Tag Relevance Fusion for Social Image Retrieval

TL;DR

This paper introduces tag relevance fusion methods for social image retrieval, improving accuracy by combining multiple relevance measures in various settings, with unsupervised fusion showing comparable effectiveness to supervised approaches.

Contribution

It systematically studies tag relevance fusion in early and late stages, in both supervised and unsupervised settings, demonstrating improved retrieval performance and practical viability.

Findings

Tag relevance fusion improves image retrieval accuracy.

Unsupervised fusion performs comparably to supervised methods.

Fusion methods are effective in real-world social image retrieval.

Abstract

Due to the subjective nature of social tagging, measuring the relevance of social tags with respect to the visual content is crucial for retrieving the increasing amounts of social-networked images. Witnessing the limit of a single measurement of tag relevance, we introduce in this paper tag relevance fusion as an extension to methods for tag relevance estimation. We present a systematic study, covering tag relevance fusion in early and late stages, and in supervised and unsupervised settings. Experiments on a large present-day benchmark set show that tag relevance fusion leads to better image retrieval. Moreover, unsupervised tag relevance fusion is found to be practically as effective as supervised tag relevance fusion, but without the need of any training efforts. This finding suggests the potential of tag relevance fusion for real-world deployment.