Matthew Collins

Full body image feature representations for gender profiling

In this paper we focus on building robust image representations for gender classification from full human bodies. We first investigate a number of state-of-the-art image representations with regard to their suitability for gender profiling from static body images. Features include Histogram of Gradients (HOG), spatial pyramid HOG and spatial pyramid bag of words etc. These representations are learnt and combined based on a kernel support vector machine (SVM) classifier. We compare a number of different SVM kernels for this task but conclude that the simple linear kernel appears to give the best overall performance. Our study shows that individual adoption of these representations for gender classification is not as promising as might be expected, given their good performance in the tasks of pedestrian detection on INRIA datasets, and object categorisation on Caltech 101 and Caltech 256 datasets. Our best results, 80% classification accuracy, were achieved from a combination of spatial shape information, captured by HOG, and colour information captured by HSV histogram based features. Additionally, to the best of our knowledge, currently there is no publicly available dataset for full body gender recognition. Hence, we further introduce a novel body gender dataset covering a large diversity of human body appearance.

Students’ perceptions of lecturing approaches: traditional versus interactive teaching

Background There is an increasing trend toward transcending from traditional teaching to student-centered methodologies that actively engage students. We aimed to analyze students’ perceptions of effective interactive teaching using PollEverywhere Audience Response System (ARS) as a worthwhile teaching methodology. It can be of great help in maintaining students’ attention and in facilitating the lecturer to pick up students’ misunderstandings and correct them. Materials and methods This system was introduced to the undergraduate dental curriculum to increase student’s motivation and attention, giving immediate feedback on student understanding during an anatomy module. Computer science (CS) students who were more familiar with the use of this technology were also involved in the study for comparison and validation of the findings. The lecturer strategically inserted questions using PollEverywhere ARS. Students’ perception of the effective interactive teaching using this technology was evaluated statistically using a questionnaire and focus groups. Results It promoted interactivity, focused attention, and provided feedback on comprehension. A total of 95% reported that it increased their participation and found that it clarified their thinking and helped to focus on key points. Another 81.7% mentioned that it increased their motivation to learn. Students regarded it as a useful method for giving real-time feedback, which stimulated their performance and participation. Data from CS students echoed the findings from the dental students. Reports from focus groups demonstrated that this strategy was helpful in focusing students’ attention and in clarifying information. Discussion PollEverywhere encouraged all students to participate during the learning process. This has proven to be an effective tool for improving students’ understanding and critical thinking. Conclusion Students regarded PollEverywhere as an effective teaching innovation that encouraged deeper ongoing retention of information. It was found to be an effective teaching aid in monitoring students’ progress and identifying deficiencies. This is of benefit in a module where interactivity is considered important.

Building professionalism and employability skills: embedding employer engagement within first-year computing modules

This paper outlines a means of improving the employability skills of first-year university students through a closely integrated model of employer engagement within computer science modules. The outlined approach illustrates how employability skills, including communication, teamwork and time management skills, can be contextualised in a manner that directly relates to student learning but can still be linked forward into employment. The paper tests the premise that developing employability skills early within the curriculum will result in improved student engagement and learning within later modules. The paper concludes that embedding employer participation within first-year models can help relate a distant notion of employability into something of more immediate relevance in terms of how students can best approach learning. Further, by enhancing employability skills early within the curriculum, it becomes possible to improve academic attainment within later modules.

Gait Based Gender Recognition Using Sparse Spatio Temporal Features

A gender balanced dataset of 101 pedestrians on a treadmill is presented. Gait is analysed for gender classification using a modification of a framework which has previously proven effective when used in behaviour recognition experiments. Sparse spatio temporal features from the video clips are classified using Support Vector Machines. Tuning parameters are investigated to find an effective feature descriptor for gender separation and an accuracy of 87% is achieved.

Psychometric Comparisons of Benevolent and Corrective Humor across 22 Countries: The Virtue Gap in Humor Goes International

Recently, two forms of virtue-related humor, benevolent and corrective, have been introduced. Benevolent humor treats human weaknesses and wrongdoings benevolently, while corrective humor aims at correcting and bettering them. Twelve marker items for benevolent and corrective humor (the BenCor) were developed, and it was demonstrated that they fill the gap between humor as temperament and virtue. The present study investigates responses to the BenCor from 25 samples in 22 countries (overall N = 7,226). The psychometric properties of the BenCor were found to be sufficient in most of the samples, including internal consistency, unidimensionality, and factorial validity. Importantly, benevolent and corrective humor were clearly established as two positively related, yet distinct dimensions of virtue-related humor. Metric measurement invariance was supported across the 25 samples, and scalar invariance was supported across six age groups (from 18 to 50+ years) and across gender. Comparisons of samples within and between four countries (Malaysia, Switzerland, Turkey, and the UK) showed that the item profiles were more similar within than between countries, though some evidence for regional differences was also found. This study thus supported, for the first time, the suitability of the 12 marker items of benevolent and corrective humor in different countries, enabling a cumulative cross-cultural research and eventually applications of humor aiming at the good.