Online Learning for Large Scale Structured Data in Complex Situations. Online Learning (OL) is the process of predicting answers for a sequence of questions. OL has enjoyed much attention in recent years due to its natural ability of processing large scale non-structured data and adapting to a changing environment. However, OL has three weaknesses: it does not scale for structured data; it often assumes that all of the data are equally important; it often considers that all of the data are compl ....Online Learning for Large Scale Structured Data in Complex Situations. Online Learning (OL) is the process of predicting answers for a sequence of questions. OL has enjoyed much attention in recent years due to its natural ability of processing large scale non-structured data and adapting to a changing environment. However, OL has three weaknesses: it does not scale for structured data; it often assumes that all of the data are equally important; it often considers that all of the data are complete and noise-free. These weaknesses limit its utility, because real data such as those that must be analysed in processing social networks, fraud detection do not satisfy the restrictions. The aim of this project is to develop theoretical and practical advances in OL that overcome the existing weaknesses.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
Australian Laureate Fellowships - Grant ID: FL170100117
Funder
Australian Research Council
Funding Amount
$3,208,192.00
Summary
On snapping up semantics of dynamic pixels from moving cameras. The project aims to develop a suite of original models and algorithms for processing and understanding videos captured by moving cameras, and to establish the mathematical foundations for deep learning-based computer vision to provide theoretical underpinnings. The project expects to generate new knowledge that will transform moving-camera computer vision with step-changes in visual quality enhancement, compression and acceleration ....On snapping up semantics of dynamic pixels from moving cameras. The project aims to develop a suite of original models and algorithms for processing and understanding videos captured by moving cameras, and to establish the mathematical foundations for deep learning-based computer vision to provide theoretical underpinnings. The project expects to generate new knowledge that will transform moving-camera computer vision with step-changes in visual quality enhancement, compression and acceleration technologies, and solutions for fundamental computer vision tasks. A new concept of feature complexity for measuring the discriminant and learnable abilities of features from deep models will also be defined. The outcomes of the project will be critical for enabling autonomous machines to perceive and interact with the environment.Read moreRead less
Multiview Complete Space Learning for Sparse Camera Network Research. Data analytics in video surveillance and social computing is a problem because data are represented by multiple heterogeneous features. This project will develop a multiview complete space learning framework to exploit heterogeneous properties to represent images obtained from sparse camera networks. It will integrate multiple features to identify people and understand behaviour, to build a database of activities occurring in ....Multiview Complete Space Learning for Sparse Camera Network Research. Data analytics in video surveillance and social computing is a problem because data are represented by multiple heterogeneous features. This project will develop a multiview complete space learning framework to exploit heterogeneous properties to represent images obtained from sparse camera networks. It will integrate multiple features to identify people and understand behaviour, to build a database of activities occurring in a wide area of surveillance. It will expand frontier technologies and safeguard Australia by providing warnings for hazardous (for example, overcrowding, trespassing), criminal, and terrorist situations. Results will be applicable internationally and enhance Australia’s role in machine learning and computer vision communities.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220101390
Funder
Australian Research Council
Funding Amount
$402,900.00
Summary
Towards Human-like Machine Perception for Embodied AI. This project aims to investigate human-like visual perception, whereby AI machines can see and interpret the world like a human. The expected outputs will empower AI machines with the abilities of human-centered visual recognition and annotation-efficient learning through a set of deep learning techniques, and the ability to actively gather visual information through a reinforcement learning methodology (for decision support). This research ....Towards Human-like Machine Perception for Embodied AI. This project aims to investigate human-like visual perception, whereby AI machines can see and interpret the world like a human. The expected outputs will empower AI machines with the abilities of human-centered visual recognition and annotation-efficient learning through a set of deep learning techniques, and the ability to actively gather visual information through a reinforcement learning methodology (for decision support). This research is fundamental to the creation of embodied AI machines, which are expected to provide assistance to humans in industry, education and health. It thus will indicate immediate applications embracing autonomous vehicles and domestic robotics, providing scientific, social and economic benefits for Australia.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE150101655
Funder
Australian Research Council
Funding Amount
$297,036.00
Summary
