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

Video abstraction method based on double-self-attention capsule network

A video summarization and attention technology, applied in the field of video processing, can solve problems such as difficult to obtain scoring functions

Pending Publication Date: 2020-11-24
CHONGQING UNIV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since most adjacent frames in a video are visually similar, it is difficult to obtain an accurate scoring function

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 abstraction method based on double-self-attention capsule network
  • Video abstraction method based on double-self-attention capsule network
  • Video abstraction method based on double-self-attention capsule network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] In order to further explain the embodiments, the present invention is provided with drawings. These drawings are a part of the disclosure of the present invention. They are mainly used to illustrate the embodiments, and can cooperate with the relevant descriptions in the specification to explain the operating principles of the embodiments. Those of ordinary skill in the art should be able to understand other possible implementation manners and advantages of the present invention from these contents. The components in the figure are not drawn to scale, and similar component symbols are usually used to indicate similar components.

[0090] According to an embodiment of the present invention, a video summarization method based on a dual self-attention capsule network is provided.

[0091] The present invention will now be further described with reference to the drawings and specific embodiments, such as Figure 1-4 As shown, the video summarization method based on the dual self-...

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 abstraction method based on a double-self-attention capsule network. The method comprises the following steps: S1, regarding a video abstraction problem as a marking problem of a video frame sequence; s2, for a given video, extracting an initial feature vector of each video frame; s3, performing feature refinement on the initial feature vector by using a double attention model; s4, fusing the refined features by using a double-flow capsule network, and marking each frame of the video; s5, training the model in a deep learning mode by using a corresponding targetfunction; and S6, generating a final abstract according to the model trained in the step S5. The method has the beneficial effects that the short-term and long-term dependency relationship can be effectively captured without being limited by the video duration, parallel processing can be realized, the running duration is reduced, and the finally obtained abstract video is non-redundant and complete.

Description

Technical field [0001] The present invention relates to the technical field of video processing, in particular, to a video summary method based on a dual self-attention capsule network. Background technique [0002] With the development and popularization of video shooting equipment such as mobile phones and digital cameras, the number of videos has increased dramatically. Due to the lack of professional photography knowledge by most photographers, most of the videos people shoot are usually redundant, and may only contain very little important information in one video. It is very time consuming to browse and understand such videos. Therefore, in order to facilitate browsing and understanding, we need to generate a concise, non-redundant summary for a given video, and the summary cannot lose important semantic information. [0003] Video summary is essentially a subset selection problem. Through the selection of subsets, we can get a summary of three levels of frame, shot and ob...

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): G06F16/738G06N3/08
CPCG06F16/739G06N3/08Y02T10/40
Inventor 王洪星傅豪徐玲杨梦宁洪明坚葛永新黄晟陈飞宇
Owner CHONGQING UNIV
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