Tao Wang

Tao Wang

Associate Professor

Minjiang University

Biography

I am an Associate Professor in the School of Computer and Big Data and the International Digital Economy College at Minjiang University. I obtained my PhD from The Australian National University, working with Xuming He and Nick Barnes. I was also a member of the Computer Vision Research Group, National ICT Australia, Canberra.

Interests

  • Object detection and segmentation
  • Context modeling for scene understanding
  • Learning and inference for computer vision

Education

  • Ph.D. in Engineering, 2016

    The Australian National University

  • B.E. in Information Engineering, 2009

    South China University of Technology

Publications

Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024.

Learning a Layout Transfer Network for Context Aware Object Detection
Learning a Layout Transfer Network for Context Aware Object Detection. IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2020.

Efficient Scene Layout Aware Object Detection for Traffic Surveillance
Efficient Scene Layout Aware Object Detection for Traffic Surveillance. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Traffic Surveillance Workshop and Challenge Best Paper Award, 2017.

Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning
Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

Glass Object Localization by Joint Inference of Boundary and Depth
Glass Object Localization by Joint Inference of Boundary and Depth. IEEE International Conference on Pattern Recognition (ICPR), 2012.

Learning Hough Forest with Depth-Encoded Context for Object Detection
Learning Hough Forest with Depth-Encoded Context for Object Detection. IEEE International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2012.

Laplacian Margin Distribution Boosting for Learning from Sparsely Labeled Data
Laplacian Margin Distribution Boosting for Learning from Sparsely Labeled Data. IEEE International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2011.

Teaching

  • Programming Principles I - Robotics Lab
  • Artificial Intelligence
  • Introduction to Artificial Intelligence
  • Linux System Applications
  • Comprehensive Training in Digital Systems
  • Professional English for Computer Science

Services

  • Reviewer for Pattern Recognition, IET Computer Vision, IET Image Processing, IET Intelligent Transport Systems, Machine Vision and Applications, IJCAI, AAAI, ICPR

Contact