Areas of Expertise

  • Computer Vision
  • Data Mining
  • Machine Learning

Publications

  1. & (2017). Nested Shallow CNN-Cascade for Face Detection in the Wild. Presented at 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017),, 165-172. Washington, DC, USA: IEEE International Conference on Automatic Face Gesture Recognition. doi:10.1109/FG.2017.29
  2. & A bag of words approach to subject specific 3D human pose interaction classification with random decision forests. Graphical Models 76(3), 162-171.
  3. & Fixing the root node: Efficient tracking and detection of 3D human pose through local solutions. Image and Vision Computing 52, 73-87.
  4. & From pose to activity: Surveying datasets and introducing CONVERSE. Computer Vision and Image Understanding 144, 73-105.
  5. & (2015). 3D interactive coronary artery segmentation using random forests and Markov random field optimization. Presented at 2014 IEEE International Conference on Image Processing (ICIP),, 942-946. Paris, France: doi:10.1109/ICIP.2014.7025189

See more...

Teaching

  • CSCM35 Big Data and Data Mining

    This course is an introductory course on data mining and its role in science and engineering. Data mining refers to the computational process of discovering patterns in large data sets. The main goal of the course is for students to gain practical data mining experience. The module is aimed at students with previous experience in programming and statistics, and preferably basic knowledge of the Python language.

  • CSDM03 Computational Thinking skills for Digital Social Scientists.

    This module will discuss some of the most widely used and artificial intelligence and machine learning, regression & clustering techniques and their applications to big data social science questions. The students will gain and understanding of both strengths and weaknesses of learning and practical know-how in applying those theories to real world problems. Topics include big social data concepts, data mining, learning theories, supervised and unsupervised learning, and reinforcement learning.

  • CSLM35 Big Data and Data Mining

    This is an introductory course on data mining and its role in science, engineering, and law. Data mining refers to the computational process of discovering patterns in large data sets. The main goal of the course is to give students practical data mining experience. The module is aimed at students with previous experience in programming and statistics, and preferably basic knowledge of the Python language.

Supervision

  • Electroencephalography Sequential Data Word Embedding in Decision Deadlocks (current)

    Student name:
    MRes
    Other supervisor: Prof Xianghua Xie
  • Deep Learning on Irregular Domains (current)

    Student name:
    PhD
    Other supervisor: Prof Xianghua Xie
  • Visual Text Understanding (current)

    Student name:
    PhD
    Other supervisor: Prof Xianghua Xie