ABSTRACT
The tags on social media websites such as Flickr are frequently imprecise and incomplete, thus there is still a gap between these tags and the actual content of the images. This paper proposes a social image ``retagging'' scheme that aims at assigning images with better content descriptors. The refining process is formulated as an optimization framework based on the consistency between ``visual similarity'' and ``semantic similarity'' in social images. An effective iterative bound optimization algorithm is applied to learn the optimal tag assignment. In addition, as many tags are intrinsically not closely-related to the visual content of the images, we employ a knowledge-based method to differentiate visual content related from unrelated tags and then constrain the tagging vocabulary of our automatic algorithm within the content related tags. Experimental results on a Flickr image collection demonstrate the effectiveness of this approach.
- D. Liu, X. S. Hua, L. J. Yang, M. Wang and H. J. Zhang. Tag Ranking. In Proceeding of ACM International World Wide Web Conference, 2009. Google ScholarDigital Library
- C. Fellbaum. Wordnet: An Electronic Lexical Database. Bradford Books, 1998.Google ScholarCross Ref
- C. Wang, F. Jing, L. Zhang and H. J. Zhang. Content-Based Image Annotation Refinement. In Proceeding of IEEE International Conference on Computer Vision and Pattern Recognition, 2007.Google ScholarCross Ref
- D. Lin. Using Syntatic Dependency as a Local Context to Resolve Word Sense Ambiguity. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics, 1997. Google ScholarDigital Library
- Y. Liu, R. Jin and L. Yang. Semi-supervised Multi-label Learning by Constrained Non-Negative Matrix Factorization. In Proceedings of the 21st National Conference on Artificial Intelligence, 2006. Google ScholarDigital Library
- D. Liu, M. Wang, L. Yang, X.-S. Hua and H. J. Zhang. Tag Quality Improvement for Social Images. In International Conference on Multimedia & Expo, 2009. Google ScholarDigital Library
Index Terms
- Retagging social images based on visual and semantic consistency
Recommendations
Image retagging
MM '10: Proceedings of the 18th ACM international conference on MultimediaOnline social media repositories such as Flickr and Zooomr allow users to manually annotate their images with freely-chosen tags, which are then used as indexing keywords to facilitate image search and other applications. However, these tags are ...
Image Retagging Using Collaborative Tag Propagation
Photo sharing websites such as Flickr host a massive amount of social images with user-provided tags. However, these tags are often imprecise and incomplete, which essentially limits tag-based image indexing and related applications. To tackle this ...
Quantifying tag representativeness of visual content of social images
MM '10: Proceedings of the 18th ACM international conference on MultimediaSocial tags describe images from many aspects including the visual content observable from the images, the context and usage of images, user opinions and others. Not all tags are therefore useful for image search and are appropriate for tag ...
Comments