Automatic generation of effective video summaries

As the popularity of video as an information medium rises, the amount of video content that we produce and archive keeps growing. This creates a demand for shorter representations of videos in order to assist the task of video retrieval. The traditional solution is to let humans watch these videos and write textual summaries based on what they saw. This summarisation process, however, is time-consuming. Moreover, a lot of useful audio-visual information contained in the original video can be lost. Video summarisation aims to turn a full-length video into a more concise version that preserves as much information as possible. The problem of video summarisation is to minimise the trade-off between how concise and how representative a summary is. There are also usability concerns that need to be addressed in a video summarisation scheme. To solve these problems, this research aims to create an automatic video summarisation framework that combines and improves on existing video summarisation techniques, with the focus on practicality and user satisfaction. We also investigate the need for different summarisation strategies in different kinds of videos, for example news, sports, or TV series. Finally, we develop a video summarisation system based on the framework, which is validated by subjective and objective evaluation. The evaluation results shows that the proposed framework is effective for creating video skims, producing high user satisfaction rate and having reasonably low computing requirement. We also demonstrate that the techniques presented in this research can be used for visualising video summaries in the form web pages showing various useful information, both from the video itself and from external sources.

Margin-adaptive model selection in statistical learning

A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one to take into account that learning within a small model can be much easier than within a large one. Requiring this “strong margin adaptivity” makes the model selection problem more challenging. We first prove, in a general framework, that some penalization procedures (including local Rademacher complexities) exhibit this adaptivity when the models are nested. Contrary to previous results, this holds with penalties that only depend on the data. Our second main result is that strong margin adaptivity is not always possible when the models are not nested: for every model selection procedure (even a randomized one), there is a problem for which it does not demonstrate strong margin adaptivity.

The influence of cultural selection on strategic communication

Strategic communication is held to be a key process by which organisations respond to environmental uncertainty. In the received view articulated in the literatures of organisational communication and public relations, strategic communication results from collaborative efforts by organisational members to create shared understanding about environmental uncertainty and, as a result of this collective understanding, formulate appropriate communication responses. In this study, I explore how such collaborative efforts towards the development of strategic communication are derived from, and bounded by, culturally shared values and assumptions. Study of the influences of an organisation‟s culture on the formulation of strategic communication is a fundamental conceptual challenge for public relations and, to date, a largely unaddressed area of research. This thesis responds to this challenge by describing a key property of organisational culture – the action of cultural selection (Durham, 1992). I integrate this property of cultural selection to extend and refine the descriptive range of Weick‟s (1969, 1979) classic sociocultural model of organizing. From this integration I propose a new model, the Cultural Selection of Strategic Communication (CSSC). Underpinning the CSSC model is the central proposition that because of the action of cultural selection during organizing processes, the inherently conservative properties of an organisation‟s culture constrain development of effective strategic communication in ways that may be unrelated to the outcomes of “environmental scanning” and other monitoring functions heralded by the public relations literature as central to organisational adaptation. Thus, by examining the development of strategic communication, I describe a central conservative influence on the social ecology of organisations. This research also responds to Butschi and Steyn‟s (2006) call for the development of theory focusing on strategic communication as well as Grunig (2006) and Sriramesh‟s (2007) call for research to further understand the role of culture in public relations practice. In keeping with the explorative and descriptive goals of this study, I employ organisational ethnography to examine the influence of cultural selection on the development of strategic communication. In this methodological approach, I use the technique of progressive contextualisation to compare data from two related but distinct cultural settings. This approach provides a range of descriptive opportunities to permit a deeper understanding of the work of cultural selection. Findings of this study propose that culture, operating as a system of shared and socially transmitted social knowledge, acts through the property of cultural selection to influence decision making, and decrease conceptual variation within a group. The findings support the view that strategic communication, as a cultural product derived from the influence of cultural selection, is an essential feature to understand the social ecology of an organisation.

The importance of organisational culture to improve a project selection process : case of public infrastructure project in Indonesia

Project selection is a decision-making process that is not merely influenced by technical aspects but also by the people who involved in the process. Organisational culture is described as a set of values and norms that are shared by people within the organisation that affects the way they interact with each other and with stakeholders from outside the organisation. The aim of this paper is to emphasize the importance of organisational culture on improving the quality of decisions in the project selection process, in addition to the influence of technical aspects of a project. The discussion is based on an extensive literature review and, as such, represents the first part of a research agenda investigating the impact of organisational culture on the project selection process applicable specifically to road infrastructure contracts. Four existing models of organisational culture (Denison 1990; Cameron and Quinn 2006; Hofstede 2001; Glaser et al 1987) are discussed and reviewed in view of their use in the larger research project to investigate the impact of culture on identified critical elements of decision-making. An understating of the way organisational culture impacts on project selection will increase the likelihood in future of relevant government departments selecting projects that achieve their stated organisational goals.

User-representative feature selection for keystroke dynamics

Continuous user authentication with keystroke dynamics uses characters sequences as features. Since users can type characters in any order, it is imperative to find character sequences (n-graphs) that are representative of user typing behavior. The contemporary feature selection approaches do not guarantee selecting frequently-typed features which may cause less accurate statistical user-representation. Furthermore, the selected features do not inherently reflect user typing behavior. We propose four statistical based feature selection techniques that mitigate limitations of existing approaches. The first technique selects the most frequently occurring features. The other three consider different user typing behaviors by selecting: n-graphs that are typed quickly; n-graphs that are typed with consistent time; and n-graphs that have large time variance among users. We use Gunetti’s keystroke dataset and k-means clustering algorithm for our experiments. The results show that among the proposed techniques, the most-frequent feature selection technique can effectively find user representative features. We further substantiate our results by comparing the most-frequent feature selection technique with three existing approaches (popular Italian words, common n-graphs, and least frequent ngraphs). We find that it performs better than the existing approaches after selecting a certain number of most-frequent n-graphs.

The impact of organisational culture on the project selection process : The case of public infrastructure project in Indonesia

Project selection is a complex decision-making process as it involves multiple objectives, constraints and stakeholders. Understanding the organisation, in particular organisational culture, is an essential stage in improving decision-making process. The influences of organisational culture on decision-making can be seen in the way people work as a team, act and cooperate in their teamwork to achieve the set goals, and also in how people think, prioritize and decide. This paper aims to give evidence of the impact of organisational culture on the decision-making process in project selection, in the Indonesian context. Data was collected from a questionnaire survey developed based on the existing models of organisational culture (Denison 1990, Hofstede 2001, and Glaser et al 1987). Four main cultural traits (involvement, consistency, mission and power-distance) were selected and employed to examine the influence of organisational culture on the effectiveness of decision-making in the current Indonesian project selection processes. The results reveal that there are differences in organisational cultures for two organisations in three provinces. It also suggests that organisational culture (particularly the traits of ‘involvement’, ‘consistency’ and ‘mission’) contribute to the effectiveness of decision-making in the selected cases.

Retrofitting commercial office buildings for sustainability : tenants’ expectations and experiences

