Relational Features Research Articles

Interactive activity recognition using pose-based spatio–temporal relation features and four-level Pachinko Allocation Model

In this paper, we go beyond the problem of recognizing video-based human interactive activities. We propose a novel approach that permits to deeply understand complex person-person activities based on the knowledge coming from human pose analysis. The joint coordinates of interactive objects are first located by an efficient human pose estimation algorithm. The relation features consisting of the intra and inter-person features of joint distance and angle, are suggested to use for describing the relationships between body components of the individual persons and the interacting two participants in the spatio-temporal dimension. These features are then provided to the codebook construction process, in which two types of codeword are generated corresponding to distance and angle features. In order to explain the relationships between poses, a flexible hierarchical topic model constructed by four layers is proposed using the Pachinko Allocation Model. The model is able to represent the full correlation between the relation features of body components as codewords, the interactive poselets as subtopics, and the interactive activities as super topics. Discrimination of complex activities presenting similar postures is further obtained by the proposed model. We validate our interaction recognition method on two practical data sets, the BIT-Interaction data set and the UT-Interaction data set. The experimental results demonstrate that the proposed approach outperforms recent interaction recognition approaches in terms of recognition accuracy.

On learning web information extraction rules with TANGO

The research on Enterprise Systems Integration focuses on proposals to support business processes by re-using existing systems. Wrappers help re-use web applications that provide a user interface only. They emulate a human user who interacts with them and extracts the information of interest in a structured format. In this article, we present TANGO, which is our proposal to learn rules to extract information from semi-structured web documents with high precision and recall, which is a must in the context of Enterprise Systems Integration. It relies on an open catalogue of features that helps map the input documents into a knowledge base in which every DOM node is represented by means of HTML, DOM, CSS, relational, and user-defined features. Then a procedure with many variation points is used to learn extraction rules from that knowledge base; the variation points include heuristics that range from how to select a condition to how to simplify the resulting rules. We also provide a systematic method to help re-configure our proposal. Our exhaustive experimentation proves that it beats others regarding effectiveness and is efficient enough for practical purposes. Our proposal was devised to be as configurable as possible, which helps adapt it to particular web sites and evolve it when necessary.

Student Perceptions of Autonomy-Supportive Instructional Interactions in the Middle Grades

ABSTRACTAutonomy support in classrooms is believed to coordinate students' inner motivational resources in ways that enhance student engagement (e.g., Jang, Kim, & Reeve, 2012). Yet, to our knowledge, no study has investigated student-generated interpretations of the motivational significance of their teachers' autonomy-supportive practices. Interpretations gathered from students' responses to video clips of their own teacher were studied with a diverse sample of students (N = 59, 50.8% male, 64.4% African American) in six urban classrooms from fourth- to eighth-grade class sections. Through this method of cued video response, we explore whether or not students experience the significance of autonomy-supportive instructional events or interactions as motivational theory predicts. Our results suggest that consideration of the social and relational features of the classrooms within which teachers enact autonomy support may identify influential contextual factors relevant to how and why autonomy support is linked to positive outcomes.

Dance performance evaluation using hidden Markov models

AbstractWe present in this paper a hidden Markov model‐based system for real‐time gesture recognition and performance evaluation. The system decodes performed gestures and outputs at the end of a recognized gesture, a likelihood value that is transformed into a score. This score is used to evaluate a performance comparing to a reference one. For the learning procedure, a set of relational features has been extracted from high‐precision motion capture system and used to train hidden Markov models. At runtime, a low‐cost sensor (Microsoft Kinect) is used to capture a learner's movements. An intermediate step of model adaptation was hence requested to allow recognizing gestures captured by this low‐cost sensor. We present one application of this gesture evaluation system in the context of traditional dance basics learning. The estimation of the log‐likelihood allows giving a feedback to the learner as a score related to his performance. Copyright © 2016 John Wiley & Sons, Ltd.

Discriminative Relational Representation Learning for RGB-D Action Recognition.

