Abstract
With the development of Internet, large scale of images are published and searched in the Web. How to find those related images has been the research focus in the field of image processing. And one of the important problems is how to efficiently rank the image search results. In this paper, we present a learning to rank model named as RLM-AVF (Visual Features based Ranking Learning Model), which is based on the large margin method, under the framework of structural SVM(Support Vector Machine). Firstly we incorporate the visual features into the ranking model together with related textual features. Then an optimal problem of learning the ranking parameters based on the large margin method is schemed. Finally the cutting plane algorithm is introduced to efficiently solve the optimal problem. This paper compared the performance of RLM-AVF with the textual ranking methods using the well-known learning to rank algorithms and reranking methods. The experimental result shows that RLM-AVF performs considerable search efficiency than the other algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Joachims, T.: Optimizing search engines using clickthrough data. In: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, pp. 133–142 (2002)
Cao, Z., Qin, T., Tsai, M.-F.: Learning to rank: from pairwise approach to listwise approach. In: Proceedings of the 24th International Conference on Machine Learning (ICML), New York, NY, USA, pp. 129–136 (2007)
Jing, Y., Baluja, S.: Visualrank: Applying pagerank to large-scale image search. IEEE Transactions on PAMI 30(11), 1877–1890 (2008)
Tian, X., Yang, L., Wang, J.: Bayesian video search reranking. In: Proceedings of the ACM International Conference on Multimedia, MM (2008)
Tsochantaridis, I., Joachims, T., Hofmann, T.: Large Margin Methods for Structured and Interdependent Output Variables. Journal of Machine Learning Research (JMLR) 6, 1453–1484 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, X., Yu, J., Li, J. (2011). RLM-AVF: Towards Visual Features Based Ranking Learning Model for Image Search. In: Zhu, M. (eds) Electrical Engineering and Control. Lecture Notes in Electrical Engineering, vol 98. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21765-4_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-21765-4_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21764-7
Online ISBN: 978-3-642-21765-4
eBook Packages: EngineeringEngineering (R0)