Towards pose-robust face recognition on video

This thesis investigates face recognition in video under the presence of large pose variations. It proposes a solution that performs simultaneous detection of facial landmarks and head poses across large pose variations, employs discriminative modelling of feature distributions of faces with varying poses, and applies fusion of multiple classifiers to pose-mismatch recognition. Experiments on several benchmark datasets have demonstrated that improved performance is achieved using the proposed solution.

Ranking based clustering for social event detection

The problem of clustering a large document collection is not only challenged by the number of documents and the number of dimensions, but it is also affected by the number and sizes of the clusters. Traditional clustering methods fail to scale when they need to generate a large number of clusters. Furthermore, when the clusters size in the solution is heterogeneous, i.e. some of the clusters are large in size, the similarity measures tend to degrade. A ranking based clustering method is proposed to deal with these issues in the context of the Social Event Detection task. Ranking scores are used to select a small number of most relevant clusters in order to compare and place a document. Additionally,instead of conventional cluster centroids, cluster patches are proposed to represent clusters, that are hubs-like set of documents. Text, temporal, spatial and visual content information collected from the social event images is utilized in calculating similarity. Results show that these strategies allow us to have a balance between performance and accuracy of the clustering solution gained by the clustering method.

Steady state visually evoked potential correlates of static and dynamic emotional face processing

While the neural regions associated with facial identity recognition are considered to be well defined, the neural correlates of non-moving and moving images of facial emotion processing are less clear. This study examined the brain electrical activity changes in 26 participants (14 males M = 21.64, SD = 3.99; 12 females M = 24.42, SD = 4.36), during a passive face viewing task, a scrambled face task and separate emotion and gender face discrimination tasks. The steady state visual evoked potential (SSVEP) was recorded from 64-electrode sites. Consistent with previous research, face related activity was evidenced at scalp regions over the parieto-temporal region approximately 170 ms after stimulus presentation. Results also identified different SSVEP spatio-temporal changes associated with the processing of static and dynamic facial emotions with respect to gender, with static stimuli predominately associated with an increase in inhibitory processing within the frontal region. Dynamic facial emotions were associated with changes in SSVEP response within the temporal region, which are proposed to index inhibitory processing. It is suggested that static images represent non-canonical stimuli which are processed via different mechanisms to their more ecologically valid dynamic counterparts.

Text mining with semantic annotation : using enriched text representation for entity-oriented retrieval, semantic relation identification and text clustering

This project is a step forward in the study of text mining where enhanced text representation with semantic information plays a significant role. It develops effective methods of entity-oriented retrieval, semantic relation identification and text clustering utilizing semantically annotated data. These methods are based on enriched text representation generated by introducing semantic information extracted from Wikipedia into the input text data. The proposed methods are evaluated against several start-of-art benchmarking methods on real-life data-sets. In particular, this thesis improves the performance of entity-oriented retrieval, identifies different lexical forms for an entity relation and handles clustering documents with multiple feature spaces.

Robust clustering of multi-type relational data via a heterogeneous manifold ensemble

High-Order Co-Clustering (HOCC) methods have attracted high attention in recent years because of their ability to cluster multiple types of objects simultaneously using all available information. During the clustering process, HOCC methods exploit object co-occurrence information, i.e., inter-type relationships amongst different types of objects as well as object affinity information, i.e., intra-type relationships amongst the same types of objects. However, it is difficult to learn accurate intra-type relationships in the presence of noise and outliers. Existing HOCC methods consider the p nearest neighbours based on Euclidean distance for the intra-type relationships, which leads to incomplete and inaccurate intra-type relationships. In this paper, we propose a novel HOCC method that incorporates multiple subspace learning with a heterogeneous manifold ensemble to learn complete and accurate intra-type relationships. Multiple subspace learning reconstructs the similarity between any pair of objects that belong to the same subspace. The heterogeneous manifold ensemble is created based on two-types of intra-type relationships learnt using p-nearest-neighbour graph and multiple subspaces learning. Moreover, in order to make sure the robustness of clustering process, we introduce a sparse error matrix into matrix decomposition and develop a novel iterative algorithm. Empirical experiments show that the proposed method achieves improved results over the state-of-art HOCC methods for FScore and NMI.

Clustering and labeling a web scale document collection using Wikipedia clusters

Clustering is an important technique in organising and categorising web scale documents. The main challenges faced in clustering the billions of documents available on the web are the processing power required and the sheer size of the datasets available. More importantly, it is nigh impossible to generate the labels for a general web document collection containing billions of documents and a vast taxonomy of topics. However, document clusters are most commonly evaluated by comparison to a ground truth set of labels for documents. This paper presents a clustering and labeling solution where the Wikipedia is clustered and hundreds of millions of web documents in ClueWeb12 are mapped on to those clusters. This solution is based on the assumption that the Wikipedia contains such a wide range of diverse topics that it represents a small scale web. We found that it was possible to perform the web scale document clustering and labeling process on one desktop computer under a couple of days for the Wikipedia clustering solution containing about 1000 clusters. It takes longer to execute a solution with finer granularity clusters such as 10,000 or 50,000. These results were evaluated using a set of external data.

