Video abstract generation method and related device

A video abstract and video frame technology, applied in the computer field, can solve problems such as time-consuming and labor-intensive, labeling errors, affecting the efficiency and accuracy of video abstracts, etc.

Active Publication Date: 2020-12-08
TENCENT TECH (SHENZHEN) CO LTD
View PDF10 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the accuracy process of supervised video summary generation is affected by manual labeling, and the process of manual labeling is time-consuming and labor-intensive, prone to labeling errors, affecting the efficiency and accuracy of video summary generation

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 abstract generation method and related device
  • Video abstract generation method and related device
  • Video abstract generation method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0108] The embodiment of the present application provides a method for generating a video summary and a related device, which can be applied to a system or program including a video summary generation function in a terminal device. By acquiring a target video, wherein the target video includes a sequence of video frames, the video The frame sequence contains multiple video frames; then extract the image features of each video frame to generate an image feature sequence; and divide the video frame sequence into multiple target segment sequences to generate a paragraph feature sequence; further image feature sequence It is fused with the paragraph feature sequence to obtain the fusion feature; and then the reinforcement learning training is performed based on the fusion feature to generate a video summary. In this way, the unsupervised video summary generation process is realized. Due to the combination of image-level image features and depth-level paragraph features, the quality...

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 abstract generation method and a related device, which are applied to a machine learning technology of artificial intelligence. The method comprises: acquiring a targetvideo; extracting image features of each video frame to generate an image feature sequence; dividing a video frame sequence into a plurality of target segment sequences to generate a paragraph feature sequence; fusing the image feature sequence and the paragraph feature sequence to obtain fused features; and carrying out reinforcement learning training based on the fusion features to generate a video abstract. According to the invention, an unsupervised video abstract generation process is realized, the video abstract generation quality is ensured by combining the image features of the picture level and the paragraph features of the depth level, and the unsupervised video abstract generation process does not need manual annotation, so that the video abstract generation efficiency and accuracy are improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method for generating a video summary and related devices. Background technique [0002] With the rapid development of Internet technology, people's requirements for entertainment forms are getting higher and higher. For example, in the process of watching a video, a fast jump process based on a video abstract can be performed, thereby improving the experience of watching a video. [0003] Generally, a supervised video summarization process can be used for summarization generation, which requires manually annotated video sequences as training samples. First, image feature extraction is performed, then feature encoding is performed, and an extraction model is trained with labels to determine the probability that each image in the video sequence belongs to the summary, and then the video is reorganized to obtain the video summary. [0004] However, the accuracy proc...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06V20/46G06V20/41G06N3/045G06F18/213G06F18/2415G06F18/253
Inventor 闫桂霞王晓利王瑞琛
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap