Visitor understanding of museum practices and processes

The study was conducted over 3 years and explored beyond what visitors to museum exhibitions learnt from written labels, to what they learnt and knew about the museum as an institution, its staff and their knowledge and understanding of the subliminal messages of exhibitions. The site used as the Victorian historical mansion, Werribee Park. Visitors to the 1880s Costume Exhibition were surveyed.

Clustering based multi-label classification for image annotation and retrieval

This paper presents a novel multi-label classification framework for domains with large numbers of labels. Automatic image annotation is such a domain, as the available semantic concepts are typically hundreds. The proposed framework comprises an initial clustering phase that breaks the original training set into several disjoint clusters of data. It then trains a multi-label classifier from the data of each cluster. Given a new test instance, the framework first finds the nearest cluster and then applies the corresponding model. Empirical results using two clustering algorithms, four multi-label classification algorithms and three image annotation data sets suggest that the proposed approach can improve the performance and reduce the training time of standard multi-label classification algorithms, particularly in the case of large number of labels.

Interpretations of corruption in intercultural bargaining

There is a fine line in business negotiations between being perceived as corrupt and having proper engagement with the natural tension and excitement of the business bargaining process. Combining literature review and experiential observation we provide a framework that will assist global business managers to more successfully negotiate cross-cultural business transactions. We identify some archetypal underpinnings of bargaining in a business context and question the established perceptions of corruption in intercultural business dealings. We conclude that different cultural systems produce variations of negotiating behaviour that need to be judged with a deeper local knowledge to avoid simply transferring inappropriate labels.

Consumer awareness and self-reported behaviours related to salt consumption in Australia

Australians are eating far more salt than is good for health. In May 2007, the Australian Division of World Action on Salt and Health (AWASH) launched a campaign to reduce population salt intake. A consumer survey was commissioned to quantify baseline aspects of awareness and behaviour related to salt and health amongst Australians. A total of 1084 individuals aged 14 years or over were surveyed by ACA Research using an established consumer panel. Participants were selected to include people of each sex, within different age bands, from major metropolitan and other areas of all Australian states and territories. Participants were invited via email to complete a brief questionnaire online. Two-thirds knew that salt was bad for health but only 14% knew the recommended maximum daily intake. Seventy percent correctly identified that most dietary salt comes from processed foods but only a quarter regularly checked food labels for salt content. Even fewer reported their food purchases were influenced by the salt level indicated (21%). The survey showed a moderate understanding of how salt effects health but there was little evidence of action to reduce salt intake. Consumer education will be one part of the effort necessary to reduce salt intake in Australia and will require government investment in a targeted campaign to achieve improvements in knowledge and behaviours.

Personal identity : moving beyond essence

Education's ancient and profoundly important pursuit to 'know thyself', is often realised through engaging with the question 'who am I?' In order to the identify who in this search, it is argued in this paper that personal identity should be understood to be embedded in the purposes one has for one's life through how one relates, and is therefore spiritual. This spiritual quality of personal identity is therefore existential in character - not essential.

However, often when children respond to this question 'who am I?', they rely upon socially constructed categories and labels such as religious, feminine, cool, punk and the like. The application of such labelling assumes that meaningfulness lies in their essence; that is, they identify what is. This can become most problematic when individuals accept and apply such essentialist labelling to themselves, because such a process can only answer 'what am I?' and not the educationally more important question of 'who am I?' This paper therefore challenges the inadequacy of such an approach and offers a conceptualisation of personal identity which is spiritually embedded in a purpose for one's life.

Cellular localization of water soluble, allergenic proteins in rye-grass (Lolium perenne) pollen using monoclonal and specific IgE antibodies with immunogold probes

A postembedding method has been developed for localizing water soluble allergens in rye-grass pollen. This uses dry fixation in glutaraldehyde vapour, followed by 2,2-dimethoxypropane, prior to a 100% ethanol series leading into embedment in LR Gold. This has allowed the attachment of specific monoclonal antibodies to the allergen, which are themselves probed with specific immunogold labels to the antibodies. Wall and cytoplasmic sites have been identified, representing an improvement of fixation and localization of allergens over previous studies employing polyclonal, broad spectrum antibodies.

Rye-grass allergens are labelled in mature pollen grains in the exine (tectum, nexine and central chamber), and in the electron opaque areas of the cytoplasm, especially mitochondria. The allergens are absent from the intine, polysaccharide (P) particles, amyloplasts, Golgi bodies and endoplasmic reticulum. IgE antibodies derived from humans allergic to rye-grass pollen, bind to similar sites in the cytoplasm but only to the outer surface of the pollen grain wall. This method now provides a valuable tool for further developmental studies on the pollen grains, in order to establish the site/s of synthesis of the allergens.

Robust recognition and segmentation of human actions using HMMs with missing observations

This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation. Based on this framework, a model is trained to automatically segment and classify an activity sequence into its constituent subactions during inferencing. This is achieved by introducing action labels into the observation vector and setting these labels as missing data during inferencing, thus forcing the system to infer the probability of each action label. Additionally, missing data provides recognition-level support for occlusions and imperfect silhouette segmentation, permitting the use of a fast (real-time) pose estimation that delegates the burden of handling undetected limbs onto the action recognition system. Findings show that the use of missing data to segment activities is an accurate and elegant approach. Furthermore, action recognition can be accurate even when almost half of the pose feature data is missing due to occlusions, since not all of the pose data is important all of the time.

