Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global com ....Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global competitiveness. Expected outcomes of this project will help to break the communication barriers between the Deaf and hearing population. This should provide significant benefits to Deaf communities through enhanced communication and improved quality-of-life, leading to a fair, more inclusive and resilient Australian society.Read moreRead less
User-task co-adaptation for effective interactive simulation environments. This project aims to deliver smart interactive simulation environments in which users and simulation tasks work together. This project aims to create novel adaptive algorithms to automatically discover those user and task features that vary together to smartly adapt users and simulation tasks to work together harmoniously, seamlessly and effectively. Interactive simulation environments are the backbone for evaluating conc ....User-task co-adaptation for effective interactive simulation environments. This project aims to deliver smart interactive simulation environments in which users and simulation tasks work together. This project aims to create novel adaptive algorithms to automatically discover those user and task features that vary together to smartly adapt users and simulation tasks to work together harmoniously, seamlessly and effectively. Interactive simulation environments are the backbone for evaluating concepts, designs, products and advanced training systems in industry and government organisations. By bringing the user naturally inside the simulation as a task's component, users can improve their experience while task performance is simultaneously optimised. Intended outcomes include novel dynamic user-task profiling algorithms and new adaptive algorithms for user-task co-adaptation. Practical outcomes may include robust and highly effective simulation environments.Read moreRead less
Semantic Vectorisation: From Bitmaps to Intelligent Representations. The objective of this innovative project is to provide a solution to the open question of representing natural images by semantically rich vector graphics. The challenges are to identify key visual and temporal elements for images and videos, and efficiently decompose the visual data into semantic vector representations that are faithful to original data, compact and editable. The project aims to investigate new bitmap-to-vecto ....Semantic Vectorisation: From Bitmaps to Intelligent Representations. The objective of this innovative project is to provide a solution to the open question of representing natural images by semantically rich vector graphics. The challenges are to identify key visual and temporal elements for images and videos, and efficiently decompose the visual data into semantic vector representations that are faithful to original data, compact and editable. The project aims to investigate new bitmap-to-vector conversion methods. It is expected to develop a framework where semantic labels and hyperlinks can be embedded in visual data automatically. It hopes to pioneer the creation of a web of images where the links are on image/video regions. New image simplification, stylisation, and non-photorealistic rendering methods are expected to be provided.Read moreRead less
Developing key vision technology for automation of aquaculture factory. This project aims to investigate structural, coloured textural, and hyperspectral analysis approaches to achieve automated lobster molt-cycle staging and classification to the level required for commercial production. High labour cost, water contamination, and disease transmission are major barriers in Australian bay lobster aquaculture inhibiting its large scale production. Automation of the production process and reducing ....Developing key vision technology for automation of aquaculture factory. This project aims to investigate structural, coloured textural, and hyperspectral analysis approaches to achieve automated lobster molt-cycle staging and classification to the level required for commercial production. High labour cost, water contamination, and disease transmission are major barriers in Australian bay lobster aquaculture inhibiting its large scale production. Automation of the production process and reducing the human contact with animals are of high priority in the development of this Australian-led emerging industry. The project aims to develop technology to bring this world- first aquaculture factory to large scale production, and create new export opportunities for lobsters and production systems.Read moreRead less
Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training ....Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training, which are anticipated to deepen our understanding of visual representation and make it easier to build and deploy computer vision applications and services. Examples of benefits include modernising machines in manufacturing and farming with visual intelligence. Read moreRead less
Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance witho ....Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance without accessing expensive test labels and improvements to system generalisation. This should provide significant benefits for computer vision applications that currently require expensive labelling, and commercial and economic benefits across sectors such as transportation, security and manufacturing.Read moreRead less
Haptic-Rendered Bell Synthesis for a Practice Carillon Clavier. This project will explore new methods of audio synthesis that respond to haptic sensing. It seeks practical ways to control the synthesis of bell sounds using the mechanical playing action of a carillon keyboard as the human interface in a virtual instrument. Sensing technology developed will also benefit other areas of new performance media where multiple forms of sensory control are required to navigate interactive virtual environ ....Haptic-Rendered Bell Synthesis for a Practice Carillon Clavier. This project will explore new methods of audio synthesis that respond to haptic sensing. It seeks practical ways to control the synthesis of bell sounds using the mechanical playing action of a carillon keyboard as the human interface in a virtual instrument. Sensing technology developed will also benefit other areas of new performance media where multiple forms of sensory control are required to navigate interactive virtual environments. The project also creates new postgraduate research training opportunities in an area that crosses disciplinary boundaries between frontier technology and the creative arts.Read moreRead less
Computational Intelligence for Complex Structured Data. This project aims to use computational intelligence techniques to reliably learn adaptive natural human pointing and gestures to control an interface on a pseudo-3D display. Highly complex data with interconnections between elements is hard to visualise on screens. Most current tools are operated using point/click/drag on 2D screens. The physical technology to capture appropriate human behaviours exists already, but not the adaptive learnin ....Computational Intelligence for Complex Structured Data. This project aims to use computational intelligence techniques to reliably learn adaptive natural human pointing and gestures to control an interface on a pseudo-3D display. Highly complex data with interconnections between elements is hard to visualise on screens. Most current tools are operated using point/click/drag on 2D screens. The physical technology to capture appropriate human behaviours exists already, but not the adaptive learning of the syntax and semantics of individual gestures and actions, nor the multi-gesture information fusion required for understanding, which could significantly enhance efficiency, for example, in sorting through named entities in an investigation. All of this is done naturally by most human beings, using biological neural networks.Read moreRead less
Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capabili ....Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capability and competitiveness in AI, and deliver robust and trustworthy learning technology. The project should provide significant benefits not only in advancing scientific and translational knowledge but also in accelerating AI innovations, safeguarding cyberspace, and reducing the burden on defence expenses in Australia.Read moreRead less