Abstract
This paper presents novel dissimilarity space specially designed for interactive multimedia retrieval. By providing queries made of positive and negative examples, the goal consists in learning the positive class distribution. This classification problem is known to be asymmetric, i.e. the negative class does not cluster in the original feature spaces. We introduce here the idea of Query-based Dissimilarity Space (QDS) which enables to cope with the asymmetrical setup by converting it in a more classical 2-class problem. The proposed approach is evaluated on both artificial data and real image database, and compared with state-of-the-art algorithms.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Boldareva, L.V., Hiemstra, D.: Interactive content-based retrieval using pre-computed object-object similarities. In: Enser, P.G.B., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol. 3115, pp. 308–316. Springer, Heidelberg (2004)
Bruno, E., Moenne-Loccoz, N., Marchand-Maillet, S.: Learning user queries in multimodal dissimilarity spaces. In: Detyniecki, M., Jose, J.M., Nürnberger, A., van Rijsbergen, C.J.‘. (eds.) AMR 2005. LNCS, vol. 3877, pp. 168–179. Springer, Heidelberg (2006)
Chang, E.Y., Li, B., Wu, G., Go, K.: Statistical learning for effective visual information retrieval. In: Proceedings of the IEEE International Conference on Image Processing (2003)
Chávez, E., Navarro, G., Baeza-Yates, R., Marroquin, J.L.: Searching in metric spaces. ACM Computing Surveys 33(3), 273–321 (2001)
Chen, Y., Zhou, X.S., Huang, T.S.: One-class svm for learning in image retrieval. In: IEEE International Conference on Image Processing (2001)
Cox, T.F., Cox, M.A.A.: Multidimensional scaling. Chapman & Hall, London (1995)
Heesch, D., Rueger, S.: Nnk networks for content-based image retrieval. In: McDonald, S., Tait, J.I. (eds.) ECIR 2004. LNCS, vol. 2997, pp. 253–266. Springer, Heidelberg (2004)
Pekalska, E., Paclík, P., Duin, R.P.W.: A generalized kernel approach to dissimilarity-based classification. Journal of Machine Learning Research 2, 175–211 (2001)
Smeaton, A.F., Over, P., Kraaij, W.: Trecvid: Evaluating the effectiveness of information retrieval tasks on digital video. In: Proceedings of the ACM MM 2004, New York, NY, pp. 652–655 (2004)
Yan, R., Hauptmann, A., Jin, R.: Negative pseudo-relevance feedback in content-based video retrieval. In: Proceedings of ACM Multimedia (MM 2003), Berkeley, USA (2003)
Zhang, R., Zhang, Z(M.): Stretching bayesian learning in the relevance feedback of image retrieval. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 355–367. Springer, Heidelberg (2004)
Zhou, X.S., Garg, A., Huang, T.S.: A discussion of nonlinear variants of biased discriminants for interactive image retrieval. In: Enser, P.G.B., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol. 3115, pp. 353–364. Springer, Heidelberg (2004)
Zhou, X.S., Huang, T.S.: Small sample learning during multimedia retrieval using biasmap. In: Proceedings of the IEEE Conference on Pattern Recognition and Computer Vision, CVPR 2001, Hawaii, vol. I, pp. 11–17 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bruno, E., Moenne-Loccoz, N., Marchand-Maillet, S. (2006). Asymmetric Learning and Dissimilarity Spaces for Content-Based Retrieval. In: Sundaram, H., Naphade, M., Smith, J.R., Rui, Y. (eds) Image and Video Retrieval. CIVR 2006. Lecture Notes in Computer Science, vol 4071. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11788034_34
Download citation
DOI: https://doi.org/10.1007/11788034_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-36018-6
Online ISBN: 978-3-540-36019-3
eBook Packages: Computer ScienceComputer Science (R0)Springer Nature Proceedings Computer Science
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.