A Review of Hashing Methods for Multimodal Retrieval

With the advent of the information age, the amount of multimedia data has exploded. That makes fast and efficient retrieval in multimodal data become an urgent requirement. Among many retrieval methods, the hashing method is widely used in multimodal data retrieval due to its low storage cost, fast and effective characteristics. This review clarifies the definition of multimodal retrieval requirements and some related concepts, then introduces some representative hashing methods, mainly supervised methods that make full use of label information, especially the latest deep hashing methods. The principle and performance of these methods are compared and analyzed. At the same time, some remaining problems and improvement space would be discussed. This review will help researchers better understand the research status and future research directions in this field.