Deep Interaction Learning in Unlabelled Big Data and Complex Systems. This project aims to effectively model intricate interactions deeply embedded in unlabelled big data and complex systems, which are often hierarchical, heterogeneous, contextual, dynamic or even contrastive. Learning such interactions is the keystone of robust data science and for realizing the value of big data but it poses significant challenges and knowledge gaps to existing data analytics and learning systems. The expected ....Deep Interaction Learning in Unlabelled Big Data and Complex Systems. This project aims to effectively model intricate interactions deeply embedded in unlabelled big data and complex systems, which are often hierarchical, heterogeneous, contextual, dynamic or even contrastive. Learning such interactions is the keystone of robust data science and for realizing the value of big data but it poses significant challenges and knowledge gaps to existing data analytics and learning systems. The expected outcomes include new-generation theories and methods for the unsupervised learning of complex interactions in real-life big data, which are anticipated to enable the intrinsic processing of big data complexities and substantially enhance Australia’s leadership in frontier data science research and applications. Read moreRead less
Robust and Explainable 3D Computer Vision. Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-s ....Robust and Explainable 3D Computer Vision. Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-supervised learning that are robust to failures and provide explainable decisions for object detection and scene segmentation. The outcomes are expected to advance theory in robust deep learning and benefit 3D mapping, surveying, infrastructure monitoring, transport and robotics industries.Read moreRead less
Declarative Networks: Towards Robust and Explainable Deep Learning. The aim of this project is to develop declarative machine learning techniques that exploit inherent structure and models of the world. Deep learning has become the dominant approach for machine learning with many products and promises built on this technology. But deep learning is expensive, opaque, brittle and relies solely on human labelled data. This project intends to make deep learning more reliable by establishing theory a ....Declarative Networks: Towards Robust and Explainable Deep Learning. The aim of this project is to develop declarative machine learning techniques that exploit inherent structure and models of the world. Deep learning has become the dominant approach for machine learning with many products and promises built on this technology. But deep learning is expensive, opaque, brittle and relies solely on human labelled data. This project intends to make deep learning more reliable by establishing theory and algorithms that allow physical and mathematical models to be embedded within a deep learning framework, providing performance guarantees and interpretability. This would likely benefit machine learning based products that can understand the world and interact with humans naturally through vision and language.Read moreRead less
Sensory orchestration for multimodal literacy learning in primary education. This project aims to advance new learning and pedagogical models of sensory orchestration for the enhanced multimodal and digital literacy learning of primary students. Multimodal literacy is increasingly important in the Australian curriculum and international research, yet research and education largely prioritise visual texts. This project will generate pedagogical and learning models to optimise students’ broadened ....Sensory orchestration for multimodal literacy learning in primary education. This project aims to advance new learning and pedagogical models of sensory orchestration for the enhanced multimodal and digital literacy learning of primary students. Multimodal literacy is increasingly important in the Australian curriculum and international research, yet research and education largely prioritise visual texts. This project will generate pedagogical and learning models to optimise students’ broadened use of the senses in multimodal and digital literacy learning. It will develop new sensory literacy programs with primary schools, community organisations, and art museums.
