Continuously learning to see. The ultimate goal of computer vision is to make a machine able to understand the world through analysis of images or videos. The new machine learning techniques developed in this project will enable previously impossible methods of computer vision and help strengthen Australia's competitiveness in this important area.
Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will desig ....Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will design very efficient binary networks, enabling large-scale deployment of deep learning to mobile devices. Thus this project will overcome two primary limitations of deep learning generally, however, and will greatly increase its already impressive domain of practical application.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE120100995
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Visual navigation for sunny summer days and stormy winter nights. This project will develop innovative techniques for camera-based navigation that recognise locations under a wide range of environmental conditions caused by day-night cycles, weather and seasonal change. These techniques will enable the widespread use of cheap and lightweight cameras in robot and personal navigation systems.
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE130100156
Funder
Australian Research Council
Funding Amount
$210,000.00
Summary
Computational infrastructure for machine learning in computer vision. The many trillions of images stored on computers around the world, including more than 100 billion on Facebook alone, represent exactly the information needed to develop artificial vision. All we need do is extract it. This project will develop the computational infrastructure required to allow Australian researchers to achieve this goal.
Discovery Early Career Researcher Award - Grant ID: DE120102948
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Interactive computer vision for image interpretation. This project aims at pushing forward the fundamental research in interactive computer vision. The outcome of this project will enable reliable and efficient solutions to real world image interpretation tasks, such as medical image analysis, financial document processing, and impact evaluation from natural disasters.
Scalable classification for massive datasets: randomised algorithms. The project will develop multi-class classification technologies capable of distinguishing between tens of thousands of classes, which are trained and applied to massive datasets. The technology will be applied in the field of microbiology, bringing high quality digital imaging and machine learning to this important area.
Monitoring intuitive expertise in the context of airport security screening. During airport security screening and processing, confusion and error are greatest when systems or contexts are unfamiliar. Poorly designed systems compromise the interactions of airport security personnel and decrease their ability to promptly and accurately respond to situations. This project aims to deliver a suite of automated methods to monitor security operator knowledge and engagement, to assess the real-time sec ....Monitoring intuitive expertise in the context of airport security screening. During airport security screening and processing, confusion and error are greatest when systems or contexts are unfamiliar. Poorly designed systems compromise the interactions of airport security personnel and decrease their ability to promptly and accurately respond to situations. This project aims to deliver a suite of automated methods to monitor security operator knowledge and engagement, to assess the real-time security screening context, and to detect unusual passenger behaviour at the screening check-point. This monitoring aims to provide new knowledge and techniques to enhance security operator performance, refine the screening process, improve passenger experience and, most critically, ensure safety at Australian airports.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE140100180
Funder
Australian Research Council
Funding Amount
$394,305.00
Summary
Advancing Dense 3D Reconstruction of Non-rigid Scenes by Using a Moving Camera. This project will advance the fundamental research in geometric computer vision and develop a new framework for efficient dense three-dimensional reconstruction of non-rigid scenes by using a moving camera. It is expected that this project will bring about breakthroughs in geometric computer vision with many daily applications, including three-dimensional natural human-computer interaction, three-dimensional reconstr ....Advancing Dense 3D Reconstruction of Non-rigid Scenes by Using a Moving Camera. This project will advance the fundamental research in geometric computer vision and develop a new framework for efficient dense three-dimensional reconstruction of non-rigid scenes by using a moving camera. It is expected that this project will bring about breakthroughs in geometric computer vision with many daily applications, including three-dimensional natural human-computer interaction, three-dimensional reconstruction from historical movies and three-dimensional realistic animations. Its outcomes will enable users to capture and manipulate their surrounding dynamic world in three-dimensions easily and conveniently. This project will alleviate many of the major difficulties (dense correspondences, long sequences, complex deformations) with conventional non-rigid reconstruction methods.Read moreRead less
Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection. The last two decades have seen an escalating interest in automating the coding of facial expressions. Despite this keen interest, the promise of computer vision systems to accurately code facial expressions in natural circumstances remains elusive. Our interdisciplinary team will research a new paradigm to account for facial alignment distortion directly rather than ai ....Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection. The last two decades have seen an escalating interest in automating the coding of facial expressions. Despite this keen interest, the promise of computer vision systems to accurately code facial expressions in natural circumstances remains elusive. Our interdisciplinary team will research a new paradigm to account for facial alignment distortion directly rather than aiming to achieve invariance to it. The project will also research new data agnostic feature compaction capabilities to enable scalable learning on the world’s largest and challenging expression dataset available to us through international collaboration. Tackling these two major open problems will make accurate coding of facial expressions in natural environments achievable.Read moreRead less
Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features t ....Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features to analyse in each modality and the hidden relationships between them. The use of deep belief networks has produced promising results in several fields, such as speech recognition, and so this project believes that our approach has the potential to improve both the sensitivity and specificity of breast cancer detection.Read moreRead less