This paper addresses the problem of recognizing human actions from RGB-D videos. A discriminative relational feature learning method is proposed for fusing heterogeneous RGB and depth modalities, and classifying the actions in RGB-D sequences. Our method factorizes the feature matrix of each modality, and enforces the same semantics for them in order to learn shared features from multimodal data. This allows us to capture the complex correlations between the two modalities. To improve the discriminative power of the relational features, we introduce a hinge loss to measure the classification accuracy when the features are employed for classification. This essentially performs supervised factorization, and learns discriminative features that are optimized for classification. We formulate the recognition task within a maximum margin framework, and solve the formulation using a coordinate descent algorithm. The proposed method is extensively evaluated on two public RGB-D action data sets. We demonstrate that the proposed method can learn extremely low-dimensional features with superior discriminative power, and outperforms the state-of-the-art methods. It also achieves high performance when one modality is missing in testing or training.

Attachment insecurity and perceived importance of relational features

Chronic attachment insecurity can affect the outlook people have on relationships. This research examines how attachment insecurity relates to perceived importance of various features in a romantic relationship (e.g., intimacy, independence). Consistent with predictions, the results from Studies 1–3 ( N1 = 53, N2 = 226, N3 = 196) revealed that greater attachment anxiety was associated with ranking intimacy higher in importance and independence lower, whereas attachment avoidance was associated with ranking independence higher, intimacy, and trust lower. Study 4 ( N4 = 175) further showed that insecure participants recognized that some of their priorities are unique to themselves and not shared by others. Additionally, they did not perceive their current relationships as having more of the relational features they prioritized. Insecure individuals thus have unique relational priorities, which may direct their romantic judgments and decisions.

Transductive hyperspectral image classification: toward integrating spectral and relational features via an iterative ensemble system

Remotely sensed hyperspectral image classification is a very challenging task due to the spatial correlation of the spectral signature and the high cost of true sample labeling. In light of this, the collective inference paradigm allows us to manage the spatial correlation between spectral responses of neighboring pixels, as interacting pixels are labeled simultaneously. The transductive inference paradigm allows us to reduce the inference error for the given set of unlabeled data, as sparsely labeled pixels are learned by accounting for both labeled and unlabeled information. In this paper, both these paradigms contribute to the definition of a spectral-relational classification methodology for imagery data. We propose a novel algorithm to assign a class to each pixel of a sparsely labeled hyperspectral image. It integrates the spectral information and the spatial correlation through an ensemble system. For every pixel of a hyperspectral image, spatial neighborhoods are constructed and used to build application-specific relational features. Classification is performed with an ensemble comprising a classifier learned by considering the available spectral information (associated with the pixel) and the classifiers learned by considering the extracted spatio-relational information (associated with the spatial neighborhoods). The more reliable labels predicted by the ensemble are fed back to the labeled part of the image. Experimental results highlight the importance of the spectral-relational strategy for the accurate transductive classification of hyperspectral images and they validate the proposed algorithm.

Folie à deux: Shared or “infected” madness? About a case report

The shared madness or Folie à deux was described in France in the nineteenth century by Charles Lasage and Pierre Falret, as a condition where a person (the primary) builds a delusional system, sharing it with another (the secondary), who must be very close to the first affected, becoming delirious with the same subject. Several theories attempt to explain the phenomenon that challenges theories of personality structures, rooted in relational and/or environmental features of psychosis. Theoretically, there are many attempts to classify this psychotic experien in some manuals they distinguish various types of partners: the simultaneous psychosis, where the two people start to became delirious at once; imposed psychosis, in which the disorder arises first with one, then going on to “healthy” individual and symptomatology disappears after being separated; and communicated psychosis, where the first transmitted the psychotic experience to the second, and he or she develops his or her own delusion not interrupted even while separated. Other classifications about shared madness not only between two people, but three, and four, even a whole family show us how complicated the delirium systems can become. In our paper, we will discuss the different theories explaining this rare psychiatric condition based on a case about two brothers of 35 and 37, who live together with the rest of the family, and also come together to the same mental health center, although with different psychiatrists.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Social networking sites and low-income teenagers: between opportunity and inequality

