Cross-media ranking method based on latent space learning and bidirectional ranking learning

Abstract

The invention discloses a cross-media sorting method based on hidden space learning and two-way sorting learning. The method includes 1, centrally constructing sorting samples of text retrieval images and sorting samples of image retrieval texts into a training sample; 2, performing cross-media sorting learning based on the hidden space learning and the two-way sorting learning on the constructed training sample, and acquiring a multimedia semantic space and a cross-media sorting model; 3, using the learned cross-media sorting model to performing cross-media sorting. The method can be applied in the text retrieval images and the image retrieval texts, and modeling is performed on two retrieval directions simultaneously, the acquired semantic understanding capacity of a retrieval model is stronger, and retrieval accuracy is higher as compared with the method considering one-way sorting learning only.

Description

technical field [0001] The invention designs cross-media retrieval, and in particular relates to a cross-media sorting method based on latent space learning and bidirectional sorting learning. Background technique [0002] Images are a very common file type these days, and they have certain semantics. Generally speaking, an image is composed of individual pixels, and the computer cannot directly understand the semantic information contained in the image. With the development of multimedia technology and network technology, more and more images emerge. Retrieval technology can help users quickly find the content they are interested in in massive data, and has become an increasingly important field in computer application technology. The traditional retrieval technology, whether it is keyword-based retrieval or content-based retrieval, cannot well meet the needs of users who want to retrieve images with text or retrieve text with images. In keyword-based retrieval systems, ...

AI Technical Summary

Problems solved by technology

However, due to the huge number of existing images, the amount of engineering in the labeling process is huge, and because the labeling content will inevitably be affected by the subjective factors of the labeler, for the same image, different labelers may label different keywords, so Keywords often cannot objectively reflect all the semantics contained in the image

The content-based retrieval system does not need to annotate the image, and the user submits a retrieval example to retrieve the image. However, there are two weaknesses in the traditional content-based retrieval technology: one is that the user can only retrieve images with the same modality as the query example. Media objects can only retrieve images through images; second, there is a semantic gap between the underlying features of images and high-level semantics, so the retrieval performance is limited

Images