An open source library to parse and analyze online collaborative knowledge-building portals

With the success of collaborative knowledge-building portals, such as Wikipedia, Stack Overflow, Quora, and GitHub, a class of researchers is driven towards understanding the dynamics of knowledge building on these portals. Even though collaborative knowledge building portals are known to be better than expert-driven knowledge repositories, limited research has been performed to understand the knowledge building dynamics in the former. This is mainly due to two reasons; first, unavailability of the standard data representation format, second, lack of proper tools and libraries to analyze the knowledge building dynamics.We describe Knowledge Data Analysis and Processing Platform (KDAP), a programming toolkit that is easy to use and provides high-level operations for analysis of knowledge data. We propose Knowledge Markup Language (Knol-ML), a generic representation format for the data of collaborative knowledge building portals. KDAP can process the massive data of crowdsourced portals like Wikipedia and Stack Overflow efficiently. As a part of this toolkit, a data-dump of various collaborative knowledge building portals is published in Knol-ML format. The combination of Knol-ML and the proposed open-source library will help the knowledge building community to perform benchmark analysis.Link of the repository: Verma et al. (2020)Video Tutorial: Verma et al. (2020)Supplementary Material: Verma et al. (2020)

An Open Source Toolkit to Parse and Analyze Online Crowdsourced Portals

With the success of crowdsourced portals, such as Wikipedia, Stack Overflow, Quora, and GitHub, a class of researchers is driven towards understanding the dynamics of knowledge building on these portals. Even though collaborative knowledge building portals are known to be better than expert-driven knowledge repositories, limited research has been performed to understand the knowledge building dynamics in the former. This is mainly due to two reasons; first, unavailability of the standard data representation format, second, lack of proper tools and libraries to analyze the knowledge building dynamics. We describe Knowledge Data Analysis and Processing Platform (KDAP), a programming toolkit that is easy to use and provides high-level operations for analysis of knowledge data. We propose Knowledge Markup Language (Knol-ML), a generic representation format for the data of collaborative knowledge building portals. KDAP can process the massive data of crowdsourced portals like Wikipedia and Stack Overflow efficiently. As a part of this toolkit, a data-dump of various collaborative knowledge building portals is published in Knol-ML format. The combination of Knol-ML and the proposed open-source library will help the knowledge building community to perform benchmark analysis.

A Novel Graph Representation for Skeleton-based Action Recognition

Graph convolutional networks (GCNs) have been proven to be effective for processing structured data, so that it can effectively capture the features of related nodes and improve the performance of model. More attention is paid to employing GCN in Skeleton-Based action recognition. But there are some challenges with the existing methods based on GCNs. First, the consistency of temporal and spatial features is ignored due to extracting features node by node and frame by frame. We design a generic representation of skeleton sequences for action recognition and propose a novel model called Temporal Graph Networks (TGN), which can obtain spatiotemporal features simultaneously. Secondly, the adjacency matrix of graph describing the relation of joints are mostly depended on the physical connection between joints. We propose a multi-scale graph strategy to appropriately describe the relations between joints in skeleton graph, which adopts a full-scale graph, part-scale graph and core-scale graph to capture the local features of each joint and the contour features of important joints. Extensive experiments are conducted on two large datasets including NTU RGB+D and Kinetics Skeleton. And the experiments results show that TGN with our graph strategy outperforms other state-of-the-art methods.

Multi Scale Temporal Graph Networks for Skeleton-Based Action Recognition

Graph convolutional networks (GCNs) can effectively capture the features of related nodes and improve the performance of model. More attention is paid to employing GCN in Skeleton-Based action recognition. But existing methods based on GCNs have two problems. First, the consistency of temporal and spatial features is ignored for extracting features node by node and frame by frame. To obtain spatiotemporal features simultaneously, we design a generic representation of skeleton sequences for action recognition and propose a novel model called Temporal Graph Networks (TGN). Secondly, the adjacency matrix of graph describing the relation of joints are mostly depended on the physical connection between joints. To appropriate describe the relations between joints in skeleton graph, we propose a multi-scale graph strategy, adopting a full-scale graph, part-scale graph and core-scale graph to capture the local features of each joint and the contour features of important joints. Experiments were carried out on two large datasets and results show that TGN with our graph strategy outperforms state-of-the-art methods.

Structured (De)composable Representations Trained with Neural Networks

This paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composable representations from input images and discrete labels. The obtained representations are based on distance estimates between the distributions given by the class label and those given by contextual information, which are modeled as environments. We prove that the representations have a clear structure allowing decomposing the representation into factors that represent classes and environments. We evaluate our novel technique on classification and retrieval tasks involving different modalities (visual and language data). In various experiments, we show how the representations can be compressed and how different hyperparameters impact performance.

De l’interprétation systémique du projet de réhabiliter un bâtiment

The target of retrofitting project only cannot be to retrofit a building. It must also modify the building integrating the new constraints of sustainable development, the energy model transition and climate change. Thus, for several years, the environment of retrofitting projects become more complex, and for reaching the highest levels of energy and environmental performance during the rehabilitation of an existing building, it is necessary to consider the complexity of the retrofitting action.In this context, a project can be viewed as a system of actions in order to convert or refurbish the building system. This interpretation is based on concepts of the systemic approach and on a generic representation with a combination having presided at the project invention.The structural and functional approaches provide a generic representation of a distanced and global view of the complexity of the retrofitting project, which as a system evolves along a path combining anticipation, caesura and virtualization.In this paper, the complex environment of the retrofitting project is presented. Different concepts of the systemic approach used to deal with the complexity of the retrofitting project are described. A chronicle of project allows to elaborate a generic representation of project. Finally, this representation is complemented by elements of systemic modeling for differently interpreting the retrofitting project.

Roma populations and health inequalities: a new perspective

Purpose The purpose of this paper is to explore the emergence of “Roma health and wellbeing” as a focus of attention in European research and in policy and the possible detrimental consequences of action founded on a generic representation of “Roma health.” Design/methodology/approach Based on discussions with and research conducted by scholars who work directly with Roma communities across European regions from a wide range of academic disciplines it suggests how future research might inform: a more nuanced understanding of the causes of poor health and wellbeing among diverse Roma populations and; actions that may have greater potential to improve the health and wellbeing among these populations. Findings In summary, the authors promote three types of research: first critical analyses that unpick the implications of current and past representations of “Roma” and “Roma health.” Second, applied participatory research that meaningfully involves people from specific self-defined Roma populations to identify important issues for their health and wellbeing. Third, learning about processes that might impact on the health and wellbeing of Roma populations from research with other populations in similarly excluded situations. Originality/value The authors provide a multidisciplinary perspective to inform research that does not perpetuate further alienation and prejudice, but promotes urgent action to redress the social and health injustices experienced by diverse Roma populations across Europe.