Continuous appearance-based trajectory SLAM

This paper describes a novel probabilistic approach to incorporating odometric information into appearance-based SLAM systems, without performing metric map construction or calculating relative feature geometry. The proposed system, dubbed Continuous Appearance-based Trajectory SLAM (CAT-SLAM), represents location as a probability distribution along a trajectory, and represents appearance continuously over the trajectory rather than at discrete locations. The distribution is evaluated using a Rao-Blackwellised particle filter, which weights particles based on local appearance and odometric similarity and explicitly models both the likelihood of revisiting previous locations and visiting new locations. A modified resampling scheme counters particle deprivation and allows loop closure updates to be performed in constant time regardless of map size. We compare the performance of CAT-SLAM to FAB-MAP (an appearance-only SLAM algorithm) in an outdoor environment, demonstrating a threefold increase in the number of correct loop closures detected by CAT-SLAM.

If Kate voted conservative would you? The role of celebrity endorsements in political party advertising

Purpose – This research has been conducted with the aim of determining if celebrity endorsers in political party advertising have a significant impact on UK voter intentions. The use of celebrity endorsements is commonplace in the USA, but little is known about its effects in the UK. This research also aims to incorporate the use of celebrity endorsements in political party advertising with the political salience construct. Political salience represents how prominent politics and political issues are in the minds of the eligible voter. Design/methodology/approach – A 2 (endorser: celebrity; non-celebrity) £ 2 (political salience: high; low) between-subjects factorial design experiment was used. The results show that celebrity endorsements do play a significant role in attitudes towards the political advert, attitudes towards the endorser and voter intention. However, this effect is significantly moderated by political salience. Findings – The results show that low political salience respondents were significantly more likely to vote for the political party when a celebrity endorser is used. However, the inverse effect is found for high political salience respondents. Practical implications – The results offer significant insights into the effect that celebrity endorsers could have in future elections and the importance that political salience plays in the effectiveness of celebrity endorsement. If political parties are to target those citizens that do not actively engage with politics then the use of celebrity endorsements would make a significant impact, given the results of this research. Originality/value – This research would be of particular interest to political party campaigners as well as academics studying the effects of advertising and identity salience.

Discriminative optimisation of the figure of merit for phonetic spoken term detection

This work proposes to improve spoken term detection (STD) accuracy by optimising the Figure of Merit (FOM). In this article, the index takes the form of phonetic posterior-feature matrix. Accuracy is improved by formulating STD as a discriminative training problem and directly optimising the FOM, through its use as an objective function to train a transformation of the index. The outcome of indexing is then a matrix of enhanced posterior-features that are directly tailored for the STD task. The technique is shown to improve the FOM by up to 13% on held-out data. Additional analysis explores the effect of the technique on phone recognition accuracy, examines the actual values of the learned transform, and demonstrates that using an extended training data set results in further improvement in the FOM.

A biologically inspired object spectral-texture descriptor and its application to vegetation classification in power-line corridors

The use of appropriate features to represent an output class or object is critical for all classification problems. In this paper, we propose a biologically inspired object descriptor to represent the spectral-texture patterns of image-objects. The proposed feature descriptor is generated from the pulse spectral frequencies (PSF) of a pulse coupled neural network (PCNN), which is invariant to rotation, translation and small scale changes. The proposed method is first evaluated in a rotation and scale invariant texture classification using USC-SIPI texture database. It is further evaluated in an application of vegetation species classification in power line corridor monitoring using airborne multi-spectral aerial imagery. The results from the two experiments demonstrate that the PSF feature is effective to represent spectral-texture patterns of objects and it shows better results than classic color histogram and texture features.

The effectiveness of literalism-symbolism in business-to-business advertising

A basic element in advertising strategy is the choice of an appeal. In business-to-business (B2B) marketing communication, a long-standing approach relies on literal and factual, benefit-laden messages. Given the highly complex, costly and involved processes of business purchases, such approaches are certainly understandable. This project challenges the traditional B2B approach and asks if an alternative approach—using symbolic messages that operate at a more intrinsic or emotional level—is effective in the B2B arena. As an alternative to literal (factual) messages, there is an emerging body of literature that asserts stronger, more enduring results can be achieved through symbolic messages (imagery or text) in an advertisement. The present study contributes to this stream of research. From a theoretical standpoint, the study explores differences in literal-symbolic message content in B2B advertisements. There has been much discussion—mainly in the consumer literature—on the ability of symbolic messages to motivate a prospect to process advertising information by necessitating more elaborate processing and comprehension. Business buyers are regarded as less receptive to indirect or implicit appeals because their purchase decisions are based on direct evidence of product superiority. It is argued here, that these same buyers may be equally influenced by advertising that stimulates internally-directed motivation, feelings and cognitions about the brand. Thus far, studies on the effect of literalism and symbolism are fragmented, and few focus on the B2B market. While there have been many studies about the effects of symbolism no adequate scale exists to measure the continuum of literalism-symbolism. Therefore, a first task for this study was to develop such a scale. Following scale development, content analysis of 748 B2B print advertisements was undertaken to investigate whether differences in literalism-symbolism led to higher advertising performance. Variations of time and industry were also measured. From a practical perspective, the results challenge the prevailing B2B practice of relying on literal messages. While definitive support was not established for the use of symbolic message content, literal messages also failed to predict advertising performance. If the ‘fact, benefit laden’ assumption within B2B advertising cannot be supported, then other approaches used in the business-to-consumer (B2C) sector, such as symbolic messages may be also appropriate in business markets. Further research will need to test the potential effects of such messages, thereby building a revised foundation that can help drive advances in B2B advertising. Finally, the study offers a contribution to the growing body of knowledge on symbolism in advertising. While the specific focus of the study relates to B2B advertising, the Literalism-Symbolism scale developed here provides a reliable measure to evaluate literal and symbolic message content in all print advertisements. The value of this scale to advance our understanding about message strategy may be significant in future consumer and business advertising research.

