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

Video processing method, machine learning model training method and related device and equipment

A video processing and video technology, applied in the field of artificial intelligence, can solve problems such as inaccurate labeling

Pending Publication Date: 2022-04-29
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only relying on visual information or text information to label small videos has the problem of inaccurate labeling

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
  • Video processing method, machine learning model training method and related device and equipment
  • Video processing method, machine learning model training method and related device and equipment
  • Video processing method, machine learning model training method and related device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0140] A method for training a machine learning model involved in the embodiment of the present application is introduced below.

[0141] Embodiment 1 introduces a method for training a machine learning model involved in the embodiment of the present application. This machine learning method can be figure 1 and figure 2 The server 200 in realizes.

[0142] Specifically, as Figure 3A As shown in an example, it is a schematic flow chart of a machine learning model training method, which may include but not limited to some or all of the following steps:

[0143] S301: Obtain a sample data set based on the sample video set.

[0144] A set of sample videos may include one or more sample videos.

[0145] Sample videos can come from figure 1 In the network video publisher terminal 400-1, the network video publishers can be professional video editors, or self-media, such as Kuaishou, Douyin and other major anchors who often publish videos on daily small videos.

[0146] The s...

Embodiment 2

[0208] A video processing method involved in the embodiment of the present application is introduced below.

[0209] In some embodiments, a video processing method provided in the embodiment of the present application may be implemented by figure 1 and figure 2 Realized by the server 200 or the terminal 400 in.

[0210] In the embodiment of the present application, it is taken that the execution subject is the server 200 as an example.

[0211] Specifically, as Figure 6A and Figure 6B As shown in an example, it is a schematic flow chart of a video processing method, which may include but not limited to some or all of the following steps:

[0212] S601: The server extracts features from the video to be processed to obtain a video feature vector.

[0213] Pending videos can come from figure 1 In the network video publisher terminal 400-1, the network video publishers may be professional video editors, or major anchors who publish videos on self-media platforms.

[0214...

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 embodiment of the invention discloses a video processing method, a machine learning model training method, a related device and equipment, and the method relates to artificial intelligence, and comprises the steps: extracting features from a to-be-processed video, and obtaining a video feature vector; extracting features from the to-be-processed text to obtain a text feature vector; the to-be-processed text corresponds to the to-be-processed video; splicing the text feature vector and the video feature vector to obtain a multi-modal feature vector; performing feature fusion on the multi-modal feature vector to obtain a fused feature vector; and classifying the to-be-processed video based on the fused feature vector to obtain a tag of the to-be-processed video. According to the method, the fusion degree of the video information and the text information can be improved, so that the video information and the text information complement each other, the tag identification accuracy of the video is improved, and the theme of the video can be better understood.

Description

technical field [0001] This application relates to the technical field of artificial intelligence, and in particular to a video processing method, a machine learning model training method, and related devices and equipment. Background technique [0002] In recent years, a form of video information flow has become popular all over the world. Compared with the traditional way of disseminating information in text, video information flow has the advantages of richer information, more convenient browsing and more impact. [0003] Generally, in addition to professional video editors, the sources of videos are more from self-media, such as Kuaishou, Douyin and other major anchors who often post videos on daily small videos. Compared with text information, the small videos released by self-media have richer content and more diverse forms. Therefore, how to understand the theme of the video in an effective way has become a technical difficulty. For small videos, we hope to summarize...

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 Applications(China)
IPC IPC(8): G06V20/40G06K9/62G06N3/04G06N3/08G06V10/764G06V10/80G06V10/82
CPCG06N3/08G06N3/044G06N3/045G06F18/241G06F18/253
Inventor 黄剑辉
Owner TENCENT TECH (SHENZHEN) CO LTD