Skip to content

Instantly share code, notes, and snippets.

@dmurfet dmurfet/dlaus.md
Last active Oct 4, 2019

Embed
What would you like to do?
Deep Learning in Australia

Deep Learning in Australia

People

Below is a list of researchers in Australia for whom deep learning is their main research area. To make this point even clearer: I am not including every single person who has published a paper using deep learning. That list would be much larger. Still, there are no doubt omissions, for which I apologise in advance. The Australian leaders in the field include:

  • Tim Baldwin, Professor University of Melbourne: deep learning for NLP, many papers in ACL.
  • Dacheng Tao, Professor University of Sydney, computer vision, AAAI, CVPR, ECCV.
  • Ian Reid, Professor University of Adelaide, computer vision and robotics, (Google Scholar crashed, TODO).
  • Chunhua Shen, Professor University of Adelaide, computer vision, AAAI, ICML, CVPR.
  • Stephen Gould, Associate Professor ANU, computer vision, WACV, ICCV, CVPR, NeurIPS.
  • Yi Yang, Professor University of Technology Sydney, IJCAI, CVPR, AAAI, ICLR, ECCV.

The rest of the field is below, with more senior people first but otherwise in no particular order. To make this even clearer: in a young field like deep learning, some of the best people are also some of the youngest, so the ordering of the following list is definitely not intended as a ranking of research strength:

  • James Bailey, CS Professor University of Melbourne, ICCV, ICML, IJCAI, CVPR, AAAI.

  • Qinfeng Shi, Associate Professor University of Adelaide, ICCV, IJCAI, CVPR, ECCV, AAAI.

  • Trevor Cohn, Associate Professor University of Melbourne: deep learning for NLP, ICML, ACL, EMNLP.

  • Lexing Xie, Professor ANU, graph data and computer vision, CVPR, AAAI, WACV.

  • Dinh Phung, Professor Monash University, AAAI, PMLR, ICLR.

  • Karin Verspoor, Professor University of Melbourne, deep learning for NLP, particularly for biomedical text, BMC Bioinformatics, ACL.

  • Reza Haffari, Associate Professor Monash, natural language processing, many papers in ACL.

  • Mingming Gong, Lecturer University of Melbourne, NeurIPS, ICML, CVPR, ICCV.

  • Tongliang Liu, Lecturer University of Sydney, CVPR, ECCV, AAAI, ICML, IJCAI.

  • Qi Wu, Senior Lecturer University of Adelaide, visual question answering, CVPR, AAAI, IJCAI

  • Chang Xu, Lecturer University of Sydney, computer vision, ICASSP, AAAI, ECCV.

  • Richard Nock, Adjunct Professor ANU/Sydney, NeurIPS, ICCV, ICML, CVPR, AAAI.

  • Yunchao Wei, Lecturer University of Technology Sydney, computer vision, AAAI, ECCV, CVPR, NeurIPS.

  • Liang Zheng, Lecturer ANU computer vision, ECCV, CVPR, ICCV.

  • Linchao Zhu, Lecturer University of Technology Sydney, NeurIPS, ICCV, CVPR, AAAI, IJCAI.

  • Xiaojun Chang, Monash, AAAI, IJCAI, Neural Computation.

Marcus Hutter and Hanna Kurniawati at ANU are interested in reinforcement learning, but neither appear to have a research interest in deep learning.

Unlike fields like pure mathematics, the best venues for publications in deep learning are often conferences. See below for a list.

Institutes and Centres

The technology oriented institutes, centres and labs:

Policy and society focused:

Somewhat related:

Conferences in deep learning

For the following information I thank Mingming Gong.

NeurIPS and ICML are the two most prestigious conferences in machine learning (including deep learning). ICLR, UAI, and AISTATS are smaller-scale conferences that are as prestigious as NeurIPS and ICML, but focusing on specific areas. ICLR focuses on deep learning, UAI focuses on graphical models and causal inference, and AISTATS focuses on the intersection between Statistics and ML. Most of the machine learning theories and new methodologies will appear in these conferences.

Because vision and language are the two most important aspects of artificial intelligence, they have their own top conferences which focus on solving real problems in vision and language. For example, CVPR, ICCV, and ECCV are the top three conferences in computer vision, and ACL, EMNLP, and NAACL are the top three conferences in natural language processing. Because deep learning is currently the leading technology in vision and language, you will see lots of deep learning papers in these conferences.

