KANG Wenxiong

Academic Title: Professor

Research Interests: Image Processing, Pattern Recognition, Computer Vision, Natural Language Processing (NLP), Biometric Recognition, and Deep Learning

Personal Profile

Kang Wenxiong, Professor and Doctoral Supervisor at South China University of Technology, concurrently serving as Dean of the School of Automation, Guangdong University of Petrochemical Technology; Deputy Director of the Guangdong Provincial Key Laboratory of Intelligent Finance Enterprises; Director of the HuaGong-Benliu Power Artificial Intelligence Joint Laboratory; and Head of the Biometric Recognition and Intelligent Perception Laboratory (BIPLAB) at South China University of Technology. Member of IEEE, ACM, and China Computer Federation (CCF); Standing Committee Member of the Seventh Committee of Tianhe District Association for Science and Technology, Guangzhou; Member of the Technical Committee on Pattern Recognition, Chinese Association for Artificial Intelligence; Member of the Technical Committee on Intelligent Interaction, Chinese Association for Artificial Intelligence; Member of the Technical Committee on Pattern Recognition and Machine Intelligence, Chinese Society of Automation; Member of the Technical Committee on Hybrid Intelligence, Chinese Society of Automation; Member of the Technical Committee on Visual Big Data, Chinese Society of Image and Graphics; and Member of the Second Committee of the Education Working Committee, Chinese Association for Artificial Intelligence.

Conducted visiting research at ETH Zurich, Switzerland, from September 2009 to June 2010 as a Researcher, and at The University of Sydney, Australia, from November 2016 to December 2017 as a Visiting Scholar. Current research interests include image processing and pattern recognition, computer vision, natural language processing, biometric recognition, and deep learning. More information: https://www.scholat.com/auwxkang

Research Projects

In recent years, led three projects funded by the National Natural Science Foundation of China, over ten provincial and ministerial-level projects including the Guangdong Provincial Natural Science Foundation, the Guangdong Science and Technology Program, and the Guangdong-Higher Education Ministry Industry-University-Research Collaboration Project, four self-initiated projects supported by the Fundamental Research Funds for the Central Universities, and more than ten research and development projects commissioned by enterprises and public institutions. Participated in multiple projects including those funded by the National Natural Science Foundation of China and the Guangdong-Hong Kong Key Areas Breakthrough Program. The research work of the national and provincial-level projects includes finger vein and palm vein recognition, hand gesture estimation and free-hand gesture authentication, online signature recognition, multi-biometric recognition, spoofing attack detection, object detection, video analysis and understanding. The research work of the industry-commissioned projects includes intelligent video analysis in power system scenarios and civil aviation airports, intelligent detection, recognition, and tracking of on-site operation personnel, document image analysis and recognition, 3D hand gesture estimation and 3D human pose estimation, embedded machine vision applications, development of intelligent visual sensors, and research and development of vein recognition systems.

Flagship Achievements

Selected Journal Publications

2021

[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=3.965, 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, doi: 10.1109/TIM.2021.3109978.
[3] Z. Zhang, F. Zhong and W. Kang*, Study on Reflection-Based Imaging Finger Vein Recognition, IEEE Transactions on Information Forensics and Security, 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=3.965, 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=3.977, 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=5.824, JCR Q1)

2014-2020

[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. (SCIIF=3.84. JCR Q1)
[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=4.133, 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 (SCI IF=5.824, JCR Q1) First Prize in the Outstanding Paper Award, Guangdong Computer Society
[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=2.779. 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. (SCI IF=5.824, JCR Q1)
[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=4.072, 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. (SCI IF=6.211, JCR Q1)
[9] 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. (SCI IF=5.824, JCR Q1)
[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, (SCI IF=3.977, JCR Q1)
[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, (SCI IF=3.241, JCR Q1)
[13] Wang Hao, Kang Wenxiong*, Chen Xiaopeng. "Research on a Video-Based Combined Palmprint and Palmar Vein Recognition System," Acta Optica Sinica, 2018, 38(2): 0215004. (Core indexed by EI). This paper was awarded the Outstanding Paper Award for Issue 2, 2018.
[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, (SCI IF=3.977, JCR Q1)
[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. (SCI IF=3.241, JCR Q1)
[17] G.Wu, W.Kang*, Exploiting Superpixel and Hybrid Hash for Kernel-Based Visual Tracking, Pattern Recognition, 2017. 68: 175-190 , (SCI IF=3.965, JCR Q1)
[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, (SCI IF=3.977, JCR Q1).
[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. (SCI IF=3.241, JCR Q1)
[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, (CI 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. (SCI IF=4.315, JCR Q1).

Selected Conference Publications

[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
[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
[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
[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
[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 (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. 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-indexed)
[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)
[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.
[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)(EI-indexed)
[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-indexed)
[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-indexed)
[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-indexed)