Profile

I received my PhD in Computer Application Technology from Hunan University in 2007. Now I am an associated professor in the Department of Data Science and Engineering, School of Computer Science and Engineering, Central South University.

In terms of teaching, recently I have mainly taken specialized courses such as multimedia principle and system design and object-oriented programming (C++) for undergraduates majoring in computer science, and basic courses such as database application technology for undergraduates. I have posted some instructional videos on the Bilibili popular video website as a supplement to my classroom teaching, including analog Electronics Technology, which I taught before, and some recent courses (click here for details). I will update the videos from time to time. As for my teaching philosophy.

In terms of scientific research, I mainly focus on facial analysis in the field of computer vision. My research involves: domain generalization and knowledge transfer from photorealistic face domain to cartoon face domain, recognition of micro expressions, error detection and error correction for face feature point location. I try to study the generalization and reliability evaluation methods of artificial intelligence and machine learning models. In addition, I also cooperated with Xiangya Hospital to study the joint motion analysis method based on four-dimensional CT image, so as to provide reliable quantitative diagnostic features for dynamic instability of the ankle joint. And I also do some research to apply computer vision methods to measurement industry such as automaitc pointer-typed meter reading.

Selected Recent Papers:

[1] Lei Wang, Pinyi Huang, Wangyang Cai*, Xiyao Li, "Micro-Expression Recognition by Fusing Action Unit Detection And Spatio-Temporal Features", in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP  2024), accepted.

[2] Pinyi Huang, Lei Wang*, Tianfu Cai, and Kehua Guo, “Micro-Expression Recognition with Layered Relations and More Input Frames,” in 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia: IEEE, Oct. 2023, pp. 2210–2214. doi: 10.1109/ICIP49359.2023.10222395.

[3] Wang L , Hou J , Guo X , et al. Micro-expression Video Clip Synthesis Method based on Spatial-temporal Statistical Model and Motion Intensity Evaluation Function[C]// IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS 2020. IEEE, 2020.

[4] L. Wang, H. Xiao, S. Luo, J. Zhang, and X. Liu, “A weighted feature extraction method based on temporal accumulation of optical flow for micro-expression recognition,” Signal Processing: Image Communication, vol. 78, pp. 246–253, Oct. 2019, doi: 10.1016/j.image.2019.07.011.

[5] L. Wang, Y. Liang, W. Cai,  and B. Zou, “Failure Detection and Correction for Appearance Based Facial Tracking,” Chinese Journal of Electronics, vol. 24, no. 1, pp. 20–25, Jan. 2015, doi: 10.1049/cje.2015.01.004.

Selected Patents:

[1] Facial Feature extraction method of cartoon characters based on qualitative spatial relationship, Patent No. ZL201310574638.1

[2] Method for calibrating and quantifying bone motion and proximity parameters in CT images, Patent No. : ZL201710234682.6

[3] A method and a device for automatic reading of a pointer type instrument that is robust to illumination, Patent No. ZL201911239888.3