We focus on manipulating and analysing large-scale complex data

Our research is dedicated to finding innovative and practical solutions to emerging data and knowledge engineering problems in real-life applications.

We aspire to develop intelligent algorithms that perform pattern recognition tasks for multi-modal data, such as:

  • Visual categorization,
  • Video analysis,
  • Content-based retrieval,
  • Session-based recommendation, etc.

Our Philosophies:

  • Nurturing passions and curiosity in innovation
  • Encouraging creative thinking
  • Striving for research excellence
  • Pursuing real-world impact

Our research spans the following areas:

  • Big Database Management:
  • Machine Learning
  • Multimedia Search
  • Information Systems
  • Intelligent Platform for Automated Road Defect Detection and Asset Management
    Research Collaboration project with Logan City Council (2021)

    Like most local governments in Australia, Logan City Council (LCC) uses intensive, manual methods to survey road surfaces within their jurisdiction to monitor for damage. Their current workflow requires well-trained inspectors to review collected street images to identify and locate any cracks. Due to the high cost and time-consuming nature of the procedure (~$400K per survey), LCC are prevented from conducting frequent surveys to keep the data up to date, resulting in a potential delay of necessary repairs, increased risks of injury and fatality to pedestrians.
    In response to an urgent need for automation in road asset management, we commenced a collaboration with LCC in 2018 aiming at adopting data science for predictive analytics, visual recognition, and interactive visualization. We have successfully retained sustainable partnership with LCC focusing on delivering the nation’s first ‘smart’ road defect and asset analytics atlas, handling heterogeneous road-related data and customised road planning tasks. The atlas affords an unprecedented capacity to automatically demonstrate and report type, severity, location and evidence of road anomalies in real-time, enabling better planning of follow-up repairs and development. This project, in turn, enhances Council employees’ data analytic skillsets and assists road asset managers monitor the functional performance of road networks efficiently.

  • Nano Scholar: Smart Literature Review System
    Research Collaborative Project with AIBN, (2020)

    This PhD project investigates the effect of experiencing same VR story from different characters’ perspectives and how that may affect the overall experience, retention, and post-experience narration of facts. The overarching goal of this project is to make VR storytelling more compelling and enjoyable. 

  • Now Pose! Makeup Transformation (2018)

    This work investigates a comprehensive system for researchers to save time on screening, selecting and digesting papers. The proposed system supports crawling full texts from supported websites, modelling major topics of content, extracting figures and tables automatically, export references and cited papers.

  • Online Action Detection and Multi-Task Predictions with Kinect and Deep Learning (2018)

    This work investigates online action analysis which is a crucial component for various real-time applications, based on the Kinect sensor and the popular deep learning approach these days. Skeleton data is the chosen modality rather than RGB or depth data, because of its low dimensionality as well as effectiveness shown in previous research. In terms of neural networks, an RNN-based model has been selected which is suitable for sequence learning while having probably less complexity and shorter latency than CNN-based models.

  • Dr Helen Huang
  • Yang Li
  • Yadan Luo
  • Chunxia Zhao
  • Hayley Faulkner
  • Junhao Lin
  • Yiyun Zhang
  • Zijian Wang
  • Yang Li
  • Zhuoxiao Chen