Video recognition method based on space-time pyramid network

Abstract

The invention provides a video recognition method based on a space-time pyramid network. The method comprises steps of extracting characteristics of each video clip sample in a video sample set through the convolution neural network, carrying out time-space linear operator processing so as to acquire a first vector and through a second convolution neural network, acquiring image information of image samples and acquiring a second vector; carrying out time-space linear operator processing on the vector obtained by splicing the first vector and the second vector; carrying out weighting pooling on an output result and the second vector so as to acquire a third vector; through average pooling, acquiring a fourth vector and a fifth vector and then carrying time-space linear operator processingso as to acquire a sixth vector; and according to a loss value, recognizing a to-be-detected video. According to the invention, through the dimension reduction operation and inverse transformation operation, problems of curse of dimensionality of bilinearity fusion and high operation complexity are solved; and by improving the bilinearity fusion operators, under the condition that two videos havethe similar background or the similar short films, better recognition effects are acquired.

Description

technical field [0001] The invention relates to the field of computer data analysis, and more specifically, to a video recognition method based on a space-time pyramid network. Background technique [0002] With the development of artificial intelligence, machine learning has been applied in various fields, such as face recognition, weather prediction, etc. Nowadays, artificial intelligence has been widely used in the field of computer vision, and image recognition technology has achieved very good accuracy, but there is still room for improvement in video data processing and video action recognition. [0003] Obtaining a better representation of video data is the basis of many computer vision tasks, such as action recognition and video subtitle recognition. Video data analysis is not only image analysis but also depends on the joint model of time and space. Many methods now take advantage of convolutional networks to build such models. However, since the framework of Con...

AI Technical Summary

Problems solved by technology

[0004] However, these methods perform poorly when two videos have similar backgrounds or are similar in short time segments.

Images