Method for increasing credibility of question prerequisite in visual question answering scene

Abstract

The invention provides a method for increasing credibility of question prerequisite in a visual question answering scene. The method comprises following steps: prerequisite information extraction, question correlation prediction database, question correlation detection, visual question answering data expansion. First, the prerequisite information in the problem is extracted; the problem correlation prediction and explanation database are constructed; and binary classification of problem image pairs (Ii, Qi) is performed; whether the image Ii has the prerequisite information in question Qi is identified; then on the basis of one-hot coding, the image Ii and the problem Qi are encoded using the VGG network and the short and long term memory network, respectively, and input the data to the multi-layer sensor for prediction. The method of the invention can handle a plurality of target objects and their relations in different scenes, provide an encoding method to calculate the image matching distance, and improve the credibility of the question prerequisite information.

Description

technical field [0001] The invention relates to the field of visual question answering, in particular to a method for improving the credibility of question premise in a visual question answering scene. Background technique [0002] In recent years, it has attracted much attention to attach image labels or subject texts to image content independently. Especially in today’s generation of massive images, it is impossible to distinguish and classify image content completely according to human eyes. Therefore, how to use prior Knowledge of the key to hashtag specific image content and accurately answer the question in Visual Q&A is something to consider. If the content of the image can be successfully answered without the labor of the human eye, it will bring extremely high significance and economic value to engineering and the visual industry, especially in places with a wide background and sparse objects such as the deep ocean. Real-time navigation information, verification of...

AI Technical Summary

Problems solved by technology

[0005] Aiming at solving the problem of low credibility of question premise in the field of visual question answering, the purpose of the present invention is to provide a method for improving the credibility of question premise in the visual question answering scene, and propose a combination of one-hot encoding and deep learning encoding new frame

Images