How to pack a bag

The artworks in this exhibition form part of my practice-led PhD research. As a daily task while travelling, packing a bag becomes a complex process, as we juggle the many movements in acquiring, discarding and arranging objects.

These artworks aim to highlight the many material interactions we have during the packing process, emphasising the ways in which we arrange materials and consider spatial constraints. For instance, how much we can “fit” in a bag, or, how we use the space of the room we are within, as well as the many movements our bodies undertake with the materials.

Exhibited works:
"Packing Diagrams", laminated digital prints
"Tracking the packing process", interactive installation
"Packing (exploring)", interactive installation, mixed media
"Packing (puzzle)", interactive installation
"bodies + bags" (excerpt), digital video loop

Object matching using boundary descriptors

The problem of object recognition is of immense practical importance and potential, and the last decade has witnessed a number of breakthroughs in the state of the art. Most of the past object recognition work focuses on textured objects and local appearance descriptors extracted around salient points in an image. These methods fail in the matching of smooth, untextured objects for which salient point detection does not produce robust results. The recently proposed bag of boundaries (BoB) method is the first to directly address this problem. Since the texture of smooth objects is largely uninformative, BoB focuses on describing and matching objects based on their post-segmentation boundaries. Herein we address three major weaknesses of this work. The first of these is the uniform treatment of all boundary segments. Instead, we describe a method for detecting the locations and scales of salient boundary segments. Secondly, while the BoB method uses an image based elementary descriptor (HoGs + occupancy matrix), we propose a more compact descriptor based on the local profile of boundary normals’ directions. Lastly, we conduct a far more systematic evaluation, both of the bag of boundaries method and the method proposed here. Using a large public database, we demonstrate that our method exhibits greater robustness while at the same time achieving a major computational saving – object representation is extracted from an image in only 6% of the time needed to extract a bag of boundaries, and the storage requirement is similarly reduced to less than 8%.

Onion-skin paper

A woman lives with her parents after her husband and sister are found in the woman's burnt out home.

Medical image retrieval based on unclean image bags

Traditional content-based image retrieval (CBIR) scheme with assumption of independent individual images in large-scale collections suffers from poor retrieval performance. In medical applications, images usually exist in the form of image bags and each bag includes multiple relevant images of the same perceptual meaning. In this paper, based on these natural image bags, we explore a new scheme to improve the performance of medical image retrieval. It is feasible and efficient to search the bag-based medical image collection by providing a query bag. However, there is a critical problem of noisy images which may present in image bags and severely affect the retrieval performance. A new three-stage solution is proposed to perform the retrieval and handle the noisy images. In stage 1, in order to alleviate the influence of noisy images, we associate each image in the image bags with a relevance degree. In stage 2, a novel similarity aggregation method is proposed to incorporate image relevance and feature importance into the similarity computation process. In stage 3, we obtain the final image relevance in an adaptive way which can consider both image bag similarity and individual image similarity. The experiments demonstrate that the proposed approach can improve the image retrieval performance significantly.

Occasional paper : Towards the development of an online learning environment (OLE) quality management framework

The project is committed to understanding, recognising and developing various forms of institutionally relevant distributed leadership in developing and trialling various components of a quality management framework for online learning environments in Australian higher education. This paper provides an overview of issues related to the management and improvement of quality, including in the context of higher education. In response to the complex and multi-dimensional nature of both quality and online learning environments (OLEs), the concept of a framework for organising policies, procedures and actions relating to the good governance of OLEs can be found in the literature. Such frameworks vary in scope, format and title, and a (non-exhaustive) sample is presented in summary here. Key learnings that can be drawn from the exemplars frameworks and the related literature include:
- the processes for the design of such frameworks;
- the components of such frameworks;
- the measurement mechanisms and metrics employed in such frameworks; and
- the validation of such frameworks.

Topic model kernel : an empirical study towards probabilistically reduced features for classification

Probabilistic topic models have become a standard in modern machine learning with wide applications in organizing and summarizing ‘documents’ in high-dimensional data such as images, videos, texts, gene expression data, and so on. Representing data by dimensional reduction of mixture proportion extracted from topic models is not only richer in semantics than bag-of-word interpretation, but also more informative for classification tasks. This paper describes the Topic Model Kernel (TMK), a high dimensional mapping for Support Vector Machine classification of data generated from probabilistic topic models. The applicability of our proposed kernel is demonstrated in several classification tasks from real world datasets. We outperform existing kernels on the distributional features and give the comparative results on non-probabilistic data types.

Biomedical time series analysis based on bag-of-words model

This research proposes a number of new methods for biomedical time series classification and clustering based on a novel Bag-of-Words (BoW) representation. It is anticipated that the objective and automatic biomedical time series clustering and classification technologies developed in this work will potentially benefit a wide range of applications, such as biomedical data management, archiving, retrieving, and disease diagnosis and prognosis in the future.