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.

Automated cross-lingual link discovery in Wikipedia

At NTCIR-9, we participated in the cross-lingual link discovery (Crosslink) task. In this paper we describe our approaches to discovering Chinese, Japanese, and Korean (CJK) cross-lingual links for English documents in Wikipedia. Our experimental results show that a link mining approach that mines the existing link structure for anchor probabilities and relies on the “translation” using cross-lingual document name triangulation performs very well. The evaluation shows encouraging results for our system.

Overview of the NTCIR-9 crosslink task : cross-lingual link discovery

This paper presents an overview of NTCIR-9 Cross-lingual Link Discovery (Crosslink) task. The overview includes: the motivation of cross-lingual link discovery; the Crosslink task definition; the run submission specification; the assessment and evaluation framework; the evaluation metrics; and the evaluation results of submitted runs. Cross-lingual link discovery (CLLD) is a way of automatically finding potential links between documents in different languages. The goal of this task is to create a reusable resource for evaluating automated CLLD approaches. The results of this research can be used in building and refining systems for automated link discovery. The task is focused on linking between English source documents and Chinese, Korean, and Japanese target documents.

Report on INEX 2011

INEX investigates focused retrieval from structured documents by providing large test collections of structured documents, uniform evaluation measures, and a forum for organizations to compare their results. This paper reports on the INEX 2011 evaluation campaign, which consisted of a five active tracks: Books and Social Search, Data Centric, Question Answering, Relevance Feedback, and Snippet Retrieval. INEX 2011 saw a range of new tasks and tracks, such as Social Book Search, Faceted Search, Snippet Retrieval, and Tweet Contextualization.

Supply chain management systems benefits : the expectation-confirmation theory perspective

Organizations adopt a Supply Chain Management System (SCMS) expecting benefits to the organization and its functions. However, organizations are facing mounting challenges to realizing benefits through SCMS. Studies suggest a growing dissatisfaction among client organizations due to an increasing gap between expectations and realization of SCMS benefits. Further, reflecting the Enterprise System studies such as Seddon et al. (2010), SCMS benefits are also expected to flow to the organization throughout its lifecycle rather than being realized all at once. This research therefore proposes to derive a lifecycle-wide understanding of SCMS benefits and realization to derive a benefit expectation management framework to attain the full potential of an SCMS. The primary research question of this study is: How can client organizations better manage their benefit expectations of SCM systems? The specific research goals of the current study include: (1) to better understand the misalignment of received and expected benefits of SCM systems; (2) to identify the key factors influencing SCM system expectations and to develop a framework to manage SCMS benefits; (3) to explore how organizational satisfaction is influenced by the lack of SCMS benefit confirmation; and (4) to explore how to improve the realization of SCM system benefits. Expectation-Confirmation Theory (ECT) provides the theoretical underpinning for this study. ECT has been widely used in the consumer behavior literature to study customer satisfaction, post-purchase behavior and service marketing in general. Recently, ECT has been extended into Information Systems (IS) research focusing on individual user satisfaction and IS continuance. However, only a handful of studies have employed ECT to study organizational satisfaction on large-scale IS. The current study will enrich the research stream by extending ECT into organizational-level analysis and verifying the preliminary findings of relevant works by Staples et al. (2002), Nevo and Chan (2007) and Nevo and Wade (2007). Moreover, this study will go further trying to operationalize the constructs of ECT into the context of SCMS. The empirical findings of the study commence with a content analysis, through which 41 vendor reports and academic reports are analyzed yielding sixty expected benefits of SCMS. Then, the expected benefits are compared with the benefits realized at a case organization in the Fast Moving Consumer Goods industry sector that had implemented a SAP Supply Chain Management System seven years earlier. The study develops an SCMS Benefit Expectation Management (SCMS-BEM) Framework. The comparison of benefit expectations and confirmations highlights that, while certain benefits are realized earlier in the lifecycle, other benefits could take almost a decade to realize. Further analysis and discussion on how the developed SCMS-BEM Framework influences ECT when applied in SCMS was also conducted. It is recommended that when establishing their expectations of the SCMS, clients should remember that confirmation of these expectations will have a long lifecycle, as shown in the different time periods in the SCMS-BEM Framework. Moreover, the SCMS-BEM Framework will allow organizations to maintain high levels of satisfaction through careful mitigation and confirming expectations based on the lifecycle phase. In addition, the study reveals that different stakeholder groups have different expectations of the same SCMS. The perspective of multiple stakeholders has significant implications for the application of ECT in the SCMS context. When forming expectations of the SCMS, the collection of organizational benefits of SCMS should represent the perceptions of all stakeholder groups. The same mechanism should be employed in the measurements of received SCMS benefits. Moreover, for SCMS, there exists interdependence of the satisfaction among the various stakeholders. The satisfaction of decision-makers or the authorized staff is not only driven by their own expectation confirmation level, it is also influenced by the confirmation level of other stakeholders‘ expectations in the organization. Satisfaction from any one particular stakeholder group can not reflect the true satisfaction of the client organization. Furthermore, it is inferred from the SCMS-BEM Framework that organizations should place emphasis on the viewpoints of the operational and management staff when evaluating the benefits of SCMS in the short and middle term. At the same time, organizations should be placing more attention on the perspectives of strategic staff when evaluating the performance of the SCMS in the long term.

