logo

For the Inventor, By the Inventor

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.

Patent No.:

US 12705874 B1

PDFFull Text
Date of Patent:
Aug. 11, 2026

Filed:

Nov. 17, 2023

Pixel-based machine-learned models for multimodal vision-language tasks

Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Michael Tobias Tschannen, Zurich, CH;

Neil Matthew Tinmouth Houlsby, Zurich, CH;

Basil Mustafa, Zurich, CH;

Assignee:

GOOGLE LLC, Mountain View, CA (US);

Attorney:

DORITY & MANNING P.A.

Primary Examiner:

Wassim Mahrouka

Int. Cl.
CPC ...
G06T 11/60 (2026.01); G06F 40/284 (2020.01); G06V 10/74 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/94 (2022.01); G06V 20/70 (2022.01);
U.S. Cl.
CPC ...
G06T 11/60 (2013.01); G06F 40/284 (2020.01); G06V 10/761 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 20/70 (2022.01); G06V 10/945 (2022.01);
Abstract

A first image and textual content associated with the first image is obtained. A second image that depicts the textual content associated with the first image is rendered. The first image and the second image are processed with a machine-learned encoding model to respectively obtain a first image embedding and a second image embedding for an image embedding space including a plurality of image embeddings. The machine-learned encoding model is trained based on a difference between the first image embedding and the second image embedding.

Find Patent Forward Citations

Tschannen, Michael. (2026). Pixel-based machine-learned models for multimodal vision-language tasks (U.S. Patent No. 12705874). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12705874

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…