Effective image search and retrieval through automatic image annotation. This project aims to develop an effective and efficient image retrieval system, so that images are retrieved as easily as textual data. The project researches and develops several key know-hows in image retrieval. It enables Australia to maintain significant advantage in the frontier technology of information processing.
Knowledge discovery and recommendation of multimedia data in healthcare. The project aims to develop tools to abstract/streamline the ever-growing information-rich multimedia contents into easily discoverable knowledges. Advanced multimedia knowledge graph will be first time developed to accurately exploit hidden knowledge for health industry, and served to generate right information recommendation for healthcare professionals (HCP) at the right time. The proposed technology will improve HCPs' c ....Knowledge discovery and recommendation of multimedia data in healthcare. The project aims to develop tools to abstract/streamline the ever-growing information-rich multimedia contents into easily discoverable knowledges. Advanced multimedia knowledge graph will be first time developed to accurately exploit hidden knowledge for health industry, and served to generate right information recommendation for healthcare professionals (HCP) at the right time. The proposed technology will improve HCPs' communication, keep them up to date, and enhance their speedy reaction to constantly changing situations/diseases, thus reducing poor patient outcomes and unnecessary hospital costs. It will make significant impact to a range of industries, e.g. healthcare, where personalised professional recommendation is demanded.Read moreRead less
Scalable Cross-Media Hashing for Searching Heterogeneous Data Sources. This project aims to use novel indexing and search approaches to realise the value of multimedia data. The ever-increasing availability and heterogeneity of multimedia data are calling for new approaches to search information across different media types and data sources. This project aims to enable accurate and real-time cross-media searches from billions of multimedia objects collected from various media sources by tackling ....Scalable Cross-Media Hashing for Searching Heterogeneous Data Sources. This project aims to use novel indexing and search approaches to realise the value of multimedia data. The ever-increasing availability and heterogeneity of multimedia data are calling for new approaches to search information across different media types and data sources. This project aims to enable accurate and real-time cross-media searches from billions of multimedia objects collected from various media sources by tackling the heterogeneity and scalability issues. Expected outcomes include scalable cross-media hashing techniques to capture implicit correlations existing in heterogeneous data and embed high-dimensional features into short binary codes; new binary code indexing and ranking schemes to further improve search speed and quality; and a large-scale cross-media system to evaluate methods and demonstrate the practical value.Read moreRead less
Realising the value of mobile videos with context awareness. Innovative approaches to analysing online video content and context will lead to new ways of interacting with video in the mobile world. This project will aim to develop real-time mobile systems for enabling rich and highly dynamic digital video experiences through context-aware indexing, retrieval and consumption of mobile videos.
Intelligent Image Retrieval from Distorted and Partial Queries for Rapid Mobile Identification of Pests Threatening Food and the Environment. Pests and diseases are major threats to the Australian food industry and environmental biosecurity. A rapid and mobile pest information retrieval system is critical to prevent a pest becoming established and devastating the region. However, automated insect image retrieval remains an unsolved challenge in the research community. This project addresses the ....Intelligent Image Retrieval from Distorted and Partial Queries for Rapid Mobile Identification of Pests Threatening Food and the Environment. Pests and diseases are major threats to the Australian food industry and environmental biosecurity. A rapid and mobile pest information retrieval system is critical to prevent a pest becoming established and devastating the region. However, automated insect image retrieval remains an unsolved challenge in the research community. This project addresses the fundamental problem of distorted and partial image query in cluttered background in order to achieve pest identification at a much earlier on-site stage. The success of this research will not only make a technical breakthrough towards retrieving objects with movable body parts, but also revolutionise the current pest detection and monitoring process.Read moreRead less
Exposing the anonymous attacker: detecting identity crimes using real-time entity resolution on large dynamic databases. Given the increasingly large costs of identity crimes in Australia, developing improved electronic identity verification techniques is highly significant in reducing losses from such crimes, making the Australian economy more competitive, and increasing consumer confidence in Australian financial institutions. Veda Advantage is widely used for identity verification by Australi ....Exposing the anonymous attacker: detecting identity crimes using real-time entity resolution on large dynamic databases. Given the increasingly large costs of identity crimes in Australia, developing improved electronic identity verification techniques is highly significant in reducing losses from such crimes, making the Australian economy more competitive, and increasing consumer confidence in Australian financial institutions. Veda Advantage is widely used for identity verification by Australian financial service providers, so the benefits of the techniques developed in this project will automatically flow through to the Australian community. These techniques will be sufficiently generic to be of use for real-time identity verification in a broad range of applications, including e-Government portals, electronic banking, online stores, or national security systems.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200100245
Funder
Australian Research Council
Funding Amount
$410,518.00
Summary
Bayesian nonparametric learning for practical sequential decision making. This project aims to develop new methods to support practical sequential decision making under uncertainty. It expects to pave the way for the next generation of sequential decision making uniquely characterised by uncertainty modelling, high sample-efficiency, efficient environment change adaptation, and automatical reward function learning. The expected outcomes will advance machine learning knowledge with a new deep lea ....Bayesian nonparametric learning for practical sequential decision making. This project aims to develop new methods to support practical sequential decision making under uncertainty. It expects to pave the way for the next generation of sequential decision making uniquely characterised by uncertainty modelling, high sample-efficiency, efficient environment change adaptation, and automatical reward function learning. The expected outcomes will advance machine learning knowledge with a new deep learning schema for data modelling and sequential decision-making knowledge with a novel deep reinforcement learning methodology. These developments have immediate applications in autonomous vehicles, advanced manufacturing, and dynamic pricing, with scientific, economic, and social benefits for Australia and the world.Read moreRead less
Single model irregular-region retrieval for rapid plant disease detection. This project aims to study the major technical barrier in plant disease image retrieval to build a pervasive rapid plant disease identification system. The techniques are designed to function on one or very few sample images, thus enabling on-line in field disease identification linked to authoritative plant disease image libraries. The success of this project will not only make significant contributions to fundamental th ....Single model irregular-region retrieval for rapid plant disease detection. This project aims to study the major technical barrier in plant disease image retrieval to build a pervasive rapid plant disease identification system. The techniques are designed to function on one or very few sample images, thus enabling on-line in field disease identification linked to authoritative plant disease image libraries. The success of this project will not only make significant contributions to fundamental theory in single model image retrieval, but also create a revolution in plant disease early detection for effective and efficient crop protection.Read moreRead less