Abstract
Given that millions of images are uploaded to the social web in a single day, how to effectively retrieve such increasing amounts of unstructured data becomes crucial. While current social platforms find images on the base of user-contributed tags, the tags are known to be subjective and noisy, and consequently put the effectiveness of social image retrieval into question. Different from existing work which focuses on analyzing individual sources of information such as textual and visual separately, in this paper we propose to fuse the heterogeneous information. We investigate the state of the art weighting methods within a linear fusion framework. Image retrieval experiments on a present day benchmark with 46 visual concept queries show encouraging results. Compared to the best search results obtained by a single source of information, the Uniform method and the Coordinate Ascent method obtain relative performance gain of 3.9% and 5.7% in terms of mean average precision. This work provides some practical guidelines for fusing multiple sources of information for improving social image retrieval.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.-T.: NUS-WIDE: A Real-World Web Image Database from National University of Singapore. In: ACM International Conference on Image and Video Retrieval (2009)
Cilibrasi, R., Vitanyi, P.: The Google Similarity Distance. IEEE Trans. on Knowl. and Data Eng. 19(3), 370–383 (2007)
Freund, Y., Iyer, R., Schapire, R., Singer, Y.: An efficient boosting algorithm for combining preferences. J. Mach. Learn. Res. 4, 933–969 (2003)
Li, X., Snoek, C., Worring, M.: Learning social tag relevance by neighbor voting. IEEE Trans. Multimedia 11(7), 1310–1322 (2009)
Li, X., Snoek, C., Worring, M.: Unsupervised multi-feature tag relevance learning for social image retrieval. In: ACM International Conference on Image and Video Retrieval (2010)
Li, X., Snoek, C., Worring, M., Smeulders, A.: Harvesting social images for bi-concept search. IEEE Trans. Multimedia 14(4), 1091–1104 (2012)
Liu, D., Hua, X.-S., Yang, L., Wang, M., Zhang, H.-J.: Tag ranking. In: International Conference on World Wide Web (2009)
Matusiak, K.: Towards user-centered indexing in digital image collections. OCLC Sys. and Services 22(4), 283–298 (2006)
Metzler, D., Croft, B.: Linear feature-based models for information retrieval. Inf. Retr. 10(3), 257–274 (2007)
Sun, A., Bhowmick, S.: Quantifying tag representativeness of visual content of social Images. In: ACM International Conference on Multimedia (2010)
Wilkins, P.: An investigation into weighted data fusion for content-based multimedia information retrieval. PhD Thesis, Dublin City University (2009)
Xu, J., Li, H.: AdaRank: a boosting algorithm for information retrieval. In: ACM SIGIR (2007)
Zhu, S., Wang, G., Ngo, C.-W., Jiang, Y.-G.: On the sampling of web images for learning visual concept classifiers. In: ACM International Conference on Image and Video Retrieval (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, X. (2012). Fusing Heterogeneous Information for Social Image Retrieval. In: Bao, Z., et al. Web-Age Information Management. WAIM 2012. Lecture Notes in Computer Science, vol 7419. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33050-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-33050-6_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33049-0
Online ISBN: 978-3-642-33050-6
eBook Packages: Computer ScienceComputer Science (R0)