Read moreRead less
Graphic Encounters: Colonial Prints and the Inscription of Aboriginality. This project plans to collate the archive of prints depicting Indigenous Australians, from national and international collections, to ask how people's place in this newly encroached territory was inscribed by colonial prints. Before the 1890s, prints (engravings, etchings and lithographs) were the principal means of reproducing images. Prints disseminated imagery of Indigenous people and determined how they were 'put in th ....Graphic Encounters: Colonial Prints and the Inscription of Aboriginality. This project plans to collate the archive of prints depicting Indigenous Australians, from national and international collections, to ask how people's place in this newly encroached territory was inscribed by colonial prints. Before the 1890s, prints (engravings, etchings and lithographs) were the principal means of reproducing images. Prints disseminated imagery of Indigenous people and determined how they were 'put in the picture' of settlement. Our colonial-era cultural heritage includes many prints (engravings, etchings, lithographs, etcetera) of Aborigines, yet they have been overlooked and the story of their production, dissemination and consumption is untold. This project aims to collate and trace this visual archive of Indigenous Australians and present its imagery to all Australians, including descendants, in an exhibition and conference, catalogue, monograph and online database.Read moreRead less
Animating the study of visual communication. This project aims to inform how dynamic colour signals broker information exchange by connecting stimulus design with perception through space and time. Biological studies of colour signalling have largely proceeded via static terms that underestimate the true fluidity of natural contexts. This project aspires to animate the field using innovative approaches such as programmable nano-drones to reveal how flashing colours are perceived under diverse vi ....Animating the study of visual communication. This project aims to inform how dynamic colour signals broker information exchange by connecting stimulus design with perception through space and time. Biological studies of colour signalling have largely proceeded via static terms that underestimate the true fluidity of natural contexts. This project aspires to animate the field using innovative approaches such as programmable nano-drones to reveal how flashing colours are perceived under diverse viewing conditions. The knowledge advances are expected to generate new intellectual paradigms and models, and have significant scope for bio-inspiration in areas such as telecommunication, information processing and the optimal design of visual displays.Read moreRead less
Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to vi ....Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to video surveillance applications, which can enhance Australia’s homeland security.Read moreRead less
Exploiting Context in Multilingual Understanding and Generation. Automatic translation technologies produce incoherent and incorrect outputs in critical areas, such as health, finance, and law. This is due to translating sentences independently, without regard to the global extra-sentential context and rich linguistic structures inherent in the wider document context. This project aims to exploit global linguistic structures, capitalising on recent advances in deep neural networks, in order to g ....Exploiting Context in Multilingual Understanding and Generation. Automatic translation technologies produce incoherent and incorrect outputs in critical areas, such as health, finance, and law. This is due to translating sentences independently, without regard to the global extra-sentential context and rich linguistic structures inherent in the wider document context. This project aims to exploit global linguistic structures, capitalising on recent advances in deep neural networks, in order to generate coherent and faithful text. Expected outcome include next-generation computational technologies for language understanding and generation. This should significantly benefit document-based language technologies and increase their applications in a range of cultural, industrial, and health settings.Read moreRead less
Enabling Automatic Graph Learning Pipelines with Limited Human Knowledge. This project aims to develop an automatic graph learning system for complex graph data analysis. Machine learning for graph data commonly requires significant human knowledge from both domain professionals as well as algorithm experts, rendering existing systems ineffective and unexplainable. This project expects to design novel graph learning techniques which automatically infer graph relations, learn graph models, adapts ....Enabling Automatic Graph Learning Pipelines with Limited Human Knowledge. This project aims to develop an automatic graph learning system for complex graph data analysis. Machine learning for graph data commonly requires significant human knowledge from both domain professionals as well as algorithm experts, rendering existing systems ineffective and unexplainable. This project expects to design novel graph learning techniques which automatically infer graph relations, learn graph models, adapts existing knowledge to new domains, and provide explanations to the graph learning system. The research results should provide benefit to governments and businesses in many critical applications, such as bioassay activity prediction, credit assessment, and drug discovery and vaccine development in response to the pandemic.Read moreRead less
Deep Weak Learning for Morphology Analysis of Micro and Nanoscale Images. This project will develop novel methods for automated discovery and quantification of image phenotypes from micro and nanoscale images. The outcome will be an advance of the state of the art in biomedical image analysis with a particular focus on generalized weakly-supervised deep learning models for morphological feature representation. The methodologies will transform the deep learning pipeline for real biomedical imagin ....Deep Weak Learning for Morphology Analysis of Micro and Nanoscale Images. This project will develop novel methods for automated discovery and quantification of image phenotypes from micro and nanoscale images. The outcome will be an advance of the state of the art in biomedical image analysis with a particular focus on generalized weakly-supervised deep learning models for morphological feature representation. The methodologies will transform the deep learning pipeline for real biomedical imaging scenarios with high heterogeneity and limited training data. The frameworks will facilitate high-throughput processing for a wide range of microscopy image modalities and biological applications, and potentially become the next generation computational platform to support fundamental research in human biology.Read moreRead less