Action recognition method based on attention mechanism of convolution recurrent neural network

Abstract

The present invention belongs to the field of computer vision action recognition, and proposes an action recognition method based on the attention mechanism of the convolution recurrent neural network, in order to solve the problem that the obvious region cannot be effectively extracted in the action recognition and to improve the accuracy of classification. The method comprises: using the convolution neural network to extract the feature of the action video automatically; using the spatial transformation network to realize the attention mechanism based on the feature map, and extracting the obvious feature region by using the attention mechanism to generate the target feature map; and inputting the target feature map into the convolutional recurrent neural network to produce the final action recognition result. Experiments show that the proposed method has achieved good results on the benchmark action video test set such as UCF-11, HMDB-51, and the like, and improves the accuracy of action recognition.

Description

technical field [0001] The invention belongs to the field of computer vision action recognition, and relates to an action recognition method based on a convolution recursive neural network based on an attention mechanism. Background technique [0002] With the development of the Internet, video has become an indispensable part of today's big data, which promotes the research on video classification and produces a large number of novel technologies. Compared with images, video has a lot of rich and contextual information, which requires the ability to build a good model to capture the features contained in it. At present, the understanding of video content has become a problem to be solved in video processing. The method of deep learning subverts the design ideas of traditional algorithms in many fields such as speech recognition, image classification, and text understanding, and gradually forms an end-to-end model starting from training data. A new mode for outputting the ...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem that the salient region cannot be effectively extracted in the process of action recognition, the present invention proposes an action recognition method based on a convolutional recurrent neural network based on the attention mechanism, which fully considers the importance of the salient region in the process of action recognition for classification. The importance and non-significant regions of the adverse effect on the classification

Images