An interaction model for human–machine creative collaboration. The project aims to demonstrate how interactive systems can enhance creative productivity, through the development and evaluation of a model for how humans and AI can interact while creating. This is expected to generate new strategies for effective, intelligent, and domain-general creativity support. These new strategies will be validated in the domains of drawing and music composition by rigorous human-centred prototyping technique ....An interaction model for human–machine creative collaboration. The project aims to demonstrate how interactive systems can enhance creative productivity, through the development and evaluation of a model for how humans and AI can interact while creating. This is expected to generate new strategies for effective, intelligent, and domain-general creativity support. These new strategies will be validated in the domains of drawing and music composition by rigorous human-centred prototyping techniques. The principal anticipated outcome of the project is a model for how to enhance creative work through interacting with AI, an opportunity that is currently largely unexplored. Benefits will include an increase in the rate of creative outputs, both within the creative industries and throughout the economy.Read moreRead less
Intelligent Virtual Human Companions. This research aims to develop intelligent virtual human companions that can seemingly integrate our immediate physical environment and understand their surroundings including people’s emotions, behaviours, actions and interactions. Such a technology will be enabled by leveraging recent advances in mixed/augmented reality technologies, and by developing innovative artificial intelligence and computer vision and graphics algorithms for dynamic real-world envir ....Intelligent Virtual Human Companions. This research aims to develop intelligent virtual human companions that can seemingly integrate our immediate physical environment and understand their surroundings including people’s emotions, behaviours, actions and interactions. Such a technology will be enabled by leveraging recent advances in mixed/augmented reality technologies, and by developing innovative artificial intelligence and computer vision and graphics algorithms for dynamic real-world environments. Unlike robots, the proposed technology will be low cost, readily deployable and customisable, and will not have any physical limitations or maintenance requirements. It will thus have a wide range of applications from elderly care, healthcare care to educational training.Read moreRead less
Natural form, aesthetics and the human brain. This project aims to study how the brain represents the emotion of aesthetic experience. This project will establish the characteristics of flowers and floral design that govern their appeal using large scale web based data collection, and identify the neural representation of floral beauty using integrative data analysis. Outcomes of the project are expected to help flower growers and designers with product planning, supporting industry sustainabili ....Natural form, aesthetics and the human brain. This project aims to study how the brain represents the emotion of aesthetic experience. This project will establish the characteristics of flowers and floral design that govern their appeal using large scale web based data collection, and identify the neural representation of floral beauty using integrative data analysis. Outcomes of the project are expected to help flower growers and designers with product planning, supporting industry sustainability. The project will also establish how the brain generates positive experience in response to our visual environment, promoting well-being by enabling informed visual design decisions.Read moreRead less
Is architecture art? a history of categories, concepts and recent practices. The project aims to link architectural theory with broader cultural theory to provide new ways for architectural theory to engage with creative practice. There is no simple answer to the recurring question of whether architecture is an art. Nevertheless, unpacking the historical and current interests at stake in this question will lead to a better understanding of architecture in contemporary culture. Current issues ari ....Is architecture art? a history of categories, concepts and recent practices. The project aims to link architectural theory with broader cultural theory to provide new ways for architectural theory to engage with creative practice. There is no simple answer to the recurring question of whether architecture is an art. Nevertheless, unpacking the historical and current interests at stake in this question will lead to a better understanding of architecture in contemporary culture. Current issues arising from the exhibition of architecture in art galleries and architecture’s classification in new measures of the cultural economy appear to be unconnected. The project plans to show that these issues are linked in the long history of systems of the arts and recent debates about the role of medium, discipline and aesthetic autonomy in defining the arts.Read moreRead less
