One-shot semantic image segmentation aims to segment the object regions for novel class with only one annotated image. Recent works adopt episodic training strategy mimic expected situation at testing time. However, these existing approaches simulate test conditions too strictly during process, and thus cannot make full use of given label information. Besides, mainly focus on foreground-backgro...

In this paper we propose a new method, called SEMQUERY, for querying information sources whose data are organized according to different schemata. The method is based on the idea of semantic elicitation, namely a process which takes in input the structural part of a query (e.g. the XPath part of an XQuery) and returns an expression in a logical language which represent the meaning of the query ...

Up to now, STI (Science, Technology, Innovation) studies are either rich but small scale (qualitative case studies) or large scale and under-complex – because they generally use only a single dataset like Patstat, Scopus, WoS (Web of Science), OECD STI indicators, etc., and therefore deploying only a few variables – determined by the data available. However, progress in the STI research field (...

While the increasing popularity of folksonomies has lead to a vast quantity of tagged data, resource retrieval in these systems is limited by them being agnostic to the meaning (i.e., semantics) of tags. Our goal is to automatically enrich folksonomy tags (and implicitly the related resources) with formal semantics by associating them to relevant concepts defined in online ontologies. We introd...

Enabling a system to automatically conceptualize and annotate a human-readable table is one way to create interesting semanticweb content. But exactly “how?” is not clear. With conceptualization and annotation in mind, we investigate a semantic-enrichment procedure as a way to turn syntactically observed table layout into semantically coherent ontological concepts, relationships, and constraint...