Dr. Yujing Sun

Biography and Research Interests

Dr. Yujing Sun is currently a Research Assistant Professor at the Department of Computer Science, Faculty of Engineering, HKU. Before that, she was a postdoctoral fellow, collaborating with Prof. Siu Ming Yiu. She obtained her PhD from the Department of Computer Science of HKU, under the supervision of Prof. Wenping Wang in 2018. She obtained her Bachelor’s Degree from the College of Science and Engineering, the University of Minnesota, Twin Cities in 2013. Her research covers topics in a wide range, including intelligent Fintech, deep learning, biometrics, computer graphics, and image processing.

Research Projects

  1. Bitcoin Wallet Investigation: Bitcoin analysis from the micro perspective
  • Bitcoin is sparking an economic revolution. Nevertheless, due to its unique characteristics, e.g., decentralization, non-traceability, and anonymity, digital currencies also attract the attention of criminals as a safe means of settlement. 
  • In most situations, investigation of suspicious bitcoin accounts is accompanied by the actions of the police. Hence, analytical tools for supporting the bitcoin wallet investigation will greatly facilitate the investigation. 
  • In this project, the team aims to promote the regulation of bitcoins by presenting a visualization system, BitAnalysis, for the bitcoin wallet investigation. BitAnalysis provides a rich set of functions and intuitive visual interfaces for law-enforcement officers and regulators, to effectively visualize and analyze the transactions of any wallet (i.e., a bitcoin account), and to track the fund flow.
  • This work is under review of IEEE Transactions on Human Machine Systems. 
  1. Bitcoin Trend Analysis: Bitcoin analysis from the macro perspective
  • As one of the earliest cryptocurrencies, Bitcoin currently has a market share of more than 65%. It has high volatility, while at the same time, can bring high returns. Therefore, both individual and institutional investors start to show great interest in bitcoin investment. People are concerned about the future trend of bitcoin, which is essential for them to make a fortune. However, bitcoin investors lack analysis tools to facilitate effective bitcoin trend analysis. 
  • In this project, the team proposes an integrated visualization system for bitcoin trend analysis, with which users can infer future bitcoin prices based on historical data and analyze bitcoin news.
  • This work is under review of IEEE Transactions on Human Machine Systems.
  1. Face Anti-spoofing: An important topic in the area of Fintech
  • Face biometrics systems are increasingly used by many business applications, which can be vulnerable to malicious attacks, leading to serious consequences. How to effectively detect spoofing faces is a critical problem. 
  • This project aims at distinguishing fakes faces from live ones from the data perspective. 
  • The team presents that appropriate nonlinear adjustment and hair geometry can amplify the contrast between real faces and attacks. Given our exploration, a simple convolutional neural network can solve the face anti-spoofing problem under different attack scenarios and achieve state-of-art performance on well-known face anti-spoofing benchmarks.
  • This work is published in The Visual Computer (2020): 1-14. 

Publications

  • Yujing Sun, Hao Xiong, Siu Ming Yiu and Kwok Yan Lam “BitAnalysis: A Visualization System for Bitcoin Wallet Analysis.” Under review ofIEEE Transactions on Human Machine Systems.
  • Yujing Sun, Hao Xiong, Siu Ming Yiu “BitTrendAnalysis: A Visual Analysis Tool for Bitcoin Trend Analysis.” Under review ofIEEE Transactions on Human Machine Systems.
  • Yujing Sun, Hao Xiong, and Siu Ming Yiu. “Understanding deep face anti-spoofing: from the perspective of data.”The Visual Computer (2020): 1-14.
  • Yujing Sun, Hao Xiong, Siu Ming Yiu and Kwok Yan Lam “BitVis: An Interactive Visualization System for Bitcoin Accounts Analysis.” 2019 Crypto Valley Conference on Blockchain Technology (CVCBT). IEEE, (2019): 21-25.
  • Yujing Sun, Yizhou Yu, and Wenping Wang. “Moiré photo restoration using multiresolution convolutional neural networks.” IEEE Transactions on Image Processing.8 (2018): 4160-4172.
  • Yuexin Ma, Xinge Zhu, Yujing Sun, and Bingzheng Yan. Image tagging by joint deep visual-semantic propagation. Pacific Rim Conference on Multimedia. Springer, Cham, 2017: 25-35.
  • Yujing Sun, Scott Schaefer, and Wenping Wang. “Image Structure Retrieval via L­0  Minimization.”IEEE transactions on visualization and computer graphics. 24.7 (2017): 2129-2139.
  • Yujing Sun,Scott Schaefer, and Wenping Wang. “Denoising point sets via L0 minimization.” Computer Aided Geometric Design (Proceedings of Geometric Model Processing 2015), 35 (2015): 2-15.
Share this...