Video classification method and device and computer readable storage medium

Abstract

The invention provides a video classification method and device, and a computer readable storage medium. The method comprises the steps of extracting video attitude data in a target video; matching the video attitude data with seed attitude data included in a preset attitude retrieval library, and determining an attitude classification category corresponding to the video attitude data, the attitude retrieval library including a corresponding relationship between the attitude data and the attitude classification category; and determining the attitude classification category corresponding to thevideo attitude data as the classification category of the target video. The attitude dimension matching can be carried out through the video attitude data and the seed attitude data, and the purposeof classifying the target video in the attitude dimension is achieved. Interference caused by information of other dimensions is reduced, so that the data calculation amount is reduced, and the problem that the calculation amount is large due to feature similarity calculation is solved. Besides, through the matching mode of the attitude data, the operation of extracting the frame-by-frame featuresof the video is avoided, and the efficiency of classifying the target video is improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a video classification method, device and computer-readable storage medium. Background technique [0002] In long videos, the characters shown in some plots often have a lot of exaggerated body movements. The video intervals containing these contents are often relatively exciting video clips. In terms of video recommendation, extraction of highlights, and video tagging, etc. , being able to efficiently and accurately find video clips corresponding to these exaggerated gestures, and classify these video clips is of great value and significance to video services. [0003] In the prior art, many wonderful pictures are displayed in the video, and the fragments corresponding to these wonderful pictures are extracted and classified. At present, a classification model based on the characteristics of static pictures is often used for processing. Specifically, the classifica...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a video classification method, device, and computer-readable storage medium, which solves the problems of large amount of data calculation and low processing efficiency in the current solution for video classification to a certain extent

Images