We investigate weakly-supervised image parsing, i.e., assigning class labels to image regions by using imagelevel labels only. Existing studies pay main attention to the formulation of the weakly-supervised learning problem, i.e., how to propagate class labels from images to regions given an affinity graph of regions. Notably, however, the affinity graph of regions, which is generally construct...

Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while implicit semantic associations behind highly complex interactions graphs largely unexploited. In this paper, we propose Semantic Graph Convolutional Networks (SGCN) that explores semantics latent semantic-paths graphs. previous wor...

soumission à Episciences Nowadays, there is a growing interest in data mining and information retrieval applications from Knowledge Graphs (KG). However, the latter (KG) suffers several quality problems such as accuracy, completeness, different kinds of errors. In DBpedia, are issues related to quality. Among them, we focus on following: entities classes they do not belong to. For instance, que...

An important task for Homeland Security is the prediction of threat vulnerabilities, such as through the detection of relationships between seemingly disjoint entities. A structure used for this task is a semantic graph, also known as a relational data graph or an attributed relational graph. These graphs encode relationships as typed links between a pair of typed nodes. Indeed, semantic graphs...

We present a graph-matching algorithm for semantic relation assignment. The algorithm is part of an interactive text analysis system. The system automatically extracts pairs of syntactic units from a text and assigns a semantic relation to each pair. This is an incremental learning algorithm, in which previously processed pairs and user feedback guide the process. After each assignment, the sys...

Semantic graphs can be seen as a way of representing and visualizing textual information in more structured, RDF-like graphs. The reader thus obtains an overview of the content, without having to read through the text. In building a compact semantic graph, an important step is grouping similar concepts under the same label and connecting them to external repositories. This is achieved through d...