Cross — Media retrieval via CCA — BP neural network

With the rapid growth of multimedia content on the Internet, multimedia retrieval has been extensively studied for decades. Most of the existing methods cast low-level features of cross-media data onto a unified feature space. However, some of these feature spaces usually do not have explicit semantics. Some methods, even if they take semantic meaning into account, do not dig the semantic information of data well. By considering the above issue, a new approach to cross-media retrieval via Canonical Correlation Analysis-Back Propagation Neural Networks(CCA-BPNN) is proposed in this paper which is able to explore jointly the correlation and semantic information. The experimental results on two datasets show the effectiveness of our proposed approach, compared with state-of-the-art methods.