The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 23, 2025

Filed:

Jul. 10, 2023
Applicants:

Hon Hai Precision Industry Co., Ltd., New Taipei, TW;

Foxconn Technology Group Co., Ltd., Guangdong Province, CN;

Inventors:

Jia Wang, New Taipei, TW;

Jing-Cheng Ke, New Taipei, TW;

Wen-Huang Cheng, New Taipei, TW;

Hong-Han Shuai, New Taipei, TW;

Yung-Hui Li, New Taipei, TW;

Assignees:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/295 (2020.01); G06V 30/146 (2022.01); G06V 30/19 (2022.01);
U.S. Cl.
CPC ...
G06F 40/295 (2020.01); G06V 30/147 (2022.01); G06V 30/19187 (2022.01);
Abstract

A recognition method includes the following steps. A text is analyzed by a language recognition network to generate an entity feature, a relation feature and an overall feature. An input image is analyzed by an object detection network to generate candidate regions. Node features, aggregated edge features and compound features are generated by an enhanced cross-modal graph attention network according to the entity feature, the relation feature, the candidate regions and the overall feature. The entity feature and the relation feature are matched to the node features and the aggregated edge features to generate the first scores. The overall feature is matched to the compound features to generate second scores. Final scores corresponding to the candidate regions are generated according to the first scores and the second scores.


Find Patent Forward Citations

Loading…