ABSTRACTRecent studies on social networking sites (SNSs) reveal that users’ social background is not a significant predictor of participation in this type of social media. The broad user bases of Facebook and other social media platforms also appear to suggest that social background no longer affects access to SNSs. A small number of studies even claim that in the participatory web environment, social content is more likely to be created by non-elites, such as lower-income people or racial minorities [Blank, G. (2013). Who creates content? Stratification and content creation on the Internet. Information, Communication & Society, 16(4), 590–612]. Nevertheless, engagement with SNSs also reproduces inequalities, for example via class- and ethnic-based ‘self-segregation’ [boyd, d. (2012). White flight in networked publics? How race and class shaped American teen engagement with MySpace and Facebook. In L. Nakamura & P. A. Chow-White (Eds.), Race after the internet (pp. 203–222). New York, NY: Routledge]. Drawing on a large-scale survey (N = 2327) and a set of 56 interviews with Italian teenagers, the current paper explores the persistent influence of socio-economic background and cultural capital in adolescents’ use of SNSs. The research findings show that, although structural variables inevitably influence their participation in social media, teenagers from ‘lower-income’ families are more enthusiastic about the communication and relational features of these sites. In contrast, their peers from ‘elite’ families focus on the capital-enhancing opportunities offered by SNSs and display a critical stance that leads them to limit their social activities on these platforms. Overall, the results suggest that SNSs are not exempt from digital inequalities, but nonetheless provide novel opportunities to lower-income teenagers.

The academic achievement of socioeconomically disadvantaged immigrant adolescents: a social capital perspective

A sizable body of literature reports that social capital, derived from relational resources embedded in micro social contexts, is crucial for student achievement. This study aimed to examine whether this applies as well to socioeconomically disadvantaged immigrant adolescents in the US. In so doing, the study first identified the types of relational features that were strongly associated with immigrant adolescents’ academic achievement, before exploring how high- and low-achieving immigrant adolescents coming from similarly socioeconomically disadvantaged backgrounds differed in terms of these relational features. To this end, the study used the dataset of the Children of Immigrants Longitudinal Study (CILS). There was a significantly positive association found between academic achievement and a number of positive characteristics of social relationships with friends and teachers. In addition, a significant disparity in these relational features was found between high and low achievers among the socioeconomically disadvantaged. The findings illuminate the salience of peer contexts and of interpersonal trust in shaping immigrant adolescents’ educational outcomes in a way that transcends socioeconomic boundaries. It is pertinent for educators and policy-makers to empower immigrant youth as independent agents capable of generating academically relevant social capital on their own outside their families and ethnic communities.

The Roles of Website Characteristics and Social Network Communities in Developing Customer E-loyalty in the Online Travel Industry

Internet and social network communities have become the essential channel for people looking for tourism information and online purchases or reservations. The academic community strive to better understand which factors influence online satisfaction and loyalty in the online travel industry. Many antecedents to e-satisfaction have been identified in the literature, namely functional and relational website characteristics. While many studies have assessed the influence of functional characteristics on esatisfaction such as usability and security, few research focused on the influence of social and human dimensions of the interface, called relational characteristics, especially in the online travel context. In fact, the relational features have been studied as a part of the optimization of the website interface and not from the logic of loyalty and brand-customer relationships. Moreover, there is a call in the literature for more research on the impact of individual engagement on social networks sites on loyalty generation. Thus, the objective of this study is to investigate how online attributes under the control of the cyber-merchant (website functional and relational attributes) and social networking sites where the firm has far less control, foster e-saisfaction and e-loyalty in the online travel industry. A self-administered survey was used and data were collected from university students who had shopped from an online travel company in the past year. By using SEM modelling, results show that usability, quality of support, and security/privacy positively impact e-satisfaction while e-satisfaction influences both cognitive and affective loyalty. Further analyses showed that personalization and online social network communities significantly influence both cognitive and affective loyalty while perceived social presence has a negative impact on cognitive loyalty. By understanding website drivers of online satisfaction and loyalty, this study contribute to help online travel companies develop strategies positioned to build long-term relationships, and thereby gain a competitive advantage.

Research on manufacturing text classification based on improved genetic algorithm

According to the features of texts, a text classification model is proposed. Base on this model, an optimized objective function is designed by utilizing the occurrence frequency of each feature in each category. According to the relation matrix oftext resource and features, an improved genetic algorithm is adopted for solution with integral matrix crossover, transposition and recombination of entire population. At last the sample date of manufacturing text information from professional resources database system is taken as an example to illustrate the proposed model and solution for feature dimension reduction and text classification. The crossover and mutation probabilities of algorithm are compared vertically and horizontally to determine a group of better parameters. The experiment results show that the proposed method is fast and effective.

