Image Tagging

Domain analysis is useful for examination of individual spheres of intellectual activity, both academic and otherwise, and has been used in the knowledge organization (KO) literature to explore specific communities and uses, including web pornography (Beaudoin and Ménard 2015), virtual online worlds (Sköld, Olle 2015), gourmet
cooking (Hartel 2010), healthy eating (McTavish 2015), art studies (Ørom 2003), the Knowledge Organization journal (Guimarães et al.
2013), and domain analysis itself (Smiraglia 2015). The results of domain analyses are useful for the development of controlled vocabularies, taxonomies, ontologies, metadata schemas, and other systems for the documentation, description, and discovery of resources, as well as for knowledge discovery in general (Smiraglia 2015; Hjørland 2017). This research describes a methodology for the elucidation of knowledge organization systems (KOS) currently in use on image websites that document graffiti, graffiti art, and street art around the world.

Automatic image tagging is one of the most important research
topics in multimedia. How to achieve accurate image tagging to
bridge the semantic gap between images’ content and users’ semantic understanding has been widely studied in the last decade. One common approach is to convert image tagging to a multi-task learning problem. However, most existing methods ignore tag correlations in the learning process. In this paper, we show the importance of tag correlations in conducting multi-task learning. We formulate image tagging as a multioutput
regression problem accounting for tag correlations, which are captured by the covariance matrix of the regression coefficients and the noise across all tags respectively. The combination of multi-output regression with tag correlation analysis takes advantage of the latent dependencies among tags to overcome limitations of existing work. Extensive experiments have been conducted on two benchmark datasets, and the results confirm that our approach outperforms the state-of-the-art methods.