(Un)Tagged Social Image Retrieval

Author(s): Xirong Li, Cees G.M. Snoek and Marcel Worring

Pp: 111-129 (19)

* (Excluding Mailing and Handling)

Abstract

Social image retrieval is increasingly important for managing and accessing the rapidly growing social-tagged images. In this chapter, we address social image retrieval from two directions which tackle the subjectiveness and the incompleteness of social tagging, respectively. To make subjective social tagging objective, we introduce a simple and effective neighbor voting algorithm to estimate the relevance of a tag with respect to the visual content it is describing. To build a concept index for untagged or incompletely tagged images, we study a new learning scenario where concept detectors are trained with negative examples created by social tagging, rather than by traditional expert labeling. Empirical studies on realistic subsets of Flickr data demonstrate the potential of the proposed algorithms for searching (un)tagged social images.

Keywords: Image retrieval, social tagging, machine tagging, tag relevance learning, concept detection, negative examples, neighbor voting, concept index, expert labeling, untagged