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
Added depth: automated high level image interpretation. Humans are very good at understanding the world through imagery, but computers lack this fundamental capacity because they lack experience of what they might see. This project will provide this experience by combining the large volumes of imagery on the Internet with three dimensional information generated by humans for other purposes.
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
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
Visual tracking with environmental constraints. By incorporating high level scene understanding into visual tracking, this project will improve the capacity to monitor and analyse complex patterns of activity in video. This has many applications in public safety and security, but the project will demonstrate it on the challenging task of tracking players during an Australian Football League (AFL) game to gather statistics on their performance.
Discovery Early Career Researcher Award - Grant ID: DE130101775
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Distributed large-scale optimisation methods in computer vision. With the number of images and video available over the internet reaching billions and growing, the need for new tools for handling and interpreting such huge amounts of data is quickly becoming apparent. This project will focus on developing new optimisation methods for efficiently computing solutions for a broad class of large-scale problems.
Sentient buildings. This project aims to unite outputs from the large and varied array of sensors deployed in buildings into a coherent whole. By coordinating detections of resources and personnel from multiple sensors, it intends to enable more efficient allocation of shared resources within a public site such as a hospital, and enable a more effective emergency response. It intends to also allow the building to adapt over time to the way it is used, or to changing conditions. This is expected ....Sentient buildings. This project aims to unite outputs from the large and varied array of sensors deployed in buildings into a coherent whole. By coordinating detections of resources and personnel from multiple sensors, it intends to enable more efficient allocation of shared resources within a public site such as a hospital, and enable a more effective emergency response. It intends to also allow the building to adapt over time to the way it is used, or to changing conditions. This is expected to benefit the Australian construction industry as well as building operators, giving them a valuable export commodity. It intends also to benefit inhabitants of the buildings by providing a more safe, secure and accommodating environment.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE160100090
Funder
Australian Research Council
Funding Amount
$250,000.00
Summary
Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object ....Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object recognition in images, speech recognition and automatic translation, bringing the prospect of machine intelligence closer than ever. Modern machine learning techniques have had huge impact in the last decade in fields such as robotics, computer vision and data analytics. The facility would enable Australian researchers to develop, learn and apply deep networks to problems of national importance in robotic vision and big data analytics. Read moreRead less
Online Learning for Large Scale Structured Data in Complex Situations. Online Learning (OL) is the process of predicting answers for a sequence of questions. OL has enjoyed much attention in recent years due to its natural ability of processing large scale non-structured data and adapting to a changing environment. However, OL has three weaknesses: it does not scale for structured data; it often assumes that all of the data are equally important; it often considers that all of the data are compl ....Online Learning for Large Scale Structured Data in Complex Situations. Online Learning (OL) is the process of predicting answers for a sequence of questions. OL has enjoyed much attention in recent years due to its natural ability of processing large scale non-structured data and adapting to a changing environment. However, OL has three weaknesses: it does not scale for structured data; it often assumes that all of the data are equally important; it often considers that all of the data are complete and noise-free. These weaknesses limit its utility, because real data such as those that must be analysed in processing social networks, fraud detection do not satisfy the restrictions. The aim of this project is to develop theoretical and practical advances in OL that overcome the existing weaknesses.Read moreRead less
Probabilistic Graphical Models For Interventional Queries. The project intends to develop methods to suggest how to optimally intervene so that the future state of the system will best suit our interests. The power of probabilistic graphical models to model complex relationships and interactions among a large number of variables facilitates many applications. However, such models only aim to understand the underlying environment. What is ultimately needed in many real-world applications is to su ....Probabilistic Graphical Models For Interventional Queries. The project intends to develop methods to suggest how to optimally intervene so that the future state of the system will best suit our interests. The power of probabilistic graphical models to model complex relationships and interactions among a large number of variables facilitates many applications. However, such models only aim to understand the underlying environment. What is ultimately needed in many real-world applications is to suggest how we ought to intervene or act, so as to alter the environment to best suit our interests. The proposed project aims to achieve this using probabilistic graphical models on massive real-world data sets, thus facilitating a variety of applications from health care to commerce and the environment.Read moreRead less