Explainable Artificial Creativity. This project aims to develop explainable models for creative AI systems which enable more productive and satisfying interactions between them and their human co-creators. This will boost both human and machine creativity through sustained, ongoing exchanges, leading to high-quality creative outcomes via automated ideation and more advanced human-machine collaborations. The proposed techniques will be validated with creative professionals, ensuring practical ind ....Explainable Artificial Creativity. This project aims to develop explainable models for creative AI systems which enable more productive and satisfying interactions between them and their human co-creators. This will boost both human and machine creativity through sustained, ongoing exchanges, leading to high-quality creative outcomes via automated ideation and more advanced human-machine collaborations. The proposed techniques will be validated with creative professionals, ensuring practical industry relevance. We expect the outcomes to include new methods that automatically generate persuasive explanations, new forms of communication including dialogues between creative AI systems and users, and new understanding of general aspects of explainability for creative AI systems.Read moreRead less
Outsider artists and the reformulation of Australian art. This project aims to produce an understanding of outsider artists, their lives, their histories, and the socio-historic context in which they made their work. “Outsider artists” includes artists experiencing incarceration, disability, mental illness and other forms of marginalisation. Integration of their work will lead to a deeper understanding of mainstream art in Australia to paint a richer, more complex picture of the history of Aust ....Outsider artists and the reformulation of Australian art. This project aims to produce an understanding of outsider artists, their lives, their histories, and the socio-historic context in which they made their work. “Outsider artists” includes artists experiencing incarceration, disability, mental illness and other forms of marginalisation. Integration of their work will lead to a deeper understanding of mainstream art in Australia to paint a richer, more complex picture of the history of Australian art. The project will alter the perspective of arts policy and agencies, and of Australian artists themselves.Read moreRead less
The art of pastoralism in Australia. This project aims to study art made on sheep and cattle station by Aboriginal labourers from the 1880s to the early 1970s, in regions from South-West Australia to Northern Queensland. Australia is said to have been founded 'on the sheep's back', but the experience of Aboriginal labour in Australian pastoralism is little documented. The project will combine the methods of art and labour histories to contextualise carved stock whip handles, early drawings of ho ....The art of pastoralism in Australia. This project aims to study art made on sheep and cattle station by Aboriginal labourers from the 1880s to the early 1970s, in regions from South-West Australia to Northern Queensland. Australia is said to have been founded 'on the sheep's back', but the experience of Aboriginal labour in Australian pastoralism is little documented. The project will combine the methods of art and labour histories to contextualise carved stock whip handles, early drawings of horses, rock engravings, watercolour paintings and branded shields. The project outcomes will be a reconstruction of Aboriginal experiences of pastoralism in Australia to create a more nuanced history of Aboriginal art before 1970, as well as the history of Australian pastoral industries.Read moreRead less
Hacking Copyright in the 21st Century: Art, Law, History & Technology. This project aims to leverage historical insights to investigate the tensions underlying the legal treatment of visual works of art. It will generate software and scholarship that trace the relationship between technology and visual copyright from the first statutory protections of visual artworks in the 18th century through to contemporary regulation of the dissemination of digital image data via digital publishing platforms ....Hacking Copyright in the 21st Century: Art, Law, History & Technology. This project aims to leverage historical insights to investigate the tensions underlying the legal treatment of visual works of art. It will generate software and scholarship that trace the relationship between technology and visual copyright from the first statutory protections of visual artworks in the 18th century through to contemporary regulation of the dissemination of digital image data via digital publishing platforms. Its significance lies in its interdisciplinary and innovative investigation of long-standing problems of contemporary copyright law at the intersection of the visual and digtal domains. It will have impact on law reform and policy development, with benefits for visual artists, collecting institutions and the public.Read moreRead less
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
MemberGuard: Protecting Machine Learning Privacy from Membership Inference. Machine Learning has become a core part of many real-world applications. However, machine learning models are vulnerable to membership inference attacks. In these attacks, an adversary can infer if a given data record has been part of the model's training data. In this project, the team aims to develop new techniques that can be used to counter these attacks, such as 1) new analytical models for membership leakage, 2) ne ....MemberGuard: Protecting Machine Learning Privacy from Membership Inference. Machine Learning has become a core part of many real-world applications. However, machine learning models are vulnerable to membership inference attacks. In these attacks, an adversary can infer if a given data record has been part of the model's training data. In this project, the team aims to develop new techniques that can be used to counter these attacks, such as 1) new analytical models for membership leakage, 2) new methods for susceptibility diagnosis, 3) new defences that leverage privacy and utility. Data-oriented services are estimated to be valuable assets in the future. These techniques can help Australia gain cutting edge advantage in machine learning security and privacy and protect its intellectual property on these services.Read moreRead less