Shaping relations: Exploiting relational features for visuospatial priming.

Although relational reasoning has been described as a process at the heart of human cognition, the exact character of relational representations remains an open debate. Symbolic-connectionist models of relational cognition suggest that relations are structured representations, but that they are ultimately grounded in feature sets; thus, they predict that activating those features can affect the trajectory of the relational reasoning process. The present work points out that such models do not necessarily specify what those features are though, and endeavors to show that spatial information is likely a part of it. To this end, it presents 2 experiments that used visuospatial priming to affect the course of relational reasoning. The first is a relational category-learning experiment in which this type of priming was shown to affect which spatial relation was learned when multiple were possible. The second used crossmapping analogy problems, paired with this same type of priming, to show that visuospatial cues can make participants more likely to map analogs based on relational roles, even with short presentation times. (PsycINFO Database Record

Informational injustice with respect to change and negative workplace emotions

Purpose– The purpose of this paper is to examine the hitherto unexplored relationship between employees’ perceptions of informational injustice with respect to change and their negative workplace emotions, as well as how this relationship might be mitigated by structural and relational features of the organizational context.Design/methodology/approach– The paper draws on quantitative data collected through the 2011 Workplace Employment Relations Survey. The hypotheses are tested with ordered probit analysis using random effects.Findings– The findings show that informational injustice enhances the development of negative workplace emotions, yet this effect is attenuated at higher levels of job influence, reward interdependence, trust, and organizational commitment.Research limitations/implications– The findings contribute by identifying several contingencies that attenuate the harmful effect of informational injustice with respect to change on negative workplace emotions. The limitations of the study include the lack of data on change-specific outcomes and the reliance on the same respondents to assess the focal variables.Practical implications– The study suggests that organizations facing the challenge of sharing complete information about internal changes can counter the employee stress that comes with limited information provision by creating appropriate internal environments.Originality/value– The study adds to research on organizational change by providing a better understanding of an unexplored driver of negative workplace emotions (i.e. informational injustice with respect to change) and explicating when such informational injustice is more or less likely to enhance these emotions.

Choix et strategies d’alliance : chroniques presque contrefactuelles des réseaux parentaux dans le patriciat vénitien, XVIII siècle

En este trabajo emplearemos un instrumento metodológico que nos ayudará a entender cómo la elección y el establecimiento de alianzas podría estar determinado por condicionantes políticos y estratégicos. Centrándonos en la República de Venecia durante el siglo XVIII, estudiaremos las características, las actitudes, los impulsos y los intereses que se esconden tras las alianzas establecidas por la aristocracia; unas marcadas por un claro componente político y otras por el deseo de adquirirlo. Tomando como referencia a sus matrimonios, exploraremos el significado de sus alianzas utilizando las herramientas propias del Social Network Analysis. Sus opciones matrimoniales y las redes que se derivan de ellas se compararán con las que nacerían de otras posibles opciones matrimoniales. El instrumento de análisis que proponemos se centra sobre la actividad desplegada por la familia Manin, gracias a la cual podremos comparar los beneficios de las hipotéticas relaciones que establecería con estas o aquellas familias. Esta investigación tiene por objeto ayudarnos a comprender la complejidad de las relaciones sociales y familiares de la aristocracia veneciana, y también, advertir de la posibilidad de ofrecer nuevos enfoques a la historia social y política.http://dx.doi.org/10.15304/ohm.24.2822

Hybrid Deep Learning for Face Verification.

This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine (RBM) model for face verification. A key contribution of this work is to learn high-level relational visual features with rich identity similarity information. The deep ConvNets in our model start by extracting local relational visual features from two face images in comparison, which are further processed through multiple layers to extract high-level and global relational features. To keep enough discriminative information, we use the last hidden layer neuron activations of the ConvNet as features for face verification instead of those of the output layer. To characterize face similarities from different aspects, we concatenate the features extracted from different face region pairs by different deep ConvNets. The resulting high-dimensional relational features are classified by an RBM for face verification. After pre-training each ConvNet and the RBM separately, the entire hybrid network is jointly optimized to further improve the accuracy. Various aspects of the ConvNet structures, relational features, and face verification classifiers are investigated. Our model achieves the state-of-the-art face verification performance on the challenging LFW dataset under both the unrestricted protocol and the setting when outside data is allowed to be used for training.

