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

Video classification method, model training method, device and equipment

A technology of video classification and classification model, applied in the field of computer vision, which can solve the problems of data sets with no start position and end position, and the inability to accurately output the position where the label appears.

Active Publication Date: 2020-02-11
GUANGDONG OPPO MOBILE TELECOMM CORP LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a video classification method, model training method, device and equipment, which can solve the problem that the deep learning model cannot accurately output the label in the Issues with placement in the video

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 classification method, model training method, device and equipment
  • Video classification method, model training method, device and equipment
  • Video classification method, model training method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0049] The present application provides a video classification model. The video classification model can not only predict the tag to which the video belongs, but also output the start position and end position of the tag in the video.

[0050] figure 1 A flow chart of a method for training a video classification model provided by an embodiment of the present application is shown. The method can be implemented by computer equipment. The method includes:

[0051] Step 101, using the video data set to train the classification model to obtain the trained classification model, the trained classification model includes: frame feature extraction layer, feature enhancement layer and classification layer;

[0052]The video dataset incl...

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 invention discloses a video classification method and device, a model training method and device and equipment. The method comprises the steps of acquiring a video classification model; performingfeature extraction on video frames in the video according to a feature extraction network of the video classification model to obtain frame feature vectors of the video frames; determining a target label to which the video frame belongs according to the product of the frame feature vector of the video frame and the maximum feature vector of each label in the video classification model, the targetlabel being one or more of the labels; and for each target label, marking a starting position and an ending position of the target label in the video according to a plurality of continuous video frames belonging to the target label in the video.

Description

technical field [0001] This application relates to the field of computer vision, in particular to a video classification method, model training method, device and equipment. Background technique [0002] Automatic understanding of video content has become a key technology for many application scenarios, such as autonomous driving, video-based search and intelligent robots, etc. Video tagging through machine learning is a way to automatically understand video content. [0003] In related technologies, a video is encoded into a series of feature vectors, including visual features and audio features, and the feature vectors are input into a trained deep learning model to obtain a label corresponding to the video. This tag is a video-level tag. Typically, the deep learning model is trained based on the Youtube-8M dataset. Youtube-8M dataset is a large-scale labeled video dataset including 6.1 million video sets and 3862 classes. [0004] However, in some scenarios, it is des...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/46G06V20/41G06V10/464G06N3/045G06F18/241G06F18/2431
Inventor 尹康
Owner GUANGDONG OPPO MOBILE TELECOMM CORP LTD