Holobody: Advancing the Future of Mixed Reality Technologies. This project aims to advance our understanding and use of mixed reality technologies by pioneering a new approach to interaction in virtual systems that recognises, capitalises on, and expands the potential of the human body as a human-machine interface. The project expects to apply the unique, embodied methodologies of dance and movement technology, integrated with customised software, advanced visualisation and artificial intelligen ....Holobody: Advancing the Future of Mixed Reality Technologies. This project aims to advance our understanding and use of mixed reality technologies by pioneering a new approach to interaction in virtual systems that recognises, capitalises on, and expands the potential of the human body as a human-machine interface. The project expects to apply the unique, embodied methodologies of dance and movement technology, integrated with customised software, advanced visualisation and artificial intelligence, to develop next-generation principles of embodied interaction in virtual systems. Expected outcomes are improved assistive technology, new prototyping techniques for manufacturing, and improved productivity through interactive and immersive systems, benefiting Australian businesses, healthcare and the arts.Read moreRead less
Archiving Australian Media Arts: Towards a method and national collection. The early years of Australian digital media arts heritage are at risk. Australians were significant contributors to the development of media arts internationally, as well as making and exhibiting work nationally, yet only a tiny portion of the digital artwork by Australian artists has made it into institutional collections. Deteriorating disks and reliance on obsolete hardware and software mean that innovative digital pre ....Archiving Australian Media Arts: Towards a method and national collection. The early years of Australian digital media arts heritage are at risk. Australians were significant contributors to the development of media arts internationally, as well as making and exhibiting work nationally, yet only a tiny portion of the digital artwork by Australian artists has made it into institutional collections. Deteriorating disks and reliance on obsolete hardware and software mean that innovative digital preservation and access solutions are needed if these artworks are to be saved. Working with key cultural institutions, this project will conserve key media art case studies from the archives of media arts organisations, and develop a best practice method for the preservation of our digital media arts heritage.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE180100950
Funder
Australian Research Council
Funding Amount
$368,446.00
Summary
Building intelligence into online video services by learning user interests. This project aims to build an intelligent video streaming service by characterising users’ view interest patterns and predict user interest changes through learning data from Internet to address the challenge caused by astronomic video population. The outcomes of the project will be of great values for users and our society by intelligently filtering out valueless, harmful, illegal and unwanted videos in advance.
Computer vision from a multi-structural analysis framework. Computer vision has applications in a wide variety of areas: security (video surveillance), entertainment (special effects), health care (medical imaging), and economy (improved automation and consumer products). This project will improve the accuracy and reliability of such applications. Advances will also lead to new products and industries.
Play it again: creating a playable history of Australasian digital games, for industry, community and research purposes. This project provides a unique account of the role played by computer games in familiarising the public to new technologies. The computer game industry grosses billions of dollars each year, and yet game technology is quickly superseded. This project redresses this gap by writing histories of the early digital age, and preserving key artefacts.
Play it again: preserving Australian videogame history. This project aims to demonstrate and evaluate the emulation of obsolete operating systems and programs in a cloud-based environment to document, preserve, and exhibit digital cultural heritage. The challenge of preserving and accessing complex digital cultural heritage such as software is one that collecting institutions worldwide are facing. This project will address this challenge by recovering the history of Australian made videogames of ....Play it again: preserving Australian videogame history. This project aims to demonstrate and evaluate the emulation of obsolete operating systems and programs in a cloud-based environment to document, preserve, and exhibit digital cultural heritage. The challenge of preserving and accessing complex digital cultural heritage such as software is one that collecting institutions worldwide are facing. This project will address this challenge by recovering the history of Australian made videogames of the 1990s, preserving significant local digital game artefacts currently at risk, and investigating how these can be exhibited as playable software using the newest emulation techniques. The project expects to generate new knowledge needed by government, museums and industry to inform future strategy and infrastructure investment aimed at making a range of digital cultural heritage available to the public.Read moreRead less
Whole image understanding by convolutions on graphs. This project seeks to develop technologies that will help computer vision interpret the whole visible scene, rather than just some of the objects therein. Existing automated methods for understanding images perform well at recognising specific objects in canonical poses, but the problem of whole image interpretation is far more challenging. Convolutional neural networks (CNN) have underpinned recent progress in object recognition, but whole-im ....Whole image understanding by convolutions on graphs. This project seeks to develop technologies that will help computer vision interpret the whole visible scene, rather than just some of the objects therein. Existing automated methods for understanding images perform well at recognising specific objects in canonical poses, but the problem of whole image interpretation is far more challenging. Convolutional neural networks (CNN) have underpinned recent progress in object recognition, but whole-image understanding cannot be tackled similarly because the number of possible combinations of objects is too large. The project thus proposes a graph-based generalisation of the CNN approach which allows scene structure to be learned explicitly. This would represent an important step towards providing computers with robust vision, allowing them to interact with their environment.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE170101259
Funder
Australian Research Council
Funding Amount
$360,000.00
Summary
Zero-shot and few-shot learning with deep knowledge transfer. This project aims to develop few-shot and zero-shot learning, visual recognition techniques that can learn a visual concept with few or no visual examples. Visual recognition is a major component in Artificial Intelligence and used in cybernetic security, robotic vision and medical image analysis. This project will use deep learning to enable the zero/few-shot learning to use and model previously unexplored information, making zero/fe ....Zero-shot and few-shot learning with deep knowledge transfer. This project aims to develop few-shot and zero-shot learning, visual recognition techniques that can learn a visual concept with few or no visual examples. Visual recognition is a major component in Artificial Intelligence and used in cybernetic security, robotic vision and medical image analysis. This project will use deep learning to enable the zero/few-shot learning to use and model previously unexplored information, making zero/few-shot learning more practical, scalable and flexible. The project is expected to advance the applicability of visual recognition in many challenging scenarios and provide effective tools to analyse the online visual data for supporting Australia’s cybernetic security.Read moreRead less
Statistical Methods of Model Fitting and Segmentation in Computer Vision. Electronic sensors such as cameras and lasers can provide a rich source of information about the position, shape, and motion of objects around us. However, to extract this information in a reliable, automatic, and accurate way requires a sophisticated statistical theory of the process. Example applications include: video surveillance (better automatic detection of moving people and vehicles and of characterising what those ....Statistical Methods of Model Fitting and Segmentation in Computer Vision. Electronic sensors such as cameras and lasers can provide a rich source of information about the position, shape, and motion of objects around us. However, to extract this information in a reliable, automatic, and accurate way requires a sophisticated statistical theory of the process. Example applications include: video surveillance (better automatic detection of moving people and vehicles and of characterising what those people and vehicles are doing), industrial prototyping and inspection (measuring the size and shape of objects), urban planning (laser scanning streetscapes to create computer models of cities), entertainment industry (movie special effects and games), etc. Read moreRead less