Designing the temporal aspects of the user interface: Views from the coal face

We aim to support user interface designers in capturing, representing and reasoning about temporal information. We have developed a method to support user interface designers in considering how the temporal aspects of software impact the user. Importantly the method is based on a detailed analysis of data from a set of situated interviews that capture the views of practicing user interface designers. This paper discusses the background research and the motivation for the method.

Moving from face-to-face to online classrooms: the reflective university teacher

This study explores the similarities, differences and possible interaction between two small groups of Canadian and Australian university teachers’ face-to-face and online teaching approaches and philosophies. The paper compares their perspectives on teaching face-to-face and online at two comparable Canadian and Australian universities, both of which offer instruction in these two modes. Teaching philosophy data were gathered with the ‘Teaching Perspectives Inventory’ developed by Pratt and Collins at the University of British Columbia, which assessed participants’ teaching approaches and philosophies in terms of their beliefs, intentions and actions in both modalities. The study upon which this paper is based builds upon a well established research partnership of the two authors who have previously explored emerging philosophies of learner centred teaching in distributed classrooms in Canada and Australia.

Teaching philosophy : moving from face-to-face to online classrooms

This article explores the similarities and differences between Canadian and Australian university teachers’ face-to-face and online teaching approaches and philosophies. It presents perspectives on teaching face-to-face and online in two comparable Canadian and Australian universities, both of which offer instruction in these two modes. The key research question was to determine if moving from face-to-face instruction to on-line teaching results in new teaching approaches or in a creative blend of those developed within each teaching modality. Qualitative data were collected using an open-ended survey, which asked participants for their thoughts on their face-to-face (f2f) and online teaching experiences. Quantitative data were collected using the “Teaching Perspectives Inventory,” which assessed participants’ teaching approaches and philosophies in terms of their beliefs, intentions, and actions. The authors’ conclusions address the issue of assisting teachers to successfully make the transition from traditional teacher-centred to newly emerging learner-centred teaching approaches in distributed classrooms.

Adaptive fusion of gait and face for human identification in video

Most work on multi-biometric fusion is based on static fusion rules which cannot respond to the changes of the environment and the individual users. This paper proposes adaptive multi-biometric fusion, which dynamically adjusts the fusion rules to suit the real-time external conditions. As a typical example, the adaptive fusion of gait and face in video is studied. Two factors that may affect the relationship between gait and face in the fusion are considered, i.e., the view angle and the subject-to-camera distance. Together they determine the way gait and face are fused at an arbitrary time. Experimental results show that the adaptive fusion performs significantly better than not only single biometric traits, but also those widely adopted static fusion rules including SUM, PRODUCT, MIN, and MAX.

Year 8 students' understanding of astronomy as a representational issue : insights from a classroom video study

The research described in this paper argues that difficulties of leaming science concepts such as those associated with processes involving the Sun, Moon and Earth, such as day and night, the seasons and phases of the moon, are fundamentally representational in nature. There is a need for learners to use their own representational, cultural and cognitive resources to engage with the subject-specific representational practices of science. From this perspective students need to understand and conceptually integrate different representational modalities or forms in learning science and reasoning in science. The researchers worked with two experienced teachers in planning a teaching sequence in astronomy using a teaching approach that highlight representational issues and options in helping students explore and develop key conceptual understandings. Classroom sequences involving the two teachers were videotaped using a combined focus on the teacher and groups of students. Video analysis software was used to capture the variety of representations used, and sequences of representational negotiation. From a pedagogical perspective the representational approach placed a significant agency in the hands of students which resulted in structured discussions around conceptual problems. Representations were used as tools for reasoning and communication to drive classroom discussions and develop higher levels of understanding in the students. The pre- and post-testing showed significant gains in students thinking from naive to more scientific understandings of astronomy.

Human action recognition based on 3D SIFT and LDA model

How to recognize human action from videos captured by modern cameras efficiently and effectively is a challenge in real applications. Traditional methods which need professional analysts are facing a bottleneck because of their shortcomings. To cope with the disadvantage, methods based on computer vision techniques, without or with only a few human interventions, have been proposed to analyse human actions in videos automatically. This paper provides a method combining the three dimensional Scale Invariant Feature Transform (SIFT) detector and the Latent Dirichlet Allocation (LDA) model for human motion analysis. To represent videos effectively and robustly, we extract the 3D SIFT descriptor around each interest point, which is sampled densely from 3D Space-time video volumes. After obtaining the representation of each video frame, the LDA model is adopted to discover the underlying structure-the categorization of human actions in the collection of videos. Public available standard datasets are used to test our method. The concluding part discusses the research challenges and future directions.

Threshold dynamic time warping for spatial activity recognition

Non-invasive spatial activity recognition is a difficult task, complicated by variation in how the same activities are conducted and furthermore by noise introduced by video tracking procedures. In this paper we propose an algorithm based on dynamic time warping (DTW) as a viable method with which to quantify segmented spatial activity sequences from a video tracking system. DTW is a widely used technique for optimally aligning or warping temporal sequences through minimisation of the distance between their components. The proposed algorithm threshold DTW (TDTW) is capable of accurate spatial sequence distance quantification and is shown using a three class spatial data set to be more robust and accurate than DTW and the discrete hidden markov model (HMM). We also evaluate the application of a band dynamic programming (DP) constraint to TDTW in order to reduce extraneous warping between sequences and to reduce the computation complexity of the approach. Results show that application of a band DP constraint to TDTW improves runtime performance significantly, whilst still maintaining a high precision and recall.

AdaBoost.MRF: boosted Markov random forests and application to multilevel activity recognition

Activity recognition is an important issue in building intelligent monitoring systems. We address the recognition of multilevel activities in this paper via a conditional Markov random field (MRF), known as the dynamic conditional random field (DCRF). Parameter estimation in general MRFs using maximum likelihood is known to be computationally challenging (except for extreme cases), and thus we propose an efficient boosting-based algorithm AdaBoost.MRF for this task. Distinct from most existing work, our algorithm can handle hidden variables (missing labels) and is particularly attractive for smarthouse domains where reliable labels are often sparsely observed. Furthermore, our method works exclusively on trees and thus is guaranteed to converge. We apply the AdaBoost.MRF algorithm to a home video surveillance application and demonstrate its efficacy.

Segmentation of intentional human gestures for sports video annotation

We present results on the recognition of intentional human gestures for video annotation and retrieval. We define a gesture as a particular, repeatable, human movement having a predefined meaning. An obvious application of the work is in sports video annotation where umpire gestures indicate specific events. Our approach is to augment video with data obtained from accelerometers worn as wrist bands by one or more officials. We present the recognition performance using a Hidden Markov Model approach for gesture modeling with both isolated gestures and gestures segmented from a stream.

Hierarchical recognition of intentional human gestures for sports video annotation

We present a novel technique for the recognition of complex human gestures for video annotation using accelerometers and the hidden Markov model. Our extension to the standard hidden Markov model allows us to consider gestures at different levels of abstraction through a hierarchy of hidden states. Accelerometers in the form of wrist bands are attached to humans performing intentional gestures, such as umpires in sports. Video annotation is then performed by populating the video with time stamps indicating significant events, where a particular gesture occurs. The novelty of the technique lies in the development of a probabilistic hierarchical framework for complex gesture recognition and the use of accelerometers to extract gestures and significant events for video annotation.

Learning people movement model from multiple cameras for behaviour recognition

In surveillance systems for monitoring people behaviours, it is important to build systems that can adapt to the signatures of people's tasks and movements in the environment. At the same time, it is important to cope with noisy observations produced by a set of cameras with possibly different characteristics. In previous work, we have implemented a distributed surveillance system designed for complex indoor environments [1]. The system uses the Abstract Hidden Markov mEmory Model (AHMEM) for modelling and specifying complex human behaviours that can take place in the environment. Given a sequence of observations from a set of cameras, the system employs approximate probabilistic inference to compute the likelihood of different possible behaviours in real-time. This paper describes the techniques that can be used to learn the different camera noise models and the human movement models to be used in this system. The system is able to monitor and classify people behaviours as data is being gathered, and we provide classification results showing the system is able to identify behaviours of people from their movement signatures.