accept as distinguished paper(杰出论文奖)
[6] L.Fang, X.Liu, L.Liu, H.Xu, W. Kang*,JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image,ECCV 2020,Accept as spotlight (亮点报告 top 5% of submissions)
[7] Z.Su, L.Fang, W. Kang, D.Hu, M. Pietikäinen, L.Liu,Dynamic Group Convolution for Accelerating Convolutional Neural Networks,ECCV 2020,Accept as spotlight (亮点报告 top 5% of submissions)
[8] N. Liang, W. Xu, C. Luo and W. Kang*, Learning the Front-end Speech Feature with Raw Waveform for End-to-end Speaker Recognition. ICCAI 2020.(EI收录)Accept
[9] H. Xu, L. Fang, X. Liang*, W. Kang, Z. Li, Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN, AAAI 2020, Oral. Accept
[10] Y. Lu, M. Tu, H. Wang, J. Zhao, and W. Kang, Finger Vein Recognition Based on Double-Orientation Coding Histogram. CCBR2019, LNCS 11818, pp. 20–27.
[11] C. Liu,W.Kang*,L.Fang, and N. Liang,Authentication System Design Based on Dynamic Hand Gesture. CCBR2019, LNCS 11818, pp. 94–103.
[12] H. Hu, W. Kang, T. Lu, H. Liu, Y. Fang, J. Zhao, F. Deng, FV-Net: learning a finger-vein like feature representation based on a CNN, ICPR2018, pp. 3489-3494.
[13] X. Lu, Y. Fang, Q.Wu, J. Zhao and W. Kang, A Novel Multiple Distances Based Dynamic Time Warping Method for Online Signature Verification,CCBR 2018,LNCS 10996, pp. 645–652, 2018
[14] X. Lu, Y. Fang, W. Kang*, Z. Wang, David D. Feng,SCUT-MMSIG:A Multimodal Online Signature Database, CCBR2017, LNCS, 10568, pp. 729-738 (EI收录)
[15] X. Qiu, S. Tian, W. Kang*, W.Jia and Q. Wu, Finger Vein Presentation Attack Detection Using Convolutional Neural Networks, CCBR2017,LNCS, 10568, pp. 296-305 (Best Student Paper 最佳学生论文) (EI收录)
[16] L. Tang, Y. Fang, Q.Wu, W. Kang*, and J. Zhao, Online Finger-Writing Signature Verification on Mobile Device for Local Authentication, CCBR 2016, LNCS 9967, pp. 1–8. (EI收录)
[17] Z. Huang, W. Kang*, Q. Wu, J. Zhao, W. Jia, A Finger Vein Identification System based on Image Quality Assessment, CCBR 2016, LNCS 9967, pp. 1–11(Best Poster Paper 最佳张贴论文)(EI收录)
[18] S.S. Muhammad, W. Kang*, Efficient Blind Image Deblurring Method for Palm print Images, The IEEE International Conference on Identity, Security and Behavior Analysis, 2015 , Page(s): 1 - 7. (EI收录)
[19] D. Li, X. Yue, Q. Wu, W. Kang*, CPGF: Core Point Detection from Global Feature for Fingerprint, CCBR2015 LNCS 9428, pp. 224–232. (EI收录)
[20] S. Zhong, X. Chen, D. Li, W. Kang*, and F. Deng, An Intelligent Access Control System based on Multi-biometrics of Finger. CCBR 2014. LNCS 8833, pp. 465-472. (EI收录)

CONTACT BY SCHOLAT
想与我进行学术交流?
立即通过学者网的 工具与我联系!
Https://www.scholat.com/auwxkang
Email:  
联系地址 :   广州市天河区华南理工大学 自动化科学与工程学院 3号楼
扫一扫,访问我的主页
  • Contact by SCHOLAT

SCHOLAT.com 学者网
ABOUT US | SCHOLAT