The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over last few years, almost existing models follow same training paradigm: they treat both object predicate classification as single-label problem, ground-truths are one-hot target labels. However, this prevalent paradigm ov...

a r t i c l e i n f o Social media have increasingly become popular platforms for information dissemination. Recently, companies have attempted to take advantage of social advertising to deliver their advertisements to appropriate customers. The success of message propagation in social media depends greatly on the content relevance and the closeness of social relationships. In this paper, consi...

In this paper, we consider the modelling of trust relationships in distributed systems based on a formal mathematical structure. We discuss different forms of trust. In particular, we address the base level authentication trust at the lower layer with a hierarchy of trust relationships at a higher level. Then we define and discuss trust direction and symmetric characteristics of trust for colla...

Most work on XML access control considers XML nodes as the smallest protection unit. This paper shows the limitation of this approach and introduces an XML access control mechanism that protects inter-node relationships. Our approach provides a finer granularity of access control than the node-based approaches(i.e., more expressive). Moreover, our approach helps achieve the “need-to-know” secur...

A human’s ability to diagnose errors, gather data, and generate features in order to build better models is largely untapped. We hypothesize that analyzing results from multiple models can help people diagnose errors by understanding relationships among data, features, and algorithms. These relationships might otherwise be masked by the bias inherent to any individual model. We demonstrate this...

Contrary to the traditional Bag-of-Words approach, we consider the Graph-of-Words (GoW) model in which each document is represented by a graph that encodes relationships between the different terms. Based on this formulation, the importance of a term is determined by weighting the corresponding node in the document, collection and label graphs, using node centrality criteria. We also introduce ...

Several recent reports have challenged the idea that transposable elements (TEs) are mainly 'selfish' or 'junk' DNA with little importance for host evolution. It has been proposed that TEs have the potential to provide host genomes with the ability to enhance their own evolution. They might also be a major source of genetic diversity, allowing response to environmental changes. Because the rela...

Problem statement: In order to facilitate XML query processing, labeling schemes are used to determine the structural relationships between XML nodes. However, labeling schemes have to reliable the existing nodes or recalculate the label values when a new node is inserted into the XML document during XML update process. EXEL as a labeling scheme is able to remove relabeling for existing nodes d...

Recent years have seen a growing number of graph-based semisupervised learning methods. While the literature currently contains several of these methods, their relationships with one another and with other graph-based data analysis algorithms remain unclear. In this paper, we present a unified view of graph-based semi-supervised learning. Our framework unifies three important and seemingly unre...

Community structure is vital to discover the important structures and potential property of complex networks. In recent years, the increasing quality of local community detection approaches has become a hot spot in the study of complex network due to the advantages of linear time complexity and applicable for large-scale networks. However, there are many shortcomings in these methods such as in...