Cross media retrieval is a propelled technique created in the domain of multimedia retrieval that aides in interfacing the different substance with each other and makes a retrieval system. The evaluations of correlation and the projection of the correct matches are the two noteworthy properties found in cross media retrieval. The low-level element writes were customarily utilized strategy and it neglects to beat different issues. Abnormal state highlights are acquainted as an answer with deal with the projection of the substance. Semantic relationship is worked at a more raised measure of reflection which is closer to the human comprehension than content correlation. In this investigation, a crossover model of solidified correlation techniques is used for perceiving the interactive media pictures and their likenesses. The consideration of different methods and algorithms identified with CMR is upgraded in the examination alongside the assurance of the conceivable result of those methods.

Cross media retrieval(CMR), Image Retrieval, Pattern graph, Image acquisition, Correlation

[1] Yan, Jihong, et al. "Joint graph regularization based modality-dependent cross-media retrieval." Multimedia Tools and Applications (2017): 1-19.
[2] Xie, Liang, Peng Pan, and Yansheng Lu. "Analyzing semantic correlation for cross-modal retrieval." Multimedia Systems 21.6 (2015): 525-539.
[3] Lu, Tong, et al. "Content-oriented multimedia document understanding through cross-media correlation." Multimedia Tools and Applications 74.18 (2015): 8105-8135.
[4] Allani, Olfa, et al. "Pattern graph-based image retrieval system combining semantic and visual features." Multimedia Tools and Applications (2017): 1-30.
[5] Huang, Lei, and YuxinPeng. "Cross-media retrieval by exploiting fine-grained correlation at entity level."Neurocomputing 236 (2017): 123-133.
[6] N. Rasiwasia, J. Costa Pereira, E. Coviello, G. Doyle, G. Lanckriet, R. Levy, and N. Vasconcelos. A new approach to cross-modal multimedia retrieval. In Proceedings of the 18th ACM International Conference on Multimedia, pages 251–260. ACM, 2010.
[7] H. Hotelling, “Relations between two sets of variates”, Journal of Biometrika, Vol.28, pp.321–377, 1936.
[8] D. Li, N. Dimitrova, M. Li, I.K. Sethi, Multimedia content processing through cross modal association, in: Proceedings of the 11th ACM International Conference on Multimedia (ACM-MM), 2003, pp. 604–611.
[9] D.W. Jacobs, A. Kumar, A. Sharma, H. Daume III, Generalized multi view analysis: a discriminative latent space, in: Proceedings of IEEE
Conference on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 2160–2167
[10] J. Pereira, E. Coviello, G. Doyle, N. Rasiwasia, G. Lanckriet, R. LevyN. Vasconcelos, On the role of correlation and abstraction in cross-modal multimedia retrieval, IEEE Trans. Pattern Anal. Mach. Intell. 36 (3) (2014) 521–535.
[11] R. Li, X. Wang, Cross-modal retrieval with correspondence auto encoder, in: Proceedings of the 22nd ACM International Conference on Multimedia (ACMMM), 2014, pp. 7–16.
[12] Liang, Jian, et al. "Self-paced cross-modal subspace matching." Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval.ACM, 2016.