Shared Decision Making with Aboriginal Women Facing Health Decisions: A qualitative study identifying needs, supports, and barriers

Shared decision making (SDM) may narrow health equity gaps by engaging clients with their health care providers in decision making; little is known about SDM interventions with Aboriginal people. This study describes the health decision-making experiences of Aboriginal women by identifying decision needs, supports, and barriers. An interpretive descriptive qualitative study was conducted from January to June 2013 with an advisory group using a mutually developed ethical framework, participatory research principles, and postcolonial theory. Aboriginal women at Minwaashin Lodge were interviewed in semi-structured interviews and transcripts were coded using thematic analysis. Participants were 13 women between 20 and 70 years of age, and of Inuit, Métis, or First Nations descent. SDM needs and supports are represented by themes focused on relational features of SDM, and presented in a Medicine Wheel framework. Findings indicate that to be relevant for Aboriginal women, SDM tools and approaches may need to be adapted, and participatory approaches must be used.

The CMS Condition Database System

The Condition Database plays a key role in the CMS computing infrastructure. The complexity of the detector and the variety of the sub-systems involved are setting tight requirements for handling the Conditions. In the last two years the collaboration has put a substantial effort in the re-design of the Condition Database system, with the aim at improving the scalability and the operability for the data taking starting in 2015. The re-design has focused on simplifying the architecture, using the lessons learned during the operation of the Run I data-taking period (20092013). In the new system the relational features of the database schema are mainly exploited to handle the metadata (Tag and Interval of Validity), allowing for a limited and controlled set of queries. The bulk condition data (Payloads) are stored as unstructured binary data, allowing the storage in a single table with a common layout for all of the condition data types. In this paper, we describe the full architecture of the system, including the services implemented for uploading payloads and the tools for browsing the database. Furthermore, the implementation choices for the core software will be discussed.

Relational underpinnings and professionality – a case study of a teacher’s practices involving students with experiences of school failure

Relational features of the educational environment, such as positive teacher-student relationships, are important for students’ academic success. This case study explores the relational practices of a teacher who negotiates educational relationships with students who have a history of school failure. ‘Gunilla’, a secondary school teacher working in the Swedish ‘Introduction Programme’ (for students who have not been accepted in national upper secondary school programmes) and identified as a successful instructor for students who have failed at school, was selected for the study. The data consists of two semi-structured interviews eliciting the informant’s stories of practice and the researcher’s contextual observation. Results show how relational practices create an emotionally safe school climate. In the initial phase of the teacher-student relationship the main purpose of the activities is to establish trust and repair the students’ self-image so that they can view themselves as successful learners. This requires professional closeness and the teacher distancing herself from a stereotypical teaching role, in order to display humaneness and empathy. The findings contribute to understanding how relational features in the everyday school context help students to learn and how school psychologists can be part of this endeavour.

A novel relational regularization feature selection method for joint regression and classification in AD diagnosis.

In this paper, we focus on joint regression and classification for Alzheimer's disease diagnosis and propose a new feature selection method by embedding the relational information inherent in the observations into a sparse multi-task learning framework. Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response-response relation, and sample-sample relation), for preserving three kinds of the similarity, such as for the features, the response variables, and the samples, respectively. To conduct feature selection, we first formulate the objective function by imposing these three relational characteristics along with an ℓ2,1-norm regularization term, and further propose a computationally efficient algorithm to optimize the proposed objective function. With the dimension-reduced data, we train two support vector regression models to predict the clinical scores of ADAS-Cog and MMSE, respectively, and also a support vector classification model to determine the clinical label. We conducted extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to validate the effectiveness of the proposed method. Our experimental results showed the efficacy of the proposed method in enhancing the performances of both clinical scores prediction and disease status identification, compared to the state-of-the-art methods.