Discovery Early Career Researcher Award - Grant ID: DE240100967
Funder
Australian Research Council
Funding Amount
$366,000.00
Summary
Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected o ....Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected outcomes include new paradigms for algorithm design and evaluation, and establishing the problem as a focus of international research. The key practical benefit would be to accelerate the wider deployment of visual perception in applications such as autonomous vehicles, interactive robotics, and video analysis.Read moreRead less
Mapping sites of visceral convergence connecting the colon and bladder. This project aims to develop multiple neuroanatomical approaches to identify where in the central nervous system the sensory signalling from the colon and bladder merge. The combination of such technologies is novel to the study of the central circuits relaying colon/bladder convergence into the brain and will generate new and detailed knowledge of the central pathways in which pelvic organ sensory (discomfort) and motor (de ....Mapping sites of visceral convergence connecting the colon and bladder. This project aims to develop multiple neuroanatomical approaches to identify where in the central nervous system the sensory signalling from the colon and bladder merge. The combination of such technologies is novel to the study of the central circuits relaying colon/bladder convergence into the brain and will generate new and detailed knowledge of the central pathways in which pelvic organ sensory (discomfort) and motor (defecation/urination) functions are coordinated. The expected outcomes are predicted to aid future discovery of mechanisms of cross-organ sensitisation and are anticipated to provide significant benefit to therapy development for chronic visceral pain syndromes associated with bowel and bladder dysfunction.Read moreRead less
New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less
Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the ....Deep visual understanding: learning to see in an unruly world. Deep Learning has achieved incredible success at an astonishing variety of Computer Vision tasks recently. This project aims to convey this success into the challenging domain of high-level image-based reasoning. It will extend deep learning to achieve flexible semantic reasoning about the content of images based on information gleaned from the huge volumes of data available on the Internet. The project expects to overcome one of the primary limitations of deep learning and will greatly increase its practical application to a range of industrial, cultural or health settings.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE190100539
Funder
Australian Research Council
Funding Amount
$408,000.00
Summary
Towards conversational vision-based Artificial Intelligence. This project aims to develop a novel learning framework, Vision-Ask-Answer-Act (V3A). This framework will allow a machine to perform a sequence of actions via a conversation with human users, based on intricate processing of not just visual input, but human-computer verbal exchanges. Artificial intelligence has great potential as a tool for economic productivity and daily tasks. Applications in cars and assistant robots, still in their ....Towards conversational vision-based Artificial Intelligence. This project aims to develop a novel learning framework, Vision-Ask-Answer-Act (V3A). This framework will allow a machine to perform a sequence of actions via a conversation with human users, based on intricate processing of not just visual input, but human-computer verbal exchanges. Artificial intelligence has great potential as a tool for economic productivity and daily tasks. Applications in cars and assistant robots, still in their early days, typically require significant expertise to use effectively. The outcomes of this project will push the boundary of vision-language research to produce a conversational intelligent agent that can be easily used in common situations across industry, transport, the medical sector, and at home.Read moreRead less
How does timing affect mammalian brain development and evolution? This project aims to generate fundamental knowledge on the origin of diversity in mammalian brain circuits by studying development of marsupials and rodents. The expected outcome is to elucidate how differences in the timing, rate and sequence of development of gene expression, cell differentiation and circuit formation can relate to the origin of key evolutionary innovations in the mammalian brain. The significance of understandi ....How does timing affect mammalian brain development and evolution? This project aims to generate fundamental knowledge on the origin of diversity in mammalian brain circuits by studying development of marsupials and rodents. The expected outcome is to elucidate how differences in the timing, rate and sequence of development of gene expression, cell differentiation and circuit formation can relate to the origin of key evolutionary innovations in the mammalian brain. The significance of understanding the dynamics of developmental systems that shape complex brain traits includes establishing new developmental paradigms in evolutionary theory, generating new tools to investigate and manipulate brain gene expression in vivo, and the potential discovery of the causes of neurodevelopmental dysfunction.Read moreRead less
Mechanisms of memory function involving site-specific tau phosphorylation. This project aims to understand the molecular principles that facilitate encoding, maintenance and retrieval of memories in the brain. To store memories in brain circuits, electrical and chemical signals are crucial. Brain cells can integrate signals into biochemical modifications of intracellular proteins. The nature of the protein modifications that represent memory within brain cells is unknown. This project uses innov ....Mechanisms of memory function involving site-specific tau phosphorylation. This project aims to understand the molecular principles that facilitate encoding, maintenance and retrieval of memories in the brain. To store memories in brain circuits, electrical and chemical signals are crucial. Brain cells can integrate signals into biochemical modifications of intracellular proteins. The nature of the protein modifications that represent memory within brain cells is unknown. This project uses innovative genome editing, mathematical modelling and proteomic approaches, to study how biochemical modifications of a key protein called tau help encode and retrieve memories. These molecular insights will make a significant advance in the current understanding of a brain function that is essential to all human activities.Read moreRead less
Molecular control of memory traces. This project aims to understand how particular molecules help encode memories in the brain for future retrieval. Individual memories are encoded in brain cells through an unknown physical process. This project uses innovative approaches to manipulate memory-containing cells and will provide a new detailed explanation of memory. Outcomes of this work will significantly advance the current understanding of how memories are physically generated and maintained, wh ....Molecular control of memory traces. This project aims to understand how particular molecules help encode memories in the brain for future retrieval. Individual memories are encoded in brain cells through an unknown physical process. This project uses innovative approaches to manipulate memory-containing cells and will provide a new detailed explanation of memory. Outcomes of this work will significantly advance the current understanding of how memories are physically generated and maintained, which is an essential component of human and animal life. This research provides significant benefits in understanding the biology behind memory and in maintaining memory capacity in ageing.
Read moreRead less
Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently ....Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently learn complex interaction and navigation behaviours that transfer to unseen environments. Our research should benefit new applications in domains of economic and societal importance that are currently too complex, unsafe, and uncertain for robot assistants, such as aged care, advanced manufacturing and domestic robotics.Read moreRead less
Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the bui ....Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the building of next generation of computer vision systems to work in open and dynamic environments. This should be able to produce solid benefits to the science, society, and economy of Australian via the application of these advanced intelligent systems.Read moreRead less