Video emotion recognition method, device, equipment and readable storage medium

A technology of emotion recognition and video, applied in the field of emotion recognition, can solve the problems of low recognition accuracy

Active Publication Date: 2021-07-06
IFLYTEK CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, voice-based emotion recognition is relatively mature, but video-based emotion recognition has low recognition accuracy due to certain restrictions.

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 emotion recognition method, device, equipment and readable storage medium
  • Video emotion recognition method, device, equipment and readable storage medium
  • Video emotion recognition method, device, equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Next, the technical scheme in the present application embodiment will be described in the present application, and it is understood that the described embodiments are intended to be described herein, not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative labor premises, all of the present application protected.

[0052]In order to obtain an emotional identification scheme having a better recognition effect, the inventors of this case conducted a deep study:

[0053] The initial idea is to treat the boundary division of the identification video (ie, a rough positioning of the mood) to obtain a video clip that is really used for emotionally recognition, and then extracts video timing from the video segment using the 3D convolutionary network. Finally, the emotion category of the video to be identified is determined based on the vide...

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 present application provides a video emotion recognition method, device, device, and readable storage medium. The method includes: acquiring a video to be recognized, and performing coarse-grained boundary division on the video to be recognized based on a specified boundary division basis, and obtaining a coarse-grained video segment; based on the spatiotemporal semantic information of the coarse-grained video segment, fine-grained boundary division is performed on the coarse-grained video segment to obtain a fine-grained video segment; at least one emotion recognition result of the fine-grained video segment is determined, and through the fine-grained video segment The emotion recognition result of the video to be recognized is obtained by at least one emotion recognition result. The emotion recognition method provided by the present application has high recognition accuracy.

Description

Technical field [0001] The present application relates to the field of emotional identification, and more particularly to an emotional identification method, apparatus, device, and readable storage medium of a video. Background technique [0002] Emotionally recognition refers to the identification of the emotional state of the specified object. The current emotion recognition has a variety of, for example, voice-based emotional identification, video-based emotional identification, etc., voice-based emotional identification by extracting acoustic features and text characteristics, Using SVM or convolutional neural networks, emotional categories are determined, different from voice-based emotional identification, video-based emotional identification does not require significant language communication, only through images can be obtained. Currently, voice-based emotional identification is relatively mature, but video-based emotional identification causes its recognition accuracy du...

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): G06F16/70
Inventor 吴小燕何山殷兵柳林刘聪
Owner IFLYTEK 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