Link discovery for Chinese/English cross-language web information retrieval

Nowadays people heavily rely on the Internet for information and knowledge. Wikipedia is an online multilingual encyclopaedia that contains a very large number of detailed articles covering most written languages. It is often considered to be a treasury of human knowledge. It includes extensive hypertext links between documents of the same language for easy navigation. However, the pages in different languages are rarely cross-linked except for direct equivalent pages on the same subject in different languages. This could pose serious difficulties to users seeking information or knowledge from different lingual sources, or where there is no equivalent page in one language or another. In this thesis, a new information retrieval task—cross-lingual link discovery (CLLD) is proposed to tackle the problem of the lack of cross-lingual anchored links in a knowledge base such as Wikipedia. In contrast to traditional information retrieval tasks, cross language link discovery algorithms actively recommend a set of meaningful anchors in a source document and establish links to documents in an alternative language. In other words, cross-lingual link discovery is a way of automatically finding hypertext links between documents in different languages, which is particularly helpful for knowledge discovery in different language domains. This study is specifically focused on Chinese / English link discovery (C/ELD). Chinese / English link discovery is a special case of cross-lingual link discovery task. It involves tasks including natural language processing (NLP), cross-lingual information retrieval (CLIR) and cross-lingual link discovery. To justify the effectiveness of CLLD, a standard evaluation framework is also proposed. The evaluation framework includes topics, document collections, a gold standard dataset, evaluation metrics, and toolkits for run pooling, link assessment and system evaluation. With the evaluation framework, performance of CLLD approaches and systems can be quantified. This thesis contributes to the research on natural language processing and cross-lingual information retrieval in CLLD: 1) a new simple, but effective Chinese segmentation method, n-gram mutual information, is presented for determining the boundaries of Chinese text; 2) a voting mechanism of name entity translation is demonstrated for achieving a high precision of English / Chinese machine translation; 3) a link mining approach that mines the existing link structure for anchor probabilities achieves encouraging results in suggesting cross-lingual Chinese / English links in Wikipedia. This approach was examined in the experiments for better, automatic generation of cross-lingual links that were carried out as part of the study. The overall major contribution of this thesis is the provision of a standard evaluation framework for cross-lingual link discovery research. It is important in CLLD evaluation to have this framework which helps in benchmarking the performance of various CLLD systems and in identifying good CLLD realisation approaches. The evaluation methods and the evaluation framework described in this thesis have been utilised to quantify the system performance in the NTCIR-9 Crosslink task which is the first information retrieval track of this kind.

Gestural, emergent and expressive : three research themes for haptic interaction

Drawing on three case studies of work in the fields of participatory design, interaction design and electronic arts, we reflect on the implications of these studies for haptic interface research. We propose three themes: gestural; emergent; and expressive; as signposts for a program of research into haptic interaction that could point the way towards novel approaches to haptic interaction and move us from optic to haptic ways of seeing.

Beyond Wearables : Experiences and Trends in Design of Portable Medical Devices

The use of Portable Medical Devices (PMDs) has become increasingly widespread over the last few years. A combination of factors; including advances in technology, the pressure to reduce public health costs and the desire to make health solutions accessible to a wider patient base are contributing to the growth in the PMD market. Design has a clear role to play in the current and future context of the PMD landscape. In this paper, we identify emerging trends in the design of PMDs; including changes in the form, purpose and mode of use, and explore how these trends are likely to fundamentally impact the nature of healthcare and the patient experience from an experience design perspective. We conclude by identifying a research opportunity for design within the healthcare and PMD context.

Achievement unlocked: Investigating the design of effective gamification experiences for mobile applications and devices

This thesis investigates the design of motivating and engaging software experiences. In particular it examines the use of video game elements in non-game contexts, known as gamification, and how to effectively design gamification experiences for smartphone applications. The original contribution of this thesis is a novel framework for designing gamification, derived from an iterative process of evaluating gamified prototypes. The outcomes of this research can help us to better understand the impact of gamification in today's society and how it can be used to design more effective software.

Perceived quality of e‐health services: A conceptual scale development of e‐health service quality based on the C‐OAR‐SE approach

Purpose Health service quality is an important determinant for health service satisfaction and behavioral intentions. The purpose of this paper is to investigate requirements of e‐health services and to develop a measurement model to analyze the construct of “perceived e‐health service quality.” Design/methodology/approach The paper adapts the C‐OAR‐SE procedure for scale development by Rossiter. The focal aspect is the “physician‐patient relationship” which forms the core dyad in the healthcare service provision. Several in‐depth interviews were conducted in Switzerland; first with six patients (as raters), followed by two experts of the healthcare system (as judges). Based on the results and an extensive literature research, the classification of object and attributes is developed for this model. Findings The construct e‐health service quality can be described as an abstract formative object and is operationalized with 13 items: accessibility, competence, information, usability/user friendliness, security, system integration, trust, individualization, empathy, ethical conduct, degree of performance, reliability, and ability to respond. Research limitations/implications Limitations include the number of interviews with patients and experts as well as critical issues associated with C‐OAR‐SE. More empirical research is needed to confirm the quality indicators of e‐health services. Practical implications Health care providers can utilize the results for the evaluation of their service quality. Practitioners can use the hierarchical structure to measure service quality at different levels. The model provides a diagnostic tool to identify poor and/or excellent performance with regard to the e‐service delivery. Originality/value The paper contributes to knowledge with regard to the measurement of e‐health quality and improves the understanding of how customers evaluate the quality of e‐health services.

Efficient Dictionary for Salted Password Analysis

User authentication is essential for accessing computing resources, network resources, email accounts, online portals etc. To authenticate a user, system stores user credentials (user id and password pair) in system. It has been an interested field problem to discover user password from a system and similarly protecting them against any such possible attack. In this work we show that passwords are still vulnerable to hash chain based and efficient dictionary attacks. Human generated passwords use some identifiable patterns. We have analysed a sample of 19 million passwords, of different lengths, available online and studied the distribution of the symbols in the password strings. We show that the distribution of symbols in user passwords is affected by the native language of the user. From symbol distributions we can build smart and efficient dictionaries, which are smaller in size and their coverage of plausible passwords from Key-space is large. These smart dictionaries make dictionary based attacks practical.

Discriminative spoken language understanding using word confusion networks

Current commercial dialogue systems typically use hand-crafted grammars for Spoken Language Understanding (SLU) operating on the top one or two hypotheses output by the speech recogniser. These systems are expensive to develop and they suffer from significant degradation in performance when faced with recognition errors. This paper presents a robust method for SLU based on features extracted from the full posterior distribution of recognition hypotheses encoded in the form of word confusion networks. Following [1], the system uses SVM classifiers operating on n-gram features, trained on unaligned input/output pairs. Performance is evaluated on both an off-line corpus and on-line in a live user trial. It is shown that a statistical discriminative approach to SLU operating on the full posterior ASR output distribution can substantially improve performance both in terms of accuracy and overall dialogue reward. Furthermore, additional gains can be obtained by incorporating features from the previous system output. © 2012 IEEE.