Video type determination method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a video type determination method and device, equipment and a storage medium, and can be applied to the fields of artificial intelligence, image processing, block chains and the like. The method comprises the following steps: determining an initial image feature of each video frame of a to-be-predicted video; and inputting each initial image feature into a video type prediction model to obtain a target type of the to-be-predicted video, the video type prediction model being obtained based on prediction of each sample video in the training sample set. By adopting the method provided by the embodiment of the invention, the type of the video can be accurately determined, and the applicability is high.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular, to a video type determination method, apparatus, device, and storage medium. Background technique [0002] In the fields of video recommendation, video retrieval, and video advertisement placement, video classification is one of the most basic representations of video content features, which has the advantages of strong interpretability and easy expansion. For example, in the field of video recommendation, videos of interest can be recommended to the target object according to the video types of the videos viewed by the target object. In the field of video retrieval, retrieval based on video types can improve the accuracy of retrieval results. [0003] The existing technology often determines the video type by identifying the objects that appear the most in the video, but it is easily affected by the background or style, which causes the determined video type to...

AI Technical Summary

Problems solved by technology

[0003] The existing technology often determines the video type by identifying the most frequently appearing objects in the video, but it is easily affected by the background or style, which leads to differences between the determined video type and the actual type. For example, if it is also a sitting person, when the character When it appears in offices, restaurants, study rooms, cars and even seaside resorts, it will correspond to different video types

The existing technology also determines the image type of some video frames in the video frame, and then deduces the video type of the video according to the image type of some video frames, but this method is limited by the image type of the video frame, which leads to the final determination The type of video output is less accurate

Images