We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and semantics of labels. The proposed combines a structure loss semantic in multi-task objective function train fully convolutional neural network. helps generate whose type magnitude are defined target processing filter. considers groups (semantic) labels prevent filtered {fr...

This paper reports on our ongoing work regarding opinion mining from Web-based discussion forums in the realm of the Understanding Advertising (UAd) project. Our approach to opinion mining is to first RDFise discussion forums in SIOC, and in a second phase to interlink the so created data with linked datasets such as DBpedia. We are confident that this should allow a market researcher to formul...

Shared Workspaces are getting more and more popular in helping people collaborate. However, it’s difficult for user to search information across different Shared Workspaces since they are currently islands that are not interlinked. Based on semantic web technologies, SIOC provide ontology and tools to interlink online communities. By using SIOC to develop an explorer for Shared Workspaces, we m...

This paper describes how we extended the SIOC ontology to take into account particular aspects of wikis in order to enable integration capabilities between various wiki systems. In particular, we will overview the proposed extensions and detail a webservice providing SIOC data from any MediaWiki instance, as well as related query examples that show how different wikis, designed as independant d...