Cross media feature retrieval and optimization: A contemporary review of research scope, challenges and objectives

Predictive analytics that learns from cross-media is one among the significant research objectives of the contemporary data science strategies. The cross-media information retrieval that often denotes as cross-media feature retrieval and optimization is the crucial and at its infant stage. The traditional approaches of predicative analytics are portrayed inthe context of unidimensional media such as text, image, or signal. In addition, the ensemble learning strategies are the alternative, if the given learning corpus is of the multidimensional media (which is the combination of two or more of test, image, video, and signal). However, the contributions those correlates the information of divergent dimensions of the given learning corpus is still remaining in the nascent stage, where it is termed as cross media feature retrieval and optimization. This manuscript is intended to brief the recent escalations and future research scope in regard to cross-media feature retrieval and optimization. In regard to this, a contemporary review of the recent contributions has been portrayed in this manuscript. © 2020, Springer Nature Switzerland AG.