Sparse representation based action and gesture recognition

In this paper we present a solution to the problem of action and gesture recognition using sparse representations. The dictionary is modelled as a simple concatenation of features computed for each action or gesture class from the training data, and test data is classified by finding sparse representation of the test video features over this dictionary. Our method does not impose any explicit training procedure on the dictionary. We experiment our model with two kinds of features, by projecting (i) Gait Energy Images (GEIs) and (ii) Motion-descriptors, to a lower dimension using Random projection. Experiments have shown 100% recognition rate on standard datasets and are compared to the results obtained with widely used SVM classifier.

Diversity in action : minority group media and social change

My thesis consists of a creative work plus an exegesis. This exegesis uses case study research to investigate three Brisbane-based media organisations and the role they play in encouraging social inclusion and other positive social change for specific disadvantaged and stigmatised minority groups. Bailey, Cammaerts and Carpentier’s theoretical approach to alternative media forms the basis of this research. Bailey et al. (2008, p. 156) view alternative media organisations as having four important roles, two media-centred and two society-centred, which must all be considered to best understand them: • serving their communities • acting as an alternative to mainstream media discourses • promoting and advocating democratisation in the media and through the media in society • functioning as a crossroads in civil society. The first case study, about community radio station 4RPH (Radio for the Print Handicapped), centres on promoting social inclusion for people with a print disability through access to printed materials (primarily mainstream print media) in an audio format. The station also provides important opportunities for members of this group to produce media and, to a lesser extent, provides disability-specific information and discussions. The second case study, about gay print and online magazine Queensland Pride, focuses on promoting social inclusion and combating the discrimination and repression of people who identify as lesbian, gay, bisexual or transgender. Central issues include the representation (including sexualised representation) of a subculture and niche target market, and the impact of commercialisation on this free publication. The third case study, about community radio station 98.9FM, explores the promotion of social inclusion for peoples whose identity, cultures, issues, politics and contributions are often absent or misrepresented in the mainstream media. This radio station provides “a first level of service” (Meadows & van Vuuren, 1998, p. 104) to these people, but also informs and entertains those in the majority society. The findings of this research suggest that there are two key mechanisms that help these media organisations to effect social change: first, strengthening the minority community and serving its needs, and second, fostering connections with the broader society.

Experimenting with affirmative action : the Coate and Loury Model

Coate and Loury (1993) suggest the impact of affirmative action on a negative stereotype is theoretically ambiguous leading to either: a benign equilibrium in which affirmative action eradicates the negative stereotype and leads to equal proportional representation of the two groups; or alternatively a patronising equilibrium in which the stereotype persists. The current paper examines this theoretical ambiguity within the context of a laboratory experiment. Although benign and patronising equilibria are equally plausible in theory, the laboratory experiments easily replicate most features of the benign equilibrium, but diverge from the theoretically predicted patronising equilibrium.

Spatio temporal feature evaluation for action recognition

Spatio-Temporal interest points are the most popular feature representation in the field of action recognition. A variety of methods have been proposed to detect and describe local patches in video with several techniques reporting state of the art performance for action recognition. However, the reported results are obtained under different experimental settings with different datasets, making it difficult to compare the various approaches. As a result of this, we seek to comprehensively evaluate state of the art spatio- temporal features under a common evaluation framework with popular benchmark datasets (KTH, Weizmann) and more challenging datasets such as Hollywood2. The purpose of this work is to provide guidance for researchers, when selecting features for different applications with different environmental conditions. In this work we evaluate four popular descriptors (HOG, HOF, HOG/HOF, HOG3D) using a popular bag of visual features representation, and Support Vector Machines (SVM)for classification. Moreover, we provide an in-depth analysis of local feature descriptors and optimize the codebook sizes for different datasets with different descriptors. In this paper, we demonstrate that motion based features offer better performance than those that rely solely on spatial information, while features that combine both types of data are more consistent across a variety of conditions, but typically require a larger codebook for optimal performance.

Writing the oriental woman : an examination of the representation of Japanese women in contemporary Australian crime fiction