AAAI and IJCAI and the top two conferences in the general artificial intelligence area. The machine learning, computer vision, and NLP tracks in these two conferences are not as good as the conferences in learning, vision, or NLP, but they are still better than other conferences. In terms of traditional AI, like multi-agent system, symbolic AI, AAAI and IJCAI are still the best conferences.

Data mining (science) focuses on applying ML methods to solve real-world data analysis problems. The best conference is KDD. ICDM and SDM are also good ones.

Here I briefly summarize the top conferences in each area:

  • ML: NeurIPS, ICML, ICLR, UAI, AISTATS; AAAI, IJCAI
  • Vision: CVPR, ICCV, ECCV; AAAI, IJCAI
  • NLP: ACL, EMNLP, NACCL; AAAI, IJCAI
  • Data science: KDD; ICDM, SDM, AAAI, IJCAI

ARC projects

Found using ARC grant search using "deep learning". DP means Discovery Project, LP means Linkage Project, DE are DECRAS. Listed are CIs only.

  • DP180103232 "Deep reinforcement learning for discovering and visualising biomarkers" University of Adelaide (Gustavo Carneiro, Andrew Bradley, Lyle Palmer).

  • LP180100697 "Music can speak for you: making music with a deep net partner" Western Sydney University (Roger Dean, Tara Hamilton).

  • DP140102794 "Automated analysis of multi-modal medical data using deep belief networks" University of Adelaide (Gustavo Carneiro, Andrew Bradley).

  • LP180101309 "Dynamic Deep Learning for Electricity Demand Forecasting" RMIT (Mahdi Jalili, Xinghuo Yu, Peter Sokolowski).

  • DP180100106 "Towards interpretable deep learning with limited examples" UTS (Ivor Tsang, Yi Yang).

  • DP190102181 " Quantification, optimisation, and application of deep uncertainty" Deakin (Saeid Nahavandi, Abbas Khosravi, Chee Peng Lim).

  • DP0770081 "Complexity, Risk Management and Dynamic Portfolio Selection in Investment Management using Advances in Evolutionary Parallel-computing Artificial Intelligence" Bond (Timothy Brailsford, Richard Terrell, Terence O'Neill, Tom Smith, Jack Penm).

  • LP160101162 " A data science framework for modelling disease patterns from medical images" Sydney (Dagan Feng, Jinman Kim).

  • DP180103491 "Intention-aware cooperative driving behaviour model for Automated Vehicles" QUT (Andry Rakotonirainy, Ronald Schroeter).

  • DP180103023 "Deep visual understanding: learning to see in an unruly world" University of Adelaide (Andton van den Hengel, Damien Teney).

  • DP190103744 "X-ray imaging and magnetic resonance approach for enhanced oil recovery" UNSW (Crhsitoph Arns, Adrian Sheppard).

  • DP180102060 " Protein structure prediction by deep long-range learning" Griffith (Yaoqi Zhou, Kuldip Paliwal).

  • DE180100203 "Deep space-time models for modelling complex environmental phenomena" Wollongong (Andrew Zammit Mangion)

  • DP190102443 "Defense against adversarial attacks on deep learning in computer vision" University of Western Australia (Ajmal Mian).

  • LP170101255 "An automated system for the analysis of road safety and conditions" Central Queensland University (Brijesh Verma).

  • DE170101259 "Zero-shot and few-shot learning with deep knowledge transfer" University of Adelaide (Lingqiao Liu).

  • FL170100117 "On snapping up semantics of dynamic pixels from moving cameras" University of Sydney (Dacheng Tao).

  • "Learning Deep Semantics for Automatic Translation between Human Languages (ARC DP, 2016 - 2019)" link CIs are Prof Trevor Cohn (UoM) and Prof. Reza Haffari (Monash).

  • "Deep Learning for Cybersecurity (DST/Data61, 2017-2021)" [link](https://www.monash.edu/it/our-research/strengths/data- science/machine-learning/research-projects/deep-learning) Prof. Dinh Phung (Monash)

  • "Generative Adversarial Networks for Behaviour Discovery (DST, 2018-2019)" link Prof. Dinh Phung. (Monash)

  • "Towards Data-Efficient Future Action Prediction in the Wild (ARC DECRA, 2019-2021)" link, Dr. Xiaojun Chang (Monash).

Other

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.