Title:
DOUBLE-STREAM VIDEO GENERATION METHOD BASED ON DIFFERENT FEATURE SPACES OF TEXT
Document Type and Number:
WIPO Patent Application WO/2020/177214
Kind Code:
A1
Abstract:
A double-stream video generation method based on different feature spaces of a text, comprising: a text feature extraction process, a double-stream video generation process, and an adversarial training process. In the present invention, according to an object appearance feature space and a corresponding motion feature space thereof described in the text, by separating a space feature and a temporal feature comprised in the text, modeling these features in a double-stream manner respectively, and optimizing a generated result in an adversarial training manner to enable video fragments to be closer to reality, intelligent generation of the video fragments conforming to the text content is realized. The method has wide market demands and application prospects in the aspects of material accumulation and data set automatic generation.
More Like This:
Inventors:
WANG WENMIN (CN)
LI WEIMIAN (CN)
HUANG ZHONGYI (CN)
LI WEIMIAN (CN)
HUANG ZHONGYI (CN)
Application Number:
PCT/CN2019/085962
Publication Date:
September 10, 2020
Filing Date:
May 08, 2019
Export Citation:
Assignee:
UNIV PEKING SHENZHEN GRADUATE SCHOOL (CN)
International Classes:
G06N3/04; G06K9/62; G06N3/08
Domestic Patent References:
| WO2017209307A1 | 2017-12-07 |
Foreign References:
| CN108596265A | 2018-09-28 | |||
| CN108090940A | 2018-05-29 | |||
| CN108830212A | 2018-11-16 | |||
| CN109325135A | 2019-02-12 | |||
| CN107609460A | 2018-01-19 | |||
| CN104731959A | 2015-06-24 |
Attorney, Agent or Firm:
BEIJING WANXIANGXINYUE INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF: