Cross-media retrieval method based on deep learning and consistent expression space learning

Abstract

The invention relates to a cross-media retrieval method based on deep learning and consistent expression spatial learning. By starting with two methods including feature selection and the similarity estimation of two highly-isomerous feature spaces, the invention puts forward the cross-media retrieval method capable of improving multimedia retrieval accuracy to a large extent by aiming at the cross-media information of two modalities including an images and a text. The method disclosed by the invention is a multimedia information mutual retrieval method which aims at two modalities including the image and the text, and cross-media retrieval accuracy is improved to a large extent. In a model which is put forward by the invention, a regulated vector inner product is adopted as a similarity metric algorithm, the directions of the feature vectors of two different modalities are considered, the influence of an index dimension is eliminated after centralization is carried out, an average value of elements is subtracted from each element in the vectors, the correlation of the two vectors subjected to average value removal is calculated, and accurate similarity can be obtained through calculation.

Description

technical field [0001] The present invention relates to cross-media retrieval technology, more specifically, to a cross-media retrieval method based on deep learning and consistent expression space learning. Background technique [0002] The research object of cross-media retrieval is: how to use computer to carry out cross-media information retrieval, that is: search for text information associated with the input image or search for images associated with the input text. [0003] The application fields of cross-media retrieval system include information retrieval, map recognition, image labeling, etc. With the rapid development of the Internet today, various network platforms, including news websites, microblogs, social networks, image and video sharing websites, etc., are increasingly changing people's perception of knowledge acquisition and social relations, and multimedia data is also constantly changing. Rapid growth, and various types of cross-media information combin...

AI Technical Summary

Problems solved by technology

The SIFT local feature used in this paper can be effectively used for object retrieval, but it cannot express the rich global content of the image well. The standard Pearson correlation algorithm used does not consider the directionality of the feature vector and the different features themselves. The difference in the dimension of the index cannot measure the similarity of the two modal features more accurately

Images