Paper Info
Title
Towards data-driven estimation of image tag relevance using visually similar and dissimilar folksonomy images.
Abstract
Given that the presence of non-relevant tags in an image folksonomy hampers the effective organization and retrieval of images, this paper discusses a novel technique for estimating the relevance of user-supplied tags with respect to the content of a seed image. Specifically, this paper proposes to compute the relevance of image tags by making use of both visually similar and dissimilar images. That way, compared to tag relevance estimation only using visually similar images, the difference in tag relevance between tags relevant and tags irrelevant with respect to the content of a seed image can be increased at a limited increase in computational cost, thus making it more straightforward to distinguish between them. The latter is confirmed through experimentation with subsets of MIRFLICKR-25000 and MIRFLICKR-1M, showing that tag relevance estimation using both visually similar and dissimilar images allows achieving more effective image tag refinement and tag-based image retrieval than tag relevance estimation only using visually similar images.
Year
DOI
Venue
2012
10.1145/2390876.2390880
SAM@MM
Keywords
Field
DocType
effective image tag refinement,dissimilar image,image folksonomy,similar image,tag relevance,towards data-driven estimation,tag relevance estimation,tag-based image retrieval,image tag relevance,image tag,seed image,relevance estimation,dissimilar folksonomy image,image retrieval
Data-driven,Information retrieval,Computer science,Image retrieval,Folksonomy
Conference
Citations 
PageRank 
References 
0
0.34
16
Authors
3
Name
Order
Citations
PageRank
Sihyoung Lee1715.71
Wesley De Neve252554.41
Yong Man Ro31192125.87