Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020107813 - METHOD AND APPARATUS FOR POSITIONING DESCRIPTIVE STATEMENT IN IMAGE, ELECTRONIC DEVICE AND STORAGE MEDIUM

Publication Number WO/2020/107813
Publication Date 04.06.2020
International Application No. PCT/CN2019/086274
International Filing Date 09.05.2019
IPC
G06F 17/27 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
20Handling natural language data
27Automatic analysis, e.g. parsing, orthograph correction
CPC
G06F 40/289
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
289Phrasal analysis, e.g. finite state techniques or chunking
G06F 40/30
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
30Semantic analysis
G06K 9/46
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/049
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
049Temporal neural nets, e.g. delay elements, oscillating neurons, pulsed inputs
Applicants
  • 北京市商汤科技开发有限公司 BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD. [CN]/[CN]
Inventors
  • 刘希慧 LIU, Xihui
  • 邵婧 SHAO, Jing
  • 王子豪 WANG, Zihao
  • 李鸿升 LI, Hongsheng
  • 王晓刚 WANG, Xiaogang
Agents
  • 北京派特恩知识产权代理有限公司 CHINA PAT INTELLECTUAL PROPERTY OFFICE
Priority Data
201811459428.730.11.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) METHOD AND APPARATUS FOR POSITIONING DESCRIPTIVE STATEMENT IN IMAGE, ELECTRONIC DEVICE AND STORAGE MEDIUM
(FR) PROCÉDÉ ET APPAREIL DE POSITIONNEMENT D'UN ÉNONCÉ DESCRIPTIF DANS UNE IMAGE, DISPOSITIF ÉLECTRONIQUE ET SUPPORT DE STOCKAGE
(ZH) 图像的描述语句定位方法及装置、电子设备和存储介质
Abstract
(EN)
The present application relates to a method and apparatus for positioning a descriptive statement in an image, an electronic device, and a storage medium. The method comprises: analyzing a descriptive statement to be analyzed and an image to be analyzed, and obtaining a plurality of statement attention weights of the descriptive statement to be analyzed and a plurality of image attention weights of the image to be analyzed; according to the plurality of statement attention weights and main features, location features and relationship features of the image to be analyzed, acquiring a plurality of first match scores; according to the plurality of first match scores and the plurality of image attention weights, acquiring a second match score between the descriptive statement to be analyzed and the image to be analyzed; and according to the second match score, determining a positioning result of the descriptive statement to be analyzed in the image to be analyzed.
(FR)
La présente invention concerne un procédé et un appareil de positionnement d'un énoncé descriptif dans une image, un dispositif électronique et un support de stockage. Le procédé consiste à : analyser un énoncé descriptif à analyser et une image à analyser et obtenir une pluralité de pondérations d'attention d'énoncé de l'énoncé descriptif à analyser et une pluralité de pondérations d'attention d'image de l'image à analyser ; en fonction de la pluralité de pondérations d'attention d'énoncé et de caractéristiques principales, de caractéristiques d'emplacement et de caractéristiques de relation de l'image à analyser, acquérir une pluralité de premiers scores de correspondance ; en fonction de la pluralité de premiers scores de correspondance et de la pluralité de pondérations d'attention d'image, acquérir un second score de correspondance entre l'énoncé descriptif à analyser et l'image à analyser ; et, en fonction du second score de correspondance, déterminer un résultat de positionnement de l'énoncé descriptif à analyser dans l'image à analyser.
(ZH)
本申请涉及一种图像的描述语句定位方法及装置、电子设备和存储介质。该方法包括:对待分析描述语句与待分析图像进行分析,获得待分析描述语句的多个语句注意力权重及待分析图像的多个图像注意力权重;根据多个语句注意力权重及待分析图像的主体特征、位置特征及关系特征,获得多个第一匹配得分;根据多个第一匹配得分以及多个图像注意力权重,获得待分析描述语句与待分析图像之间的第二匹配得分;根据第二匹配得分,确定待分析描述语句在待分析图像中的定位结果。
Also published as
KRKR1020207008623
Latest bibliographic data on file with the International Bureau