We discuss two kinds of semantics relevant to Computer Vision (CV) systems - Visual Semantics and Lexical Semantics. While visual semantics focus on how humans build concepts when using vision to perceive a target reality, lexical semantics focus on how humans build concepts of the same target reality through the use of language. The lack of coincidence between visual and lexical semantics, in turn, has a major impact on CV systems in the form of the Semantic Gap Problem (SGP). The paper, while extensively exemplifying the lack of coincidence as above, introduces a general, domain-agnostic methodology to enforce alignment between visual and lexical semantics.

In Visual Semantics we study how humans build mental representations, i.e., concepts , of what they visually perceive. We call such concepts, substance concepts. In this paper we provide a theory and an algorithm which learns substance concepts which correspond to the concepts, that we call classification concepts , that in Lexical Semantics are used to encode word meanings. The theory and algorithm are based on three main contributions: (i) substance concepts are modeled as visual objects , namely sequences of similar frames, as perceived in multiple encounters ; (ii) substance concepts are organized into a visual subsumption hierarchy based on the notions of Genus and Differentia that resemble the notions that, in Lexical Semantics, allow to construct hierarchies of classification concepts; (iii) the human feedback is exploited not to name objects, as it has been the case so far, but, rather, to align the hierarchy of substance concepts with that of classification concepts. The learning algorithm is implemented for the base case of a hierarchy of depth two. The experiments, though preliminary, show that the algorithm manages to acquire the notions of Genus and Differentia with reasonable accuracy, this despite seeing a small number of examples and receiving supervision on a fraction of them.

We present a knowledge-rich methodology for disambiguating Wikipedia categories with WordNet synsets and using this semantic information to restructure a taxonomy automatically generated from the Wikipedia system of categories. We evaluate against a manual gold standard and show that both category disambiguation and taxonomy restructuring perform with high accuracy. Besides, we assess these methods on automatically generated datasets and show that we are able to effectively enrich WordNet with a large number of instances from Wikipedia. Our approach produces an integrated resource, thus bringing together the fine-grained classification of instances in Wikipedia and a well-structured top-level taxonomy from WordNet.