Research Summary

I conduct both theoretical and applied research in the areas of large scale inverse optimization, compressive sensing, sparse learning, image/video processing, multimedia, computer vision and medical image analysis. I am most interested in creating efficient algorithms with nice theoretical guarantees and practical values (especially in practical applications involved large scale data), as well as developing novel theoretical insights into existing algorithms and problems.

Projects on Maching Learning and Computer Vision

Non-Intrusive Load Monitoring (NILM)

  • How to fully exploit the inherent characteristics of each appliance in a specific functional mode?
  • How to fully consider both specific characteristics, working states and consumptions together?
  • How to derive efficient algorithms for low-sample-rate data of each appliance to enhance model scalability for Low-frequency Energy Disaggregation?
  • How to investigate effiecient inference algorithms to learn the latent states from measured aggregation data?

Human/Facial Behavior

  • Real-time face tracking with a web camera or Kinect
  • Fatigue detection by tracking slow eyelid closure and blinking
  • Dyadic Synchrony as a Measure of Trust and Veracity
  • Facial expression recognition

Structure Sparsity: Theorems, Algorithms and Applications

  • Structured sparsity theorems give the insight when known structure/sparse priors
  • Iterative greedy algorithm (StructOMP) for strcutured sparsity recovery problem
  • Sucessful applications on Compressive sensing on graph structured sparse data

Dynamic Group Sparsity and Its Applications

  • The coefficients in data are not only sparse but also clustered
  • Applications on Video forground detection and abnormal detection
  • New feature selection scheme for dynamic group sparse feaures



Projects on Biomedical Imaging Informatics


Lung Cancer Imaging Genomics

  • Connections between morphology and prognosis
  • Big pathological Image analytics for clinical outcome prediction
  • High-dimensional molecular profiling data analytics
  • Integrating pathological image data with molecular profiling data

Magnetic Resonance Imaging

  • Compressive Sensing techniques for accelerated MR imaging
  • Fast Image reconstruction method for compressive sensing MRI
  • Gradient sparse and wavelet sparse prior for MRI

4D Cardiac Reconstruction and Motion Analysis

  • 4D high resolution cardiac images acquired by the 320 multi-detector CT
  • 4D cardiac reconstruction of the surface of the left ventricle (LV) for a full cardiac cycle.
  • Capturing complex anatomical features, such as the papillary muscles and the ventricular trabeculae
  • Enabling to investigate functional significance in health and disease

3D Modeling, Simulation and Segmentation

  • Deformal moded for cardiac/lung/liver/brain segmentation
  • 3D Metamorph model for MRI and CT segmentation
  • 3D active volume model for MRI and CT segmentation


Projects on Biometrics Before 2005