WO2023147764 - SYSTEMS, METHODS, AND MEDIA FOR MAIN GROUP IDENTIFICATION IN IMAGES VIA SOCIAL RELATION RECOGNITION
National phase entry is expected:
Publication Number
WO/2023/147764
Publication Date
10.08.2023
International Application No.
PCT/CN2023/073554
International Filing Date
28.01.2023
Title **
[English]
SYSTEMS, METHODS, AND MEDIA FOR MAIN GROUP IDENTIFICATION IN IMAGES VIA SOCIAL RELATION RECOGNITION
[French]
SYSTÈMES, PROCÉDÉS ET SUPPORTS D'IDENTIFICATION DE GROUPE PRINCIPAL DANS DES IMAGES PAR RECONNAISSANCE DE RELATION SOCIALE
Applicants **
HUAWEI TECHNOLOGIES CO., LTD.
Huawei Administration Building
Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
Inventors
LU, Minlong
Suite 400, 303 Terry Fox Drive
Kanata Ottawa, Ontario 231, CA
CANNONS, Kevin James
Suite 400, 303 Terry Fox Drive
Kanata Ottawa, Ontario 231, CA
XU, Zhan
Huawei Administration Building
Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
Priority Data
17/592,790
04.02.2022
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| * | |
International Searching Authority |
CNIPA
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Translation |
|
Recalculate
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing | 1429 | |
| EPO | Filing, Examination | 8567 | |
| Japan | Filing | 594 | |
| South Korea | Filing | 575 | |
| USA | Filing, Examination | 2710 |
Total: 13875 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Systems, methods, and computer-readable media for identifying a main group of people in an image via social relation recognition. The main group of people is identified within an image by identifying social relationships between people visible in the image. The identification of social relationships is performed by a Social Relation Recognition Network (SRRN) trained using deep learning. The SRRN combines two techniques for group identification, First Glance and Graph Reasoning, and fuses their outputs to generate a prediction of group membership. A group refinement module improves and filters the group membership after identification of an initial main group.[French]
La présente invention concerne des systèmes, des procédés et des supports lisibles par ordinateur permettant d'identifier un groupe principal de personnes dans une image par l'intermédiaire d'une reconnaissance de relation sociale. Le groupe principal de personnes est identifié dans une image par identification de relations sociales entre des personnes visibles dans l'image. L'identification de relations sociales est effectuée par un réseau de reconnaissance de relations sociales (SRRN) entraîné à l'aide d'un apprentissage profond. Le SRRN combine deux techniques d'identification de groupe, premier coup d'œil et raisonnement de graphe, et fusionne leurs résultats pour générer une prédiction d'appartenance à un groupe. Un module d'affinement de groupe améliore et filtre l'appartenance à un groupe après l'identification d'un groupe principal initial.