Using interaction signatures to find and label chairs and floors

The use of interaction signatures to recognize objects without considering the object's physical structure is discussed. Without object recognition, smart homes cannot make full use of video cameras because vision systems cannot provide object-related context to the human activities monitored. One important advantage of interaction signatures is that people frequently and repeatedly interact with household objects, so the system can build evidence for object locations and labels.

Calibration of audio-video sensors for multi-modal event indexing

This paper addresses the coordinated use of video and audio cues to capture and index surveillance events with multimodal labels. The focus of this paper is the development of a joint-sensor calibration technique that uses audio-visual observations to improve the calibration process. One significant feature of this approach is the ability to continuously check and update the calibration status of the sensor suite, making it resilient to independent drift in the individual sensors. We present scenarios in which this system is used to enhance surveillance.

Face recognition using kernel ridge regression

In this paper, we present novel ridge regression (RR) and kernel ridge regression (KRR) techniques for multivariate labels and apply the methods to the problem of face recognition. Motivated by the fact that the regular simplex vertices are separate points with highest degree of symmetry, we choose such vertices as the targets for the distinct individuals in recognition and apply RR or KRR to map the training face images into a face subspace where the training images from each individual will locate near their individual targets. We identify the new face image by mapping it into this face subspace and comparing its distance to all individual targets. An efficient cross-validation algorithm is also provided for selecting the regularization and kernel parameters. Experiments were conducted on two face databases and the results demonstrate that the proposed algorithm significantly outperforms the three popular linear face recognition techniques (Eigenfaces, Fisherfaces and Laplacianfaces) and also performs comparably with the recently developed Orthogonal Laplacianfaces with the advantage of computational speed. Experimental results also demonstrate that KRR outperforms RR as expected since KRR can utilize the nonlinear structure of the face images. Although we concentrate on face recognition in this paper, the proposed method is general and may be applied for general multi-category classification problems.

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.

Combining image regions and human activity for indirect object recognition in indoor wide-angle views

Traditional methods of object recognition are reliant on shape and so are very difficult to apply in cluttered, wideangle and low-detail views such as surveillance scenes. To address this, a method of indirect object recognition is proposed, where human activity is used to infer both the location and identity of objects. No shape analysis is necessary. The concept is dubbed 'interaction signatures', since the premise is that a human will interact with objects in ways characteristic of the function of that object - for example, a person sits in a chair and drinks from a cup. The human-centred approach means that recognition is possible in low-detail views and is largely invariant to the shape of objects within the same functional class. This paper implements a Bayesian network for classifying region patches with object labels, building upon our previous work in automatically segmenting and recognising a human's interactions with the objects. Experiments show that interaction signatures can successfully find and label objects in low-detail views and are equally effective at recognising test objects that differ markedly in appearance from the training objects.

Human action segmentation via controlled use of missing data in HMMs

Segmentation of individual actions from a stream of human motion is an open problem in computer vision. This paper approaches the problem of segmenting higher-level activities into their component sub-actions using Hidden Markov Models modified to handle missing data in the observation vector. By controlling the use of missing data, action labels can be inferred from the observation vector during inferencing, thus performing segmentation and classification simultaneously. The approach is able to segment both prominent and subtle actions, even when subtle actions are grouped together. The advantage of this method over sliding windows and Viterbi state sequence interrogation is that segmentation is performed as a trainable task, and the temporal relationship between actions is encoded in the model and used as evidence for action labelling.

Learning discriminative sequence models from partially labelled data for activity recognition

Recognising daily activity patterns of people from low-level sensory data is an important problem. Traditional approaches typically rely on generative models such as the hidden Markov models and training on fully labelled data. While activity data can be readily acquired from pervasive sensors, e.g. in smart environments, providing manual labels to support fully supervised learning is often expensive. In this paper, we propose a new approach based on partially-supervised training of discriminative sequence models such as the conditional random field (CRF) and the maximum entropy Markov model (MEMM). We show that the approach can reduce labelling effort, and at the same time, provides us with the flexibility and accuracy of the discriminative framework. Our experimental results in the video surveillance domain illustrate that these models can perform better than their generative counterpart (i.e. the partially hidden Markov model), even when a substantial amount of labels are unavailable.

Hierarchical semi-markov conditional random fields for recursive sequential data

Inspired by the hierarchical hidden Markov models (HHMM), we present the hierarchical semi-Markov conditional random field (HSCRF), a generalisation of embedded undirected Markov chains to model complex hierarchical, nested Markov processes. It is parameterised in a discriminative framework and has polynomial time algorithms for learning and inference. Importantly, we develop efficient algorithms for learning and constrained inference in a partially-supervised setting, which is important issue in practice where labels can only be obtained sparsely. We demonstrate the HSCRF in two applications: (i) recognising human activities of daily living (ADLs) from indoor surveillance cameras, and (ii) noun-phrase chunking. We show that the HSCRF is capable of learning rich hierarchical models with reasonable accuracy in both fully and partially observed data cases.