This study considers the challenges in representing women from other cultures in the crime fiction genre. The study is presented in two parts; an exegesis and a creative practice component consisting of a full length crime fiction novel, Batafurai. The exegesis examines the historical period of a section of the novel—post-war Japan—and how the area of research known as Occupation Studies provides an insight into the conditions of women during this period. The exegesis also examines selected postcolonial theory and its exposition of representations of the 'other' as a western construct designed to serve Eurocentric ends. The genre of crime fiction is reviewed, also, to determine how characters purportedly representing Oriental cultures are constricted by established stereotypes. Two case studies are examined to investigate whether these stereotypes are still apparent in contemporary Australian crime fiction. Finally, I discuss my own novel, Batafurai, to review how I represented people of Asian background, and whether my attempts to resist stereotype were successful. My conclusion illustrates how novels written in the crime fiction genre are reliant on strategies that are action-focused, rather than character-based, and thus often use easily recognizable types to quickly establish frameworks for their stories. As a sub-set of popular fiction, crime fiction has a tendency to replicate rather than challenge established stereotypes. Where it does challenge stereotypes, it reflects a territory that popular culture has already visited, such as the 'female', 'black' or 'gay' detective. Crime fiction also has, as one of its central concerns, an interest in examining and reinforcing the notion of societal order. It repeatedly demonstrates that crime either does not pay or should not pay. One of the ways it does this is to contrast what is 'good', known and understood with what is 'bad', unknown, foreign or beyond our normal comprehension. In western culture, the east has traditionally been employed as the site of difference, and has been constantly used as a setting of contrast, excitement or fear. Crime fiction conforms to this pattern, using the east to add a richness and depth to what otherwise might become a 'dry' tale. However, when used in such a way, what is variously eastern, 'other' or Oriental can never be paramount, always falling to secondary side of the binary opposites (good/evil, known/unknown, redeemed/doomed) at work. In an age of globalisation, the challenge for contemporary writers of popular fiction is to be responsive to an audience that demands respect for all cultures. Writers must demonstrate that they are sensitive to such concerns and can skillfully manage the tensions caused by the need to deliver work that operates within the parameters of the genre, and the desire to avoid offence to any cultural or ethnic group. In my work, my strategy to manage these tensions has been to create a back-story for my characters of Asian background, developing them above mere genre types, and to situate them with credibility in time and place through appropriate historical research.

Semi-binary based video features for activity representation

Efficient and effective feature detection and representation is an important consideration when processing videos, and a large number of applications such as motion analysis, 3D scene understanding, tracking etc. depend on this. Amongst several feature description methods, local features are becoming increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational complexity, their performance is still too limited for real world applications. Furthermore, rapid increases in the uptake of mobile devices has increased the demand for algorithms that can run with reduced memory and computational requirements. In this paper we propose a semi binary based feature detectordescriptor based on the BRISK detector, which can detect and represent videos with significantly reduced computational requirements, while achieving comparable performance to the state of the art spatio-temporal feature descriptors. First, the BRISK feature detector is applied on a frame by frame basis to detect interest points, then the detected key points are compared against consecutive frames for significant motion. Key points with significant motion are encoded with the BRISK descriptor in the spatial domain and Motion Boundary Histogram in the temporal domain. This descriptor is not only lightweight but also has lower memory requirements because of the binary nature of the BRISK descriptor, allowing the possibility of applications using hand held devices.We evaluate the combination of detectordescriptor performance in the context of action classification with a standard, popular bag-of-features with SVM framework. Experiments are carried out on two popular datasets with varying complexity and we demonstrate comparable performance with other descriptors with reduced computational complexity.

Supervised latent dirichlet allocation models for efficient activity representation

Local spatio-temporal features with a Bag-of-visual words model is a popular approach used in human action recognition. Bag-of-features methods suffer from several challenges such as extracting appropriate appearance and motion features from videos, converting extracted features appropriate for classification and designing a suitable classification framework. In this paper we address the problem of efficiently representing the extracted features for classification to improve the overall performance. We introduce two generative supervised topic models, maximum entropy discrimination LDA (MedLDA) and class- specific simplex LDA (css-LDA), to encode the raw features suitable for discriminative SVM based classification. Unsupervised LDA models disconnect topic discovery from the classification task, hence yield poor results compared to the baseline Bag-of-words framework. On the other hand supervised LDA techniques learn the topic structure by considering the class labels and improve the recognition accuracy significantly. MedLDA maximizes likelihood and within class margins using max-margin techniques and yields a sparse highly discriminative topic structure; while in css-LDA separate class specific topics are learned instead of common set of topics across the entire dataset. In our representation first topics are learned and then each video is represented as a topic proportion vector, i.e. it can be comparable to a histogram of topics. Finally SVM classification is done on the learned topic proportion vector. We demonstrate the efficiency of the above two representation techniques through the experiments carried out in two popular datasets. Experimental results demonstrate significantly improved performance compared to the baseline Bag-of-features framework which uses kmeans to construct histogram of words from the feature vectors.

Mirror neurons, the representation of word meaning, and the foot of the third left frontal convolution

Previous neuroimaging research has attempted to demonstrate a preferential involvement of the human mirror neuron system (MNS) in the comprehension of effector-related action word (verb) meanings. These studies have assumed that Broca's area (or Brodmann's area 44) is the homologue of a monkey premotor area (F5) containing mouth and hand mirror neurons, and that action word meanings are shared with the mirror system due to a proposed link between speech and gestural communication. In an fMRI experiment, we investigated whether Broca's area shows mirror activity solely for effectors implicated in the MNS. Next, we examined the responses of empirically determined mirror areas during a language perception task comprising effector-specific action words, unrelated words and nonwords. We found overlapping activity for observation and execution of actions with all effectors studied, i.e., including the foot, despite there being no evidence of foot mirror neurons in the monkey or human brain. These "mirror" areas showed equivalent responses for action words, unrelated words and nonwords, with all of these stimuli showing increased responses relative to visual character strings. Our results support alternative explanations attributing mirror activity in Broca's area to covert verbalisation or hierarchical linearisation, and provide no evidence that the MNS makes a preferential contribution to comprehending action word meanings.

