Method, device, computer equipment and storage medium for video action classification

Abstract

The disclosure relates to a video action classification method, device, computer equipment and storage medium, and belongs to the technical field of machine learning models. The method comprises: obtaining the video to be classified, determining a plurality of video frames in the video to be classified; inputting the plurality of video frames into the optical flow replacement module in the optimized video action classification model after training, and obtaining the corresponding The optical flow feature information; input multiple video frames into the three-dimensional convolutional neural module in the optimized video action classification model after training, and obtain the spatial feature information corresponding to multiple video frames; based on optical flow feature information and spatial feature information , to determine the classification category information corresponding to the video to be classified. With this disclosure, multiple video frames of the video to be classified can be directly used as the input of the optical flow replacement module in the model, and the optical flow replacement module can directly extract the optical flow feature information corresponding to the multiple video frames of the video to be classified, further improving improve the efficiency of classification processing.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning models, and in particular to a video action classification method, device, computer equipment and storage medium. Background technique [0002] With the development of society, more and more users like to use fragmented time to watch or shoot short videos. When any user uploads a short video shot to the short video platform, relevant personnel in the short video platform can view the short video and classify the actions of the objects in the short video according to subjective ideas, such as dancing, climbing trees, drinking water etc. Then, relevant personnel can add corresponding tags to the short video according to the classification results. [0003] In the process of realizing the present disclosure, the inventors found at least the following problems: [0004] Due to the huge number of short videos received by the short video platform, if the actions of objects in each s...

AI Technical Summary

Problems solved by technology

[0004] Due to the huge number of short videos received by the short video platform, if the actions of the objects in each short video are manually classified, the efficiency of the classification operation will be extremely low

Images