Video classification method and device, readable medium and electronic equipment

Abstract

The invention relates to a video classification method and device, a readable medium and electronic equipment, and relates to the technical field of video processing, and the method comprises the steps: carrying out the transformation of a to-be-classified video through a target transformation group, obtaining a plurality of transformation videos, determining a video classification result of the to-be-classified video through a trained video classification model according to the plurality of transformation videos, wherein the video classification model is used for determining a target video feature corresponding to the transformed video according to the transformed video and determining a video classification result according to the target video feature, and the target video feature is a feature with transformation invariance in the transformed video. According to the video classification method and device, the target video features with transformation invariance are extracted from the plurality of transformed videos by using the video classification model, and video classification is performed through the target video features, so that the influence of rotation, scaling or affine transformation on video classification can be avoided, and the accuracy of video classification is improved.

Description

technical field [0001] The present disclosure relates to the technical field of video processing, and in particular, to a video classification method, apparatus, readable medium and electronic device. Background technique [0002] With the continuous development of Internet technology, more and more videos are uploaded to the Internet by users. In order to better analyze and manage the videos in the Internet, it is necessary to classify the videos. Currently, video classification is usually performed by using an end-to-end CNN (English: Convolutional Neural Networks, Chinese: Convolutional Neural Network) model to learn the implicit spatiotemporal relationship in the video for video classification. However, in practical situations, since the orientation and distance of the video capture device are arbitrary, the acquired video image may have some rotation, scaling or affine transformation relative to the standard image. These transformations will make it difficult for the ...

AI Technical Summary

Problems solved by technology

However, in actual situations, since the orientation and distance of the video capture device are arbitrary, the acquired video image may have some rotation, scaling or affine transformation relative to the standard image.

These transformations will make it difficult for the CNN model to perform feature learning uniformly, and affect the generalization ability of the CNN model, reducing the accuracy of video classification

Images