Multiple instance dictionary learning for activity representation

This paper presents an effective feature representation method in the context of activity recognition. Efficient and effective feature representation plays a crucial role not only in activity recognition, but also in a wide range of applications such as motion analysis, tracking, 3D scene understanding etc. In the context of activity recognition, local features are increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational requirements, their performance is still limited for real world applications due to a lack of contextual information and models not being tailored to specific activities. We propose a new activity representation framework to address the shortcomings of the popular, but simple bag-of-words approach. In our framework, first multiple instance SVM (mi-SVM) is used to identify positive features for each action category and the k-means algorithm is used to generate a codebook. Then locality-constrained linear coding is used to encode the features into the generated codebook, followed by spatio-temporal pyramid pooling to convey the spatio-temporal statistics. Finally, an SVM is used to classify the videos. Experiments carried out on two popular datasets with varying complexity demonstrate significant performance improvement over the base-line bag-of-feature method.

Human action recognition from video sequences

This PhD research has proposed new machine learning techniques to improve human action recognition based on local features. Several novel video representation and classification techniques have been proposed to increase the performance with lower computational complexity. The major contributions are the construction of new feature representation techniques, based on advanced machine learning techniques such as multiple instance dictionary learning, Latent Dirichlet Allocation (LDA) and Sparse coding. A Binary-tree based classification technique was also proposed to deal with large amounts of action categories. These techniques are not only improving the classification accuracy with constrained computational resources but are also robust to challenging environmental conditions. These developed techniques can be easily extended to a wide range of video applications to provide near real-time performance.

Affirmative action and effort choice: An experimental investigation

We study the effect of affirmative action on effort in an experiment conducted in high schools in socioeconomically disadvantaged areas in Queensland, Australia. All participating schools have a large representation of indigenous Australians, a population group that is frequently targeted by affirmative action. Our participants perform a simple real-effort task in a competitive setting. Those ranked in the top third receive a high piece-rate payment and all the others receive a low payment. We introduce affirmative action by providing the lowest (bottom third) performers with a positive handicap increasing their chances to achieve the high payment target. Our findings show that the policy increases effort of those that it aims to favour, without discouraging effort of those who are indirectly penalized by affirmative action.

Hamilton’s theory of turns and a new geometrical representation for polarization optics

Hamilton’s theory of turns for the group SU(2) is exploited to develop a new geometrical representation for polarization optics. While pure polarization states are represented by points on the Poincaré sphere, linear intensity preserving optical systems are represented by great circle arcs on another sphere. Composition of systems, and their action on polarization states, are both reduced to geometrical operations. Several synthesis problems, especially in relation to the Pancharatnam-Berry-Aharonov-Anandan geometrical phase, are clarified with the new representation. The general relation between the geometrical phase, and the solid angle on the Poincaré sphere, is established.

Effective action and adiabatic expansions for the 1-D and 2-D hubbard models at half-filling

We analyze here the occurrence of antiferromagnetic (AFM) correlations in the half-filled Hubbard model in one and two space dimensions using a natural fermionic representation of the model and a newly proposed way of implementing the half-filling constraint. We find that our way of implementing the constraint is capable of enforcing it exactly already at the lowest levels of approximation. We discuss how to develop a systematic adiabatic expansion for the model and how Berry's phase contributions arise quite naturally from the adiabatic expansion. At low temperatures and in the continuum limit the model gets mapped onto an O(3) nonlinear sigma model (NLsigma). A topological, Wess-Zumino term is present in the effective action of the ID NLsigma as expected, while no topological terms are present in 2D. Some specific difficulties that arise in connection with the implementation of an adiabatic expansion scheme within a thermodynamic context are also discussed, and we hint at possible solutions.

Human action recognition using a fast learning fully complex-valued classifier

In this paper, we use optical flow based complex-valued features extracted from video sequences to recognize human actions. The optical flow features between two image planes can be appropriately represented in the Complex plane. Therefore, we argue that motion information that is used to model the human actions should be represented as complex-valued features and propose a fast learning fully complex-valued neural classifier to solve the action recognition task. The classifier, termed as, ``fast learning fully complex-valued neural (FLFCN) classifier'' is a single hidden layer fully complex-valued neural network. The neurons in the hidden layer employ the fully complex-valued activation function of the type of a hyperbolic secant function. The parameters of the hidden layer are chosen randomly and the output weights are estimated as the minimum norm least square solution to a set of linear equations. The results indicate the superior performance of FLFCN classifier in recognizing the actions compared to real-valued support vector machines and other existing results in the literature. Complex valued representation of 2D motion and orthogonal decision boundaries boost the classification performance of FLFCN classifier. (c) 2012 Elsevier B.V. All rights reserved.