Lipidomics of vision. Presbyopia and cataract are the major causes of visual impairment worldwide. Nevertheless, our understanding of lens ageing at both a cellular and molecular level is limited. This project will gain new insight into the effect of age on lens membrane lipids and their role in the development of presbyopia and cataract.
Testing the Modularity of Memory. Researchers disagree about whether verbal and visual working memory (WM) storage occurs in separate modules. Recent evidence suggests that only verbal memoranda have access to a specialised module, while visual memories make use of more general resources. This project aims to re-examine interference between verbal and visual memoranda using statistical methods specialised for assessing whether multiple latent factors underlie performance on recognition memory ta ....Testing the Modularity of Memory. Researchers disagree about whether verbal and visual working memory (WM) storage occurs in separate modules. Recent evidence suggests that only verbal memoranda have access to a specialised module, while visual memories make use of more general resources. This project aims to re-examine interference between verbal and visual memoranda using statistical methods specialised for assessing whether multiple latent factors underlie performance on recognition memory tasks, examining adult and child populations. This is expected to influence applications of WM theory in many everyday settings, resulting in improvements in educational practices, workplace procedures, and clinical treatments that depend on theoretical understandings of limits in cognition.Read moreRead less
Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of n ....Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of nearly pure additions to fulfil the requisites of accuracy, robustness, calibration and generalisation in real-world computer vision tasks. The success of this project will benefit deep learning-based products on smartphones or robots in health and cybersecurity.Read moreRead less
AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing n ....AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing novel deep learning algorithms. The new algorithms will benefit a wide range of applications, e.g. to effectively use car crash training samples for accurately identifying potential road crashes in transport and to effectively use rare medical imaging training data for robustly diagnosing diseases in health.Read moreRead less
Multiview Complete Space Learning for Sparse Camera Network Research. Data analytics in video surveillance and social computing is a problem because data are represented by multiple heterogeneous features. This project will develop a multiview complete space learning framework to exploit heterogeneous properties to represent images obtained from sparse camera networks. It will integrate multiple features to identify people and understand behaviour, to build a database of activities occurring in ....Multiview Complete Space Learning for Sparse Camera Network Research. Data analytics in video surveillance and social computing is a problem because data are represented by multiple heterogeneous features. This project will develop a multiview complete space learning framework to exploit heterogeneous properties to represent images obtained from sparse camera networks. It will integrate multiple features to identify people and understand behaviour, to build a database of activities occurring in a wide area of surveillance. It will expand frontier technologies and safeguard Australia by providing warnings for hazardous (for example, overcrowding, trespassing), criminal, and terrorist situations. Results will be applicable internationally and enhance Australia’s role in machine learning and computer vision communities.Read moreRead less
Developing better treatments for language disorders. This project will enable better treatment of people with disorders affecting language such as aphasia, dyslexia, and dementia. It will achieve this through development of more detailed theories of language processing, better assessment of language disorders and a better understanding of how treatments for language disorders have their effects.
Parallel and generative binding in human visual cortex. Imagine watching a group of children running around in brightly coloured T-shirts. How does your brain keep track of which colour goes with which T-shirt goes with which child? This project will use magnetic resonance imaging to identify where in our brains information about colour, shape and motion gets put together.
Speaking my language: International speech acquisition in Australia. It is important to differentiate between children who have communication impairment (difficulty learning all languages) from those who only have difficulty learning subsequent language(s). Communication impairment in multilingual children is both undiagnosed and over-diagnosed due to lack of culturally-sensitive measurement tools. Early intervention can ameliorate communication impairment in children and can reduce subsequent e ....Speaking my language: International speech acquisition in Australia. It is important to differentiate between children who have communication impairment (difficulty learning all languages) from those who only have difficulty learning subsequent language(s). Communication impairment in multilingual children is both undiagnosed and over-diagnosed due to lack of culturally-sensitive measurement tools. Early intervention can ameliorate communication impairment in children and can reduce subsequent educational, social and occupational outcomes of untreated communication impairment. By working with people around the world, this Fellowship will result in the development of the International Speech Assessment designed to differentially identify children and to specify holistic early intervention goals.Read moreRead less
Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to vi ....Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to video surveillance applications, which can enhance Australia’s homeland security.Read moreRead less
Seeing the forest and the trees: Cognitive and neural mechanisms underlying recognition of individual objects and sets. When confronted with a set of similar objects, such as a crowd of faces or a flow of oncoming cars, human observers can rapidly and seemingly automatically extract summary statistics of these sets of objects (e.g., mean expression or location). This research will provide insights into how the human visual system executes this massive feat of computation. This represents a vital ....Seeing the forest and the trees: Cognitive and neural mechanisms underlying recognition of individual objects and sets. When confronted with a set of similar objects, such as a crowd of faces or a flow of oncoming cars, human observers can rapidly and seemingly automatically extract summary statistics of these sets of objects (e.g., mean expression or location). This research will provide insights into how the human visual system executes this massive feat of computation. This represents a vital step in understanding vision in general and in eventually applying our knowledge to the development of artificial vision systems and to rehabilitation of visual disorders. The research will also investigate the effects of attentional load on perception of summary statistics of the environment, which is critical for tasks such as driving in busy traffic.Read moreRead less