Introduction Buildings, which account for approximately half of all annual energy and greenhouse gas emissions, are an important target area for any strategy addressing climate change. Whilst new commercial buildings increasingly address sustainability considerations, incorporating green technology in the refurbishment process of older buildings is technically, financially and socially challenging. This research explores the expectations and experiences of commercial office building tenants, whose building was under-going green refurbishment. Methodology Semi-structured in-depth interviews with seven residents and neighbours of a large case-study building under-going green refurbishment in Melbourne, Australia. Built in 1979, the 7,008m² ‘B’ grade building consists of 11 upper levels of office accommodation, ground floor retail, and a basement area leased as a licensed restaurant. After refurbishment, which included the installation of chilled water pumps, solar water heating, waterless urinals, insulation, disabled toilets, and automatic dimming lights, it was expected that the environmental performance of the building would move from a non-existent zero ABGR (Australian Building Greenhouse Rating) star rating to 3.5 stars, with a 40% reduction in water consumption and 20% reduction in energy consumption. Interviews were transcribed, with responses analysed using a thematic approach, identifying categories, themes and patterns. Results Commercial property tenants are on a journey to sustainability - they are interested and willing to engage in discussions about sustainability initiatives, but the process, costs and benefits need to be clear. Critically, whilst sustainability was an essential and non-negotiable criterion in building selection for government and larger corporate tenants, sustainability was not yet a core business value for smaller organisations – whilst they could see it as an emerging issue, they wanted detailed cost-benefit analyses, pay-back calculations of proposed technologies and, ideally, wished they could trial the technology first-hand in some way. Although extremely interested in learning more, most participants reported relatively minimal knowledge of specific sustainability features, designs or products. In discussions about different sustainable technologies (e.g., waterless urinals, green-rated carpets), participants frequently commented that they knew little about the technology, had not heard of it or were not sure exactly how it worked. Whilst participants viewed sustainable commercial buildings as the future, they had varied expectations about the fate of existing older buildings – most felt that they would have to be retrofitted at some point to meet market expectations and predicted the emergence of a ‘non-sustainability discount’ for residing in a building without sustainable features. Discussion This research offers a beginning point for understanding the difficulty of integrating green technology in older commercial buildings. Tenants currently have limited understandings of technology and potential building performance outcomes, which ultimately could impede the implementation of sustainable initiatives in older buildings. Whilst the commercial property market is interested in learning about sustainability in the built environment, the findings highlight the importance of developing a strong business case, communication and transition plan for implementing sustainability retrofits in existing commercial buildings.

Towards an automatic system for road lane marking extraction in large-scale aerial images acquired over rural areas by hierarchical image analysis and Gabor filter

An automatic approach to road lane marking extraction from high-resolution aerial images is proposed, which can automatically detect the road surfaces in rural areas based on hierarchical image analysis. The procedure is facilitated by the road centrelines obtained from low-resolution images. The lane markings are further extracted on the generated road surfaces with 2D Gabor filters. The proposed method is applied on the aerial images of the Bruce Highway around Gympie, Queensland. Evaluation of the generated road surfaces and lane markings using four representative test fields has validated the proposed method.

Acoustic component detection for automatic species recognition in environmental monitoring

Automatic species recognition plays an important role in assisting ecologists to monitor the environment. One critical issue in this research area is that software developers need prior knowledge of specific targets people are interested in to build templates for these targets. This paper proposes a novel approach for automatic species recognition based on generic knowledge about acoustic events to detect species. Acoustic component detection is the most critical and fundamental part of this proposed approach. This paper gives clear definitions of acoustic components and presents three clustering algorithms for detecting four acoustic components in sound recordings; whistles, clicks, slurs, and blocks. The experiment result demonstrates that these acoustic component recognisers have achieved high precision and recall rate.

Evaluating automatic road detection across a large aerial imagery collection

The automated extraction of roads from aerial imagery can be of value for tasks including mapping, surveillance and change detection. Unfortunately, there are no public databases or standard evaluation protocols for evaluating these techniques. Many techniques are further hindered by a reliance on manual initialisation, making large scale application of the techniques impractical. In this paper, we present a public database and evaluation protocol for the evaluation of road extraction algorithms, and propose an improved automatic seed finding technique to initialise road extraction, based on a combination of geometric and colour features.

Investigating the performance of automatic new topic identification across multiple datasets 1

Recent studies on automatic new topic identification in Web search engine user sessions demonstrated that neural networks are successful in automatic new topic identification. However most of this work applied their new topic identification algorithms on data logs from a single search engine. In this study, we investigate whether the application of neural networks for automatic new topic identification are more successful on some search engines than others. Sample data logs from the Norwegian search engine FAST (currently owned by Overture) and Excite are used in this study. Findings of this study suggest that query logs with more topic shifts tend to provide more successful results on shift-based performance measures, whereas logs with more topic continuations tend to provide better results on continuation-based performance measures.