Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-label video classification method and system, system training method and device

A video classification and multi-label technology, applied in the direction of instrumentation, computing, character and pattern recognition, etc., can solve problems such as feature spaces that do not take into account the better initial feature space

Active Publication Date: 2021-08-20
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The original video and audio features are directly used as the input of the aggregation operation NetVLAD, without considering whether the initial feature space is suitable for a better feature space for multi-label video classification problems

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
  • Multi-label video classification method and system, system training method and device
  • Multi-label video classification method and system, system training method and device
  • Multi-label video classification method and system, system training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0192] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

[0193] The multi-label video classification technology based on the neural network model generally inputs the feature information of the video to be labeled into the trained neural network model, and then uses the neural network model to generate label information for the video. The public dataset YouTube-8M can be used for multi-label video classification by the existing Gated NetVLAD method.

[0194] YouTube-8M is currently the largest video dataset released by Google, which contains more than 7 million YouTube video data, corresponding to 4716 classification labels. Google also released the characteristics of these videos, including video and audio parts. The extraction process of video features is as follows: sampling an image every 1 second, accumulatively sampling 300 images, and then extracting ...

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 present invention provides a multi-label video classification method and system, system training method and device, wherein the multi-label video classification method includes: acquiring the video to be processed, extracting the initial features of the video to be processed; extracting the extracted initial video feature matrix and The initial audio feature matrix is ​​transformed separately to generate a new video feature matrix and a new audio feature matrix; the new video feature matrix and the new audio feature matrix are aggregated to generate an aggregated feature vector; Process multiple classification labels of a video and the confidence corresponding to each classification label. The multi-label video classification method provided by the embodiment of the present invention can improve the accuracy of multi-label video classification.

Description

technical field [0001] The present invention relates to the technical field of multi-label video classification, in particular to a multi-label video classification method and system, and a system training method and device. Background technique [0002] With the development of Internet technology, more and more people choose to watch videos through the Internet. When displaying video information, the video playback website will display the classification label of the video, that is, the category to which the video belongs. Often, a video has more than one tag, for example, a video can have both a war tag and a sci-fi tag. Multi-label video classification can be achieved through neural network models. [0003] The multi-label video classification technology based on the neural network model generally inputs the feature information of the video to be labeled into the trained neural network model, and then uses the neural network model to generate label information for the v...

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): G06K9/00
CPCG06V20/41G06V20/46
Inventor 梁大为
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com