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

Music-driven dance generation method

A music and dance technology, applied in the field of music-driven dance movement generation, can solve the problems of ignoring the internal connection between music and video, and not finding a strong correlation between music and video, and achieve fast calculation speed, simple prediction process, and high accuracy Improved effect

Pending Publication Date: 2020-02-28
NANJING UNIV OF SCI & TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The limitations of the above attempts either did not find a strong correlation between music and video, or only focused on synthesizing human motion while ignoring the intrinsic connection between music and 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
  • Music-driven dance generation method
  • Music-driven dance generation method
  • Music-driven dance generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with accompanying drawing.

[0049] The invention discloses a music-driven dance generation method, which has multiple potential application prospects, such as virtual reality, animation characters and choreography. For a given music sequence, in order to generate natural dance moves, the following conditions need to be met: 1) the rhythm between dance moves and music beats should be harmonious; 2) the generated dance moves should have obvious diversity.

[0050] The present invention proposes a sequence-to-sequence learning architecture (LSTM-SA) utilizing long short-term memory and self-attention mechanisms. The music-driven dance generation method of the present invention includes three main processes of neural network model construction, neural network training, and network model testing.

[0051] The neural network construction process refers to selecting an appropriate network framework, designi...

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 music-driven dance generation method comprising the following aspects of 1) collecting a dance data set; 2) performing advanced feature extraction on music and dance sequences; and 3) providing a brand-new cross-domain sequence pair sequence learning framework for real dance generation. According to the method in the invention, the efficiency is high, the accuracy is alsoimproved, the model is more complex, the model size is small, the calculation speed is high, the prediction process is simpler, and the music can be quickly combined with the dance sequences.

Description

technical field [0001] The invention relates to the fields of cross-domain sequence analysis and audio-video analysis, and more specifically, a music-driven dance movement generation method. Background technique [0002] Deep learning based on sequence analysis has many applications, including language processing, video tracking, cross-domain analysis, sentiment analysis based on semantic features. Cross-domain sequence analysis is one of the important branches of sequence analysis. Cross-domain sequence analysis refers to finding the correspondence between two different types of sequences. There are many related applications, such as translation between different languages, using natural language to synthesize real images. [0003] Audio-video analysis is a special case of cross-domain sequence analysis. Compared with other disciplines, there are relatively few studies on audio and video analysis. The main reason is that for general traditional video, the correlation be...

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): G10L25/12G10L25/24G10L25/63G06N3/04G06N3/08
CPCG10L25/12G10L25/24G10L25/63G06N3/084G06N3/045
Inventor 刘亚洲祁玉
Owner NANJING UNIV OF SCI & TECH
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