In particular, the Deep Joint Semantic Reconstruction Hash (DJSRH) proposed by Suet al. [8] unifies semantic similarities into a uniform relevance matrix to catch the potential association of the input multimodal instances. Wang et al. [12] proposed a semantic alignment hash method (DSAH), ...
In addition, a discrete optimization algorithm is proposed to solve the discrete problems. Our major contributions can be summarized as follows: 1. A novel supervised cross-modal hashing method, i.e., DSAH, is proposed to learn the discriminative compact hash codes for large-scale retrieval ...