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:
Jun. 23, 2026

Filed:

Jan. 04, 2023
Applicant:

Salesforce, Inc., San Francisco, CA (US);

Inventors:

Jiaxian Guo, Sydney, AU;

Junnan Li, Singapore, SG;

Chu Hong Hoi, Singapore, SG;

Assignee:

Salesforce, Inc., San Francisco, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 10/25 (2022.01); G06F 16/583 (2019.01); G06N 3/042 (2023.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06N 3/042 (2023.01); G06F 16/583 (2019.01); G06V 10/25 (2022.01); G06V 10/82 (2022.01);
Abstract

Embodiments described herein provide systems and methods for providing zero-shot visual question answering. A first image and a first question relating to a visual content of the first image are received. One or more image captions relevant to the first question are determined using a visual-language neural model by determining portions of the first image relevant to the first question. Answer candidates are generated using the one or more image captions, answer candidates. Synthetic question-answer pairs are generated using synthetic questions generated using the answer candidates and the answer candidates. A prompt is generated by concatenating the synthetic question-answer pairs. A first answer to the first question is generated using a language network model using an input of the first question prepended with the prompt.


Find Patent Forward Citations

Loading…