The influence of internal load density on the energy and thermal performance of air-conditioned office buildings in the face of global warming

Internal heat sources may not only consume energy directly through their operation (e.g. lighting), but also contribute to building cooling or heating loads, which indirectly change building cooling and heating energy. Through the use of building simulation technique, this paper investigates the influence of building internal load densities on the energy and thermal performance of air conditioned office buildings in Australia. Case studies for air conditioned office buildings in major Australian capital cities are presented. It is found that with a decrease of internal load density in lighting and/or plug load, both the building cooling load and total energy use can be significantly reduced. Their effect on overheating hour reduction would be dependent on the local climate. In particular, it is found that if the building total internal load density is reduced from the base case of “medium” to “extra–low, the building total energy use under the future 2070 high scenario can be reduced by up to 89 to 120 kWh/m² per annum and the overheating problem could be completely avoided. It is suggested that the reduction in building internal load densities could be adopted as one of adaptation strategies for buildings in face of the future global warming.

Assessment and application of clustering techniques to atmospheric particle number size distribution for the purpose of source apportionment

Long-term measurements of particle number size distribution (PNSD) produce a very large number of observations and their analysis requires an efficient approach in order to produce results in the least possible time and with maximum accuracy. Clustering techniques are a family of sophisticated methods which have been recently employed to analyse PNSD data, however, very little information is available comparing the performance of different clustering techniques on PNSD data. This study aims to apply several clustering techniques (i.e. K-means, PAM, CLARA and SOM) to PNSD data, in order to identify and apply the optimum technique to PNSD data measured at 25 sites across Brisbane, Australia. A new method, based on the Generalised Additive Model (GAM) with a basis of penalised B-splines, was proposed to parameterise the PNSD data and the temporal weight of each cluster was also estimated using the GAM. In addition, each cluster was associated with its possible source based on the results of this parameterisation, together with the characteristics of each cluster. The performances of four clustering techniques were compared using the Dunn index and Silhouette width validation values and the K-means technique was found to have the highest performance, with five clusters being the optimum. Therefore, five clusters were found within the data using the K-means technique. The diurnal occurrence of each cluster was used together with other air quality parameters, temporal trends and the physical properties of each cluster, in order to attribute each cluster to its source and origin. The five clusters were attributed to three major sources and origins, including regional background particles, photochemically induced nucleated particles and vehicle generated particles. Overall, clustering was found to be an effective technique for attributing each particle size spectra to its source and the GAM was suitable to parameterise the PNSD data. These two techniques can help researchers immensely in analysing PNSD data for characterisation and source apportionment purposes.

Embracing humanity in the face of death: Why do existential concerns moderate ingroup humanization?

People humanize their ingroup to address existential concerns about their mortality, but the reasons why they do so remain ambiguous. One explanation is that people humanize their ingroup to bolster their social identity in the face of their mortality. Alternatively, people might be motivated to see their ingroup as more uniquely human (UH) to distance themselves from their corporeal “animal” nature. These explanations were tested in Australia, where social identity is tied less to UH and more to human nature (HN) which does not distinguish humans from animals. Australians attributed more HN traits to the ingroup when mortality was salient, while the attribution of UH traits remained unchanged. This indicates that the mortality-buffering function of ingroup humanization lies in reinforcing the humanness of our social identity, rather than just distancing ourselves from our animal nature. Implications for (de)humanization in intergroup relations are discussed.

Techniques to effectively buffer schedules in the face of uncertainties

Resource assignment and scheduling is a difficult task when job processing times are stochastic, and resources are to be used for both known and unknown demand. To operate effectively within such an environment, several novel strategies are investigated. The first focuses upon the creation of a robust schedule, and utilises the concept of strategically placed idle time (i.e. buffering). The second approach introduces the idea of maintaining a number of free resources at each time, and culminates in another form of strategically placed buffering. The attraction of these approaches is that they are easy to grasp conceptually, and mimic what practitioners already do in practice. Our extensive numerical testing has shown that these techniques ensure more prompt job processing, and reduced job cancellations and waiting time. They are effective in the considered setting and could easily be adapted for many real life problems, for instance those in health care. This article has more importantly demonstrated that integrating the two approaches is a better strategy and will provide an effective stochastic scheduling approach.