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 12646232 B1

PDFFull Text
Date of Patent:
Jun. 02, 2026

Filed:

Feb. 06, 2024

Temporally consistent and semantics guided text-based video editing generative artificial intelligence (ai) model with improved initialization

Applicant:

Qualcomm Incorporated, San Diego, CA (US);

Inventors:

Hyojin Park, San Diego, CA (US);

Debasmit Das, San Diego, CA (US);

Munawar Hayat, San Diego, CA (US);

Fatih Murat Porikli, San Diego, CA (US);

Assignee:

QUALCOMM Incorporated, San Diego, CA (US);

Attorney:

Seyfarth Shaw LLP

Primary Examiner:

Grace Q Li

Int. Cl.
CPC ...
G06T 11/60 (2026.01); G06F 40/40 (2020.01); G06T 5/60 (2024.01); G06T 5/70 (2024.01); G06V 20/40 (2022.01); G06V 20/70 (2022.01);
U.S. Cl.
CPC ...
G06T 11/60 (2013.01); G06T 5/60 (2024.01); G06T 5/70 (2024.01); G06V 20/46 (2022.01); G06V 20/70 (2022.01); G06F 40/40 (2020.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract

A processor-implemented method performed for text-based video editing includes receiving a video input and a text prompt. The video input includes a sequence of video frames. Features of the video input are extracted to generate a latent representation of the video input. Noise is injected to the latent representation of the video input to generate a noise injected latent. The noise is conditioned on the video input. An artificial neural network (ANN) model processes the noise injected latent based on the text prompt to adapt the video input according to the text prompt.

Find Patent Forward Citations

Park, Hyojin. (2026). Temporally consistent and semantics guided text-based video editing generative artificial intelligence (ai) model with improved initialization (U.S. Patent No. 12646232). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12646232

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

Loading…