3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environmen ....3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environments and open up new possibilities for applications in fields such as virtual reality, architecture, and city planning. The proposed 3D diffusion models will also enhance the accuracy of computer vision tasks related to 3D scene understanding, such as object detection, tracking, and semantic segmentation.Read moreRead less
Personalised Privacy-Preserving Network Data Publishing System . Data sharing has become a driving force for many businesses in industrial sectors. This project aims to develop a privacy preserving network data publishing system that can preserve user privacy in a personalised way while maintaining maximal utility of the published data. To make accurate privacy preservation, this project will design novel learning models to derive accurate users’ correlation and their privacy intention, develop ....Personalised Privacy-Preserving Network Data Publishing System . Data sharing has become a driving force for many businesses in industrial sectors. This project aims to develop a privacy preserving network data publishing system that can preserve user privacy in a personalised way while maintaining maximal utility of the published data. To make accurate privacy preservation, this project will design novel learning models to derive accurate users’ correlation and their privacy intention, develop efficient privacy preserving algorithms to deal with static and dynamic network data sharing. The success of this project will benefit many industries and government agencies to reduce users’ privacy breaches, avoid illegal consequences of sharing data, and enhance these service providers’ service quality.Read moreRead less
Investigation of a Dynamic Collaborative Framework for Multi-Modal Devices. Modern business and society increasingly call for agility through the rapid formation of groups and collaboration of individuals. Mobile computing devices have the potential to enable this collaboration. However this is currently unrealised; software is not keeping up with hardware. This project aims to investigate techniques and software tools to provide an adaptive framework for multimedia-rich applications, which seam ....Investigation of a Dynamic Collaborative Framework for Multi-Modal Devices. Modern business and society increasingly call for agility through the rapid formation of groups and collaboration of individuals. Mobile computing devices have the potential to enable this collaboration. However this is currently unrealised; software is not keeping up with hardware. This project aims to investigate techniques and software tools to provide an adaptive framework for multimedia-rich applications, which seamlessly support collaboration through multi-modal communications between heterogenous mobile devices. This combination of multimedia, smart devices and advanced communications has the potential to revolutionise many key industries by making information available and manipulable in new and better ways.Read moreRead less
Gesture-controlled interaction to enrich information access. This project is a study of gestural computing (enabled by sensors such as pressure mats, infra-red sensors and video tracking) which aims to move away from desk-bound, restrictive computing environments and towards computing that is more integral to the building structure and space itself. Linking gesture controllers and information sonification delivers a unique bridge between data and human interaction. Enriching the capacity to acce ....Gesture-controlled interaction to enrich information access. This project is a study of gestural computing (enabled by sensors such as pressure mats, infra-red sensors and video tracking) which aims to move away from desk-bound, restrictive computing environments and towards computing that is more integral to the building structure and space itself. Linking gesture controllers and information sonification delivers a unique bridge between data and human interaction. Enriching the capacity to access information in dense workplace environments is central to improved efficiency across the Australian workforce. Greater accuracy and enhanced techniques for controlling information in visually-overloaded work environments contribute to Australia's competitive leadership in a global marketplace.Read moreRead less
Quality of Service in 3G Wireless Systems with Hybrid Networks. The increasing demand of providing Internet-based services over the mobile handsets has led to the transition from circuit-based 2G systems to packet-based network architectures in the emerging 3G systems. A major technical challenge for this paradigm shift is maintaining quality of services (QoS) for the existing data and voice and future Internet services such as streaming multimedia over such packet switching networks. This proje ....Quality of Service in 3G Wireless Systems with Hybrid Networks. The increasing demand of providing Internet-based services over the mobile handsets has led to the transition from circuit-based 2G systems to packet-based network architectures in the emerging 3G systems. A major technical challenge for this paradigm shift is maintaining quality of services (QoS) for the existing data and voice and future Internet services such as streaming multimedia over such packet switching networks. This project aims to investigate end-to-end QoS solutions in the 3G systems. Australian mobile Internet and voice carriers will significantly benefit from this technology.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE0347194
Funder
Australian Research Council
Funding Amount
$411,000.00
Summary
