Yuhang Wu

Staff Research Scientist

Research Areas: Adversarial machine learning, Graph-based abnormal detection, and Biometrics

Yuhang Wu, Visa Research Team

Biography

Dr. Yuhang Wu joined Visa Research as a Staff Research Scientist in January 2019. Yuhang received his Ph.D. in Computer Science from University of Houston in 2018, and B.S. in Intelligent Science and Technology from Capital Normal University in 2013. His Ph.D. thesis titled ‘Face Recognition in Unconstrained Conditions: Improving Face Alignment and Constructing a Pose-Invariant Compact Biometric Template’ focuses on robust and efficient algorithms for dealing with unconstrained face recognition problem under large head pose variation and occlusions.

Prior to joining Visa, Yuhang was a Research Assistant at University of Houston, working on deep learning-based face detection, alignment, reconstruction and recognition. Before working at University of Houston, he was a Research Intern at Visa Research, Qualcomm, and the Chinese Academy of Sciences.

As a member of the AI research team, his research interests are in adversarial machine learning, graph-based abnormal detection, and biometrics. He has published more than 10 papers in several international conferences and journals, including International Cryptocurrency Blockchain (ICB), International Conference on Biometrics: Theory, Applications, and Systems (BTAS), International Joint Conference on Biometrics (IJCB), Transactions on Biometrics, Behavior, and Identity Science (T-BIOM) and others. Dr. Wu is the recipient of numerous awards, including the Best Reviewer Award of ICME 2019, Best Ph.D. student of computer science department, University of Houston, and the highest honor of Shuping Scholarship, Beijing.

Conferences

  • Wu, Y., & Kakadiaris, Ioannis A. (2019). Three-Dimensional Face Alignment Using A Convolutional Point-Set Representation. IEEE Transactions on Biometrics, Behavior, and Identity Science.
  • Wu, Y., & Kakadiaris, Ioannis A. (2019). Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition. IAPR International Conference on Biometrics.
  • Wu, Y., Shah, S. K., & Kakadiaris, I. A. (2018). GoDP: Globally Optimized Dual Pathway deep network architecture for facial landmark localization in-the-wild. Image and Vision Computing, 73, 1–16.
  • Wu, Y., & Kakadiaris, I. A. (2018). Tackling the Optimization and Precision Weakness of Deep Cascaded Regression for Facial Key-point Localization. Deep Learning in Biometrics.
  • Dou, P., Wu, Y., Shah, S. K., & Kakadiaris, I. A. (2018). Monocular 3D facial shape reconstruction from a single 2D image with coupled-dictionary learning and sparse coding. Pattern Recognition, 81, 515–527.

  • Wu, Y., Shah, S. K., & Kakadiaris, I. A. (2018). Annotated face model-based alignment: a robust landmark-free pose estimation approach for 3D model registration. Machine Vision and Applications.
  • Wu, Y., & Kakadiaris, I. A. (2017). Facial 3D model registration under occlusions with sensiblepoints-based reinforced hypothesis refinement. IEEE International Joint Conference on Biometrics.
  • Xu, X., Ha, L., Dou, Y., Wu, Y., & Kakadiaris, I. A. (2017). 3D-aided Pose Invariant 2D Face Recognition System. IEEE International Joint Conference on Biometrics.
  • Wu, Y., Shah, S., & Kakadiaris, I. (2016). Rendering or normalization? An analysis of the 3D-aided pose-invariant face recognition. IEEE International Conference on Identity, Security and Behavior Analysis.
  • Wu, Y., Xu, X., Shah, S. K., & Kakadiaris, I. A. (2015). Towards fitting a 3D dense facial model to a 2D image: A landmark-free approach. IEEE International Conference on Biometrics Theory, Applications and Systems.
  • Dou, P., Zhang, L., Wu, Y., Shah, S. K., & Kakadiaris, I. A. (2015). Pose-robust Face Signature for Multi-view Face Recognition. IEEE International Conference on Biometrics Theory, Applications and Systems.
  • Dou, P., Wu, Y., Shah, S. K., & Kakadiaris, I. A. (2014). Robust 3D face shape reconstruction from single images via two-fold coupled structure learning. British Machine Learning Vision Conference.
  • Dou, P., Wu, Y., Shah, S., & Kakadiaris, I. (2014). Benchmarking 3D pose estimation for face recognition. International Conference on Pattern Recognition.