Discrete supervision cross-modal hashing retrieval method based on semantic alignment

Abstract

The invention discloses a DSAH (discrete semantic alignment hashing) method based on semantic alignment for cross-modal retrieval. In the training process, a heterogeneous gap is reduced by the aid ofimage attributes and modal alignment semantic information. In order to reduce memory overhead and training time, a latent semantic space is learned by synergistic filtering, and the internal relationbetween a hash code and a label is directly built. Finally, in order to decrease quantization errors, a discrete optimization method is proposed to obtain a hash function with better performances. Inthe retrieval process, samples in a testing set are mapped to a binary space by the hash function, the Hamming distance between a binary code of a query sample and a heterogeneous sample to be retrieved is calculated, and front ranked samples are returned according to the sequence from small to large. Experimental results of two representative multi-modal data sets prove superior performances ofDSAH.

Description

Technical field: [0001] The invention belongs to the technical field of multimedia retrieval, and relates to a cross-modal hash retrieval method, in particular to a discrete-supervised cross-modal hash retrieval method based on semantic alignment. Background technique: [0002] In the era of Web 2.0, people can upload data of various modalities through the network, such as images, texts, and videos. Utilizing data in various modalities to represent information allows netizens to obtain the information they need more intuitively and easily. Although the information representations of these different modalities are different, they may contain the same semantic information. Therefore, for the search content submitted by the user, the data returned by the search engine in multiple modalities can describe the user's search intention more vividly and vividly. , which can improve the experience of network users. [0003] The representations of samples of different modalities are ...

AI Technical Summary

Problems solved by technology

However, none of the above methods directly learn discrete hash codes, resulting in a decre

Images