Unlock instant, AI-driven research and patent intelligence for your innovation.

A video classification method, device and electronic equipment

A video classification and video technology, applied in the field of video processing, can solve problems such as inaccurate video classification results, and achieve the effect of accurate classification results

Active Publication Date: 2022-03-25
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present disclosure provides a video classification method, device and electronic equipment to at least solve the problem of inaccurate video classification results in related technologies

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A video classification method, device and electronic equipment
  • A video classification method, device and electronic equipment
  • A video classification method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0060] It should be noted that the terms "first", "second" and the like in the description and claims of the present disclosure and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances so that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods co...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The disclosure relates to a video classification method, device and electronic equipment. The method includes: for each modality in the plurality of modalities, extracting the features of the video to be processed on the modality; obtaining the video file to be processed as the video to be processed; using a multi-head self-attention mechanism to calculate the video to be processed Processing the attention value of the video on the modality, the attention value is used to represent the contextual relationship between the features of the video to be processed on this modality and the features of the video to be processed on other modality; Fusing the attention value of the video to be processed on each modality to obtain the fusion feature of the video to be processed; using the pre-trained model to map the fusion feature to obtain the video to be processed The classification result of the model is used to realize the mapping of the fusion feature to the classification result. The fusion feature can effectively reflect the contextual relationship between the features on different modalities, and then obtain more accurate classification results.

Description

technical field [0001] The present disclosure relates to the technical field of video processing, and in particular, to a video classification method, apparatus, and electronic device. Background technique [0002] In some application scenarios, videos need to be classified for practical needs. For example, a short video platform needs to classify uploaded videos. In the process of classifying the video, in order to fully obtain the relevant features of the video, analysis can be performed from multiple video-related modalities. For example, the video can be classified by synthesizing the modal features of the video image, attached text, and voice. [0003] In the related art, the features of the video in multiple modalities are often spliced ​​end-to-end, as the features of the video, and input to the subsequent fully connected layer to perform the end-to-end mapping of the spliced ​​features to the classification results. , to get the classification result of the video. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/40G06V10/80G06K9/62
CPCG06V20/40G06V20/46G06F18/253
Inventor 李涛李岩
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD