A Crowdsourcing Procedure for the Discovery of Non-Obvious Attributes of Social Image
This addresses the need for better image understanding in social contexts, but it is incremental as it builds on existing crowdsourcing methods for a specific domain.
The paper tackles the problem of discovering non-obvious attributes in social images, which are overlooked in conventional research, by introducing a crowdsourcing procedure; the result is demonstrated through an analysis showing added value compared to user tags in a fashion domain example.
Research on mid-level image representations has conventionally concentrated relatively obvious attributes and overlooked non-obvious attributes, i.e., characteristics that are not readily observable when images are viewed independently of their context or function. Non-obvious attributes are not necessarily easily nameable, but nonetheless they play a systematic role in people`s interpretation of images. Clusters of related non-obvious attributes, called interpretation dimensions, emerge when people are asked to compare images, and provide important insight on aspects of social images that are considered relevant. In contrast to aesthetic or affective approaches to image analysis, non-obvious attributes are not related to the personal perspective of the viewer. Instead, they encode a conventional understanding of the world, which is tacit, rather than explicitly expressed. This paper introduces a procedure for discovering non-obvious attributes using crowdsourcing. We discuss this procedure using a concrete example of a crowdsourcing task on Amazon Mechanical Turk carried out in the domain of fashion. An analysis comparing discovered non-obvious attributes with user tags demonstrated the added value delivered by our procedure.