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.

Racism, Representation and Photography

Representation of Aborigines by Aborigines and non -Aborigines; articles by Andrew Dewdney, Mervyn Biship, Alana Harris, Sandy Edwards, Rea Saunders, Ricky Maynard , Brenda Croft, Ruth Braunstein, Michael Riley, Huw Davies, Penny Taylor, Darlene McKenzie, Kurt Brereton and Eric Michaels, annotated separately.

λ-orthogonal pericyclic macromolecular photoligation

A photochemical strategy enabling λ-orthogonal reactions is introduced to construct macromolecular architectures and to encode variable functional groups with site-selective precision into a single molecule by the choice of wavelength. λ-Orthogonal pericyclic reactions proceed independently of one another by the selection of functional groups that absorb light of specific wavelengths. The power of the new concept is shown by a one-pot reaction of equimolar quantities of maleimide with two polymers carrying different maleimide-reactive endgroups, that is, a photoactive diene (photoenol) and a nitrile imine (tetrazole). Under selective irradiation at λ=310–350 nm, any maleimide (or activated ene) end-capped compound reacts exclusively with the photoenol functional polymer. After complete conversion of the photoenol, subsequent irradiation at λ=270–310 nm activates the reaction of the tetrazole group with functional enes. The versatility of the approach is shown by λ-orthogonal click reactions of complex maleimides, functional enes, and polymers to the central polymer scaffold.

Representation and authenticity of historic landscapes in Australia and China

Histories of past communities are embedded in landscapes around the world but many are suffering from material change or neglect of their fabric. This study was aimed at discovering and representing the authentic intangible experience of two historic landscapes for conservation purposes. A 2500 year old site in Yangzhou, China and a 2000 year old site on St Helena Island in Moreton Bay were found to be managed under two culturally different regimes of authenticity. This research has contributed to challenging the notion that there is only one way to conserve authenticity in historic landscapes of the Asia Pacific.

Deriving word association networks from text corpora

This article presents and evaluates a model to automatically derive word association networks from text corpora. Two aspects were evaluated: To what degree can corpus-based word association networks (CANs) approximate human word association networks with respect to (1) their ability to quantitatively predict word associations and (2) their structural network characteristics. Word association networks are the basis of the human mental lexicon. However, extracting such networks from human subjects is laborious, time consuming and thus necessarily limited in relation to the breadth of human vocabulary. Automatic derivation of word associations from text corpora would address these limitations. In both evaluations corpus-based processing provided vector representations for words. These representations were then employed to derive CANs using two measures: (1) the well known cosine metric, which is a symmetric measure, and (2) a new asymmetric measure computed from orthogonal vector projections. For both evaluations, the full set of 4068 free association networks (FANs) from the University of South Florida word association norms were used as baseline human data. Two corpus based models were benchmarked for comparison: a latent topic model and latent semantic analysis (LSA). We observed that CANs constructed using the asymmetric measure were slightly less effective than the topic model in quantitatively predicting free associates, and slightly better than LSA. The structural networks analysis revealed that CANs do approximate the FANs to an encouraging degree.

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.

Populations of models, experimental designs and coverage of parameter space by Latin Hypercube and Orthogonal Sampling

In this paper we have used simulations to make a conjecture about the coverage of a t-dimensional subspace of a d-dimensional parameter space of size n when performing k trials of Latin Hypercube sampling. This takes the form P(k,n,d,t) = 1 - e^(-k/n^(t-1)). We suggest that this coverage formula is independent of d and this allows us to make connections between building Populations of Models and Experimental Designs. We also show that Orthogonal sampling is superior to Latin Hypercube sampling in terms of allowing a more uniform coverage of the t-dimensional subspace at the sub-block size level. These ideas have particular relevance when attempting to perform uncertainty quantification and sensitivity analyses.

What is voice? Issues of identity and representation in the framing of reviews

There is a well-founded ethical concern in the present regarding the question Ήow can we include everybody's voice equally in the framing of reviews?' This paper is a response to the complexities that inhere in that question. It is not about Review of Educational Research (RER) as a specific site but about the systems of reasoning that construct the opening question about reviews and that suggest possible answers, including the response: 'What is voice?'

Leveraging Lean Production Philosophy for Rationalising a Non-Linear Representation of Construction Specifications

This paper presents an approach, based on Lean production philosophy, for rationalising the processes involved in the production of specification documents for construction projects. Current construction literature erroneously depicts the process for the creation of construction specifications as a linear one. This traditional understanding of the specification process often culminates in process-wastes. On the contrary, the evidence suggests that though generalised, the activities involved in producing specification documents are nonlinear. Drawing on the outcome of participant observation, this paper presents an optimised approach for representing construction specifications. Consequently, the actors typically involved in producing specification documents are identified, the processes suitable for automation are highlighted and the central role of tacit knowledge is integrated into a conceptual template of construction specifications. By applying the transformation, flow, value (TFV) theory of Lean production the paper argues that value creation can be realised by eliminating the wastes associated with the traditional preparation of specification documents with a view to integrating specifications in digital models such as Building Information Models (BIM). Therefore, the paper presents an approach for rationalising the TFV theory as a method for optimising current approaches for generating construction specifications based on a revised specification writing model.

Difference covering arrays and pseudo-orthogonal Latin squares

A pair of Latin squares, A and B, of order n, is said to be pseudo-orthogonal if each symbol in A is paired with every symbol in B precisely once, except for one symbol with which it is paired twice and one symbol with which it is not paired at all. A set of t Latin squares, of order n, are said to be mutually pseudo-orthogonal if they are pairwise pseudo-orthogonal. A special class of pseudo-orthogonal Latin squares are the mutually nearly orthogonal Latin squares (MNOLS) first discussed in 2002, with general constructions given in 2007. In this paper we develop row complete MNOLS from difference covering arrays. We will use this connection to settle the spectrum question for sets of 3 mutually pseudo-orthogonal Latin squares of even order, for all but the order 146.

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.