Abstract
With the development of multimedia, the amount of unstructured data of multimedia is increasing, especially for the tourism. Meanwhile, it is one of the key issue to analysis large-scale unstructured data, which helps us to find the hidden relevance between redundant and different data. How to retrieve efficiently, and recommend accurately for cross-media retrieval is more and more important. This paper proposes a new data mode for cross-media retrieval - unstructured data compatible model, short for UDC model. The UDC model is constructed by its own metadata. All metadata are organized by a certain hierarchical relationship. Every metadata consists of three layers: the feature layer, the semantic layer and the compatibility layer. Furthermore, this paper presents retrieval and recommendation algorithms based on UDC model. The experiment results demonstrate that the retrieval engine based on UDC mode can be more effective for cross-media retrieval and recommendation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Foote, J.T.: Content-based retrieval of music and audio, multimedia storage and archiving system II. Proc of Spie 3229, 138–147 (1997)
Saul, L.K., Weinberger, K.Q., Fei, S., et al.: Spectral methods for dimensionality reduction. Semisupervised Learn. 2006, 1041–1048 (2006)
Wang, X.J., Zhang, L., Li, X., et al.: Annotating images by mining image search results. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1919–1932 (2008)
Wang, J.Z., Geman, D., Luo, J., et al.: Real-world image annotation and retrieval: an introduction to the special section. IEEE Trans. Softw. Eng. 30(11), 1873–1876 (2008)
Tao, H.U., Gang-Shan, W.U., Ren, T.W., et al.: Ontology-based cross-media retrieval technique. Comput. Eng. 35(8), 266–268 (2009)
Zhang, H., Zhuang, Y., Wu, F.: Cross-modal correlation learning for clustering on image-audio dataset. In: International Conference on Multimedia 2007, Augsburg, Germany, pp. 273–276, September 2007
Wu, F., Zhuang, Y.: Cross media analysis and retrieval on the web: theory and algorithm. J. Comput.-Aided Des. Comput. Graph. 22(1), 1–9 (2010)
Acknowledgement
This work is supported by the National Science Foundation of China (Grant Nos. 61502082), the Fundamental Research Funds for the Central Universities, ZYGX2014J065 and the Smart Cities Foundation of Sichuan (Grant Nos. RWS-CYHKF-04-2015003).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Hu, H., Li, X., Wu, W., Liu, Z. (2016). A Compatible Model of Unstructured Data for Cross-Media Retrieval in the Field of Tourism. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2016. IDEAL 2016. Lecture Notes in Computer Science(), vol 9937. Springer, Cham. https://doi.org/10.1007/978-3-319-46257-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-46257-8_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46256-1
Online ISBN: 978-3-319-46257-8
eBook Packages: Computer ScienceComputer Science (R0)