Feature-domain super-resolution for IRIS recognition

Uncooperative iris identification systems at a distance suffer from poor resolution of the captured iris images, which significantly degrades iris recognition performance. Superresolution techniques have been employed to enhance the resolution of iris images and improve the recognition performance. However, all existing super-resolution approaches proposed for the iris biometric super-resolve pixel intensity values. This paper considers transferring super-resolution of iris images from the intensity domain to the feature domain. By directly super-resolving only the features essential for recognition, and by incorporating domain specific information from iris models, improved recognition performance compared to pixel domain super-resolution can be achieved. This is the first paper to investigate the possibility of feature domain super-resolution for iris recognition, and experiments confirm the validity of the proposed approach.

Mining positive and negative patterns for relevance feature discovery

It is a big challenge to guarantee the quality of discovered relevance features in text documents for describing user preferences because of the large number of terms, patterns, and noise. Most existing popular text mining and classification methods have adopted term-based approaches. However, they have all suffered from the problems of polysemy and synonymy. Over the years, people have often held the hypothesis that pattern-based methods should perform better than term-based ones in describing user preferences, but many experiments do not support this hypothesis. The innovative technique presented in paper makes a breakthrough for this difficulty. This technique discovers both positive and negative patterns in text documents as higher level features in order to accurately weight low-level features (terms) based on their specificity and their distributions in the higher level features. Substantial experiments using this technique on Reuters Corpus Volume 1 and TREC topics show that the proposed approach significantly outperforms both the state-of-the-art term-based methods underpinned by Okapi BM25, Rocchio or Support Vector Machine and pattern based methods on precision, recall and F measures.

Teaching new dogs old tricks. How the move to 24/7 interactive, integrated multimedia, multi-platform news and feature delivery is not really changing the skills employers demand of graduates

The journalism revolution is upon us. In a world where we are constantly being told that everyone can be a publisher and challenges are emerging from bloggers, Twitterers and podcasters, journalism educators are inevitably reassessing what skills we now need to teach to keep our graduates ahead of the game. QUT this year tackled that question head-on as a curriculum review and program restructure resulted in a greater emphasis on online journalism. The author spent a week in the online newsrooms of each of two of the major players – ABC online news and thecouriermail.com to watch, listen and interview some of the key players. This, in addition to interviews with industry leaders from Fairfax and news.com, lead to the conclusion that while there are some new skills involved in new media much of what the industry is demanding is in fact good old fashioned journalism. Themes of good spelling, grammar, accuracy and writing skills and a nose for news recurred when industry players were asked what it was that they would like to see in new graduates. While speed was cited as one of the big attributes needed in online journalism, the conclusion of many of the players was that the skills of a good down-table sub or a journalist working for wire service were not unlike those most used in online newsrooms.

Swell : a feature-length screenplay set in the world of Australian surfing, and an accompanying exegesis on three-act structure

Despite many arguments to the contrary, the three-act story structure, as propounded and refined by Hollywood continues to dominate the blockbuster and independent film markets. Recent successes in post-modern cinema could indicate new directions and opportunities for low-budget national cinemas.

Spectral–texture feature extraction using statistical moments with application to object-based vegetation species classification

The use of appropriate features to characterise an output class or object is critical for all classification problems. In order to find optimal feature descriptors for vegetation species classification in a power line corridor monitoring application, this article evaluates the capability of several spectral and texture features. A new idea of spectral–texture feature descriptor is proposed by incorporating spectral vegetation indices in statistical moment features. The proposed method is evaluated against several classic texture feature descriptors. Object-based classification method is used and a support vector machine is employed as the benchmark classifier. Individual tree crowns are first detected and segmented from aerial images and different feature vectors are extracted to represent each tree crown. The experimental results showed that the proposed spectral moment features outperform or can at least compare with the state-of-the-art texture descriptors in terms of classification accuracy. A comprehensive quantitative evaluation using receiver operating characteristic space analysis further demonstrates the strength of the proposed feature descriptors.

Facial expression recognition using facial movement features

Facial expression is an important channel for human communication and can be applied in many real applications. One critical step for facial expression recognition (FER) is to accurately extract emotional features. Current approaches on FER in static images have not fully considered and utilized the features of facial element and muscle movements, which represent static and dynamic, as well as geometric and appearance characteristics of facial expressions. This paper proposes an approach to solve this limitation using ‘salient’ distance features, which are obtained by extracting patch-based 3D Gabor features, selecting the ‘salient’ patches, and performing patch matching operations. The experimental results demonstrate high correct recognition rate (CRR), significant performance improvements due to the consideration of facial element and muscle movements, promising results under face registration errors, and fast processing time. The comparison with the state-of-the-art performance confirms that the proposed approach achieves the highest CRR on the JAFFE database and is among the top performers on the Cohn-Kanade (CK) database.