Discriminative detection and quantification of cancer imaging biomarkers. This project aims to develop a new framework for the detection and quantification of cancer biomarkers in diagnostic and histopathology images with discriminative modelling of intrinsic structures. The framework will be the first computerised solution to provide automated, quantitative annotations of cancer imaging biomarkers at the macroscopic and microscopic levels to support standardised reporting of image interpretatio ....Discriminative detection and quantification of cancer imaging biomarkers. This project aims to develop a new framework for the detection and quantification of cancer biomarkers in diagnostic and histopathology images with discriminative modelling of intrinsic structures. The framework will be the first computerised solution to provide automated, quantitative annotations of cancer imaging biomarkers at the macroscopic and microscopic levels to support standardised reporting of image interpretation. It will help to alleviate the inter-observer variability and time-consuming process of manual analysis. The project aims to advance fundamental biomedical imaging research in generalised visual structure extraction and classification, and enable large-scale translational research in systems pathology for personalised cancer care.Read moreRead less
Assistive micro-navigation for vision impaired people. This project aims to develop novel algorithms to transform a simple camera into a smart sensor, that can enable a vision-impaired person to navigate freely and without additional aids in a crowded area. Such a smart sensor will be endowed with the capability to detect and locate obstacles, identify the walking path, recognise objects and traffic signs and convey step-by-step instructions to the user. The project outcomes are expected to impr ....Assistive micro-navigation for vision impaired people. This project aims to develop novel algorithms to transform a simple camera into a smart sensor, that can enable a vision-impaired person to navigate freely and without additional aids in a crowded area. Such a smart sensor will be endowed with the capability to detect and locate obstacles, identify the walking path, recognise objects and traffic signs and convey step-by-step instructions to the user. The project outcomes are expected to improve the well-being and accessibility to public areas for vision-impaired people and reduce physical access disparities for this disadvantaged and vulnerable group. Furthermore, technologies developed in this project can potentially be adapted for use in related special navigation applications such as road safety, self-driving vehicles, and autonomous robots.Read moreRead less
Dynamic Visual Scene Gist Recognition using a Probabilistic Inference Framework. How can we see the forest without intentionally looking for the trees? How can we tell traffic is flowing smoothly on a busy highway without identifying vehicles or measuring their speed? These are the questions that inspire this research project. Humans are endowed with the ability to grasp the ‘gist’ or overall meaning of a complex visual scene from a single glance and without attention to details. The aim of this ....Dynamic Visual Scene Gist Recognition using a Probabilistic Inference Framework. How can we see the forest without intentionally looking for the trees? How can we tell traffic is flowing smoothly on a busy highway without identifying vehicles or measuring their speed? These are the questions that inspire this research project. Humans are endowed with the ability to grasp the ‘gist’ or overall meaning of a complex visual scene from a single glance and without attention to details. The aim of this project is to develop new computational vision models that combine biological visual processing with probabilistic inference for gist recognition. The developed models will be able to mimic human vision by analysing a complex dynamic scene rapidly and classifying its semantic categories, without identifying individual objects.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220101379
Funder
Australian Research Council
Funding Amount
$417,000.00
Summary
Towards Transferable Visual Understanding in the Real World. This project aims to investigate how to improve the transferability of visual understanding algorithm and system in the real-world applications. This project expects to innovate and advance knowledge in the fields of visual transfer learning and generalizable visual representation learning. Expected outcomes of this project include techniques and algorithms to make the visual understanding system robust to diverse real-world scenarios. ....Towards Transferable Visual Understanding in the Real World. This project aims to investigate how to improve the transferability of visual understanding algorithm and system in the real-world applications. This project expects to innovate and advance knowledge in the fields of visual transfer learning and generalizable visual representation learning. Expected outcomes of this project include techniques and algorithms to make the visual understanding system robust to diverse real-world scenarios. This project should provide significant benefits, such as improving the robustness and safety of autonomous vehicles in transportation area, and reducing the cost of destructive data collection for intelligent fault detection in advanced manufacturing area.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE130101311
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Predicting health status of geriatric patients from user trusted multimedia observations. The information technology developed in this project will provide health care specialists with a better window into the lives of elderly patients. Their behaviour can then be accurately interpreted, potentially leading to earlier recognition of problems and better treatment.