Interactive Television Audience Research Laboratory. Interactive Television is a rapidly emerging platform for global media and e-commerce that is poised to dramatically transform the role of television in society. In collaboration with a range of university and industry partners, Murdoch University aims to establish Australia's first dedicated public research laboratory for assessing consumer motivation, evaluating program usability and theorising audience response to Interactive Television app ....Interactive Television Audience Research Laboratory. Interactive Television is a rapidly emerging platform for global media and e-commerce that is poised to dramatically transform the role of television in society. In collaboration with a range of university and industry partners, Murdoch University aims to establish Australia's first dedicated public research laboratory for assessing consumer motivation, evaluating program usability and theorising audience response to Interactive Television applications. The laboratory will feature specialised testing equipment designed to emulate real-world digital broadcasting environments, enabling rich data on viewing behaviour to be collected and analysed. As an independent facility, the laboratory will provide an invaluable resource for academic and industry research.Read moreRead less
Dynamic media: innovative social and artistic developments in new media in Australia, Britain, Canada and Scandinavia since 1990. This study will foreground strengths and remedy weaknesses in Australian new media arts and innovative social uses of new media. By studying the international strategies for social use of dynamic media, this study will provide information for Australians to more extensively implement dynamic media within a social context. It will highlight the innovation of Australian ....Dynamic media: innovative social and artistic developments in new media in Australia, Britain, Canada and Scandinavia since 1990. This study will foreground strengths and remedy weaknesses in Australian new media arts and innovative social uses of new media. By studying the international strategies for social use of dynamic media, this study will provide information for Australians to more extensively implement dynamic media within a social context. It will highlight the innovation of Australian artists and researchers in the development of dynamic media and position these internationally. A major long-term benefit of this study will be an online database that will both profile and be accessible to Australian artists, arts organizations, new media researchers and social innovators. Read moreRead less
Nuanced recollection and representation: the political and rhetorical strategies of The Peterborough Chronicle. This study will enhance our understanding of essential aspects of historical writing in Anglo-Saxon and early Norman England. The analysis, to be presented in a digital facsimile presentation of this invaluable historical document, will be published in Oxford University's new Bodleian Digital Texts Series. This series, produced at The University of Melbourne with The Bodleian Library ....Nuanced recollection and representation: the political and rhetorical strategies of The Peterborough Chronicle. This study will enhance our understanding of essential aspects of historical writing in Anglo-Saxon and early Norman England. The analysis, to be presented in a digital facsimile presentation of this invaluable historical document, will be published in Oxford University's new Bodleian Digital Texts Series. This series, produced at The University of Melbourne with The Bodleian Library as collaborator, sets the standard internationally for the digital analysis and presentation of materials preserved in manuscript form, and consequently is establishing the University as a centre of excellence for this kind of work.Read moreRead less
Application Frameworks for Collaborative Learning. We will pioneer the use of key software engineering techniques - design patterns and application frameworks - to reduce the cost and improve the quality of online collaborative learning activities. For the first time, we will combine software engineering and educational knowledge to use design patterns to describe best practice for these activities in engineering terms; we will use application frameworks to aggregate these patterns and implement ....Application Frameworks for Collaborative Learning. We will pioneer the use of key software engineering techniques - design patterns and application frameworks - to reduce the cost and improve the quality of online collaborative learning activities. For the first time, we will combine software engineering and educational knowledge to use design patterns to describe best practice for these activities in engineering terms; we will use application frameworks to aggregate these patterns and implement them as a readily usable tool. The result will be a powerful new generation of stable collaborative eLearning tools with enhanced scalability, interoperability and adaptability.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100477
Funder
Australian Research Council
Funding Amount
$421,554.00
Summary
Advancing Human Perception: Countering Evolving Malicious Fake Visual Data. The aim of this project is to provide new effective and generalisable deepfake detection methods for automatically detecting maliciously manipulated visual data generated by misused artificial intelligence (AI) techniques. It will present innovative computer vision and image processing knowledge and techniques, enabling the developed methods to advance human perception in recognising fake data, enhance cybersecurity, and ....Advancing Human Perception: Countering Evolving Malicious Fake Visual Data. The aim of this project is to provide new effective and generalisable deepfake detection methods for automatically detecting maliciously manipulated visual data generated by misused artificial intelligence (AI) techniques. It will present innovative computer vision and image processing knowledge and techniques, enabling the developed methods to advance human perception in recognising fake data, enhance cybersecurity, and protect privacy in AI applications. The anticipated outcomes should provide significant benefits to a wide range of applications, such as providing timely alerts to the media, government organisations, and the industry about misleading fake visual data, and preventing financial crimes on synthetic identity fraud.Read moreRead less