Multimedia Reasoning with f-SHIN

Knowledge-Driven Multimedia Information Extraction and Ontology Evolution

Stoilos

et al. 2011

Self Cite

Abstract. Multimedia documents constitute extremely rich information resources, whose efficacious management is intertwined with the effective capturing of the underlying semantics. The conveyed meaning may span along multiple levels and relates to search and retrieval tasks, much as to the very extraction and interpretation of content descriptions. In this chapter we consider the formal representation of multimedia semantics that pertain to media and domain specific descriptions, for the purpose of supporting both the extraction and subsequent semantic management of such descriptions. To this end, firstly, we present first an overview of existing approaches to the representation of multimedia content and discuss open issues. Subsequently, we present the ontology infrastructure developed in the context of the BOEMIE project tailored towards the formal representation of multimedia content. Concluding, we present what can non-standard formal representation technologies, such as fuzzy knowledge representation formalisms bring to multimedia document processing and management.

Section: Fuzzy Extensions Of Owl and Dlsmentioning

confidence: 99%

Semantic Representation of Multimedia Content

Dalakleidi

Knowledge-Driven Multimedia Information Extraction and Ontology Evolution

Stoilos

et al. 2011

Self Cite

“…However, in a significant share of the proposed DLs based approaches, image interpretation translates to augmenting the explicitly asserted data, made available via image analysis, with additional ones that are derived through the application of inference over the known only objects and relationships. Indicative approaches include amongst others the works presented in [3,4,5,6,7]. The underlying assumption is that the analysis provided descriptions correspond to all relevant information.…”

Section: Open Vs Closed World Semanticsmentioning

confidence: 99%

Trends and Issues in Description Logics Frameworks for Image Interpretation

Artificial Intelligence: Theories, Models and Applications

Kompatsiaris

2010

Abstract. Description Logics have recently attracted significant interest as the underlying formalism for conceptual modelling in the context of high-level image interpretation. Differences in the formulation of image interpretation semantics have resulted in varying configurations with respect to the adopted modelling paradigm, the utilised form of reasoning, and the way imprecision is managed. In this paper, we examine the relevant literature, outlining the corresponding strengths and weaknesses, and argue that although coming up with a complete solution is hard to envisage any time soon, there are a number of key considerations that may serve as guidelines towards this direction.

“…Fuzzy DLs have been proposed in [24] for the purpose for semantic multimedia retrieval; the fuzzy annotations however are assumed to be available. Fuzzy DLs have been proposed recently in [25] and [26] for enhancing machine learning based extracted image annotations and document classification respectively; however, neither approach addresses the problem of resolving semantic inconsistencies in the initially extracted descriptions.…”

Section: Relevant Workmentioning

confidence: 99%

Using Fuzzy DLs to Enhance Semantic Image Analysis

Kompatsiaris

Strintzis

2008

Semantic Multimedia

Abstract. Research in image analysis has reached a point where detectors can be learned in a generic fashion for a significant number of conceptual entities. The obtained performance however exhibits versatile behaviour, reflecting implications over the training set selection, similarities in visual manifestations of distinct conceptual entities, and appearance variations of the conceptual entities. In this paper, we investigate the use of formal semantics in order to benefit from the logical associations between the conceptual entities, and thereby alleviate part of the challenges involved in extracting semantic descriptions. More specifically, a fuzzy DL based reasoning framework is proposed for the extraction of enhanced image descriptions based on an initial set of graded annotations, generated through generic image analysis techniques. Under the proposed reasoning framework, the initial descriptions are integrated and further enriched at a semantic level, while additionally inconsistencies emanating from conflicting descriptions are resolved. Experimentation in the domain of outdoor images has shown very promising results, demonstrating the added value in terms of accuracy and completeness of the resulting content descriptions.