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 12555375 B1

Date of Patent:

Feb. 17, 2026

Filed:

Jul. 28, 2022

Temporal action localization with mutual task guidance

Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Bo Wu, Cambridge, MA (US);

Chuang Gan, Cambridge, MA (US);

Pin-Yu Chen, White Plains, NY (US);

Yang Zhang, Cambridge, MA (US);

Xin Zhang, Chappaqua, NY (US);

Assignee:

International Business Machines Corporation, Armonk, NY (US);

Attorney:

CHIP LAW GROUP

Primary Examiner:

Feng Niu

Int. Cl.

CPC ...

G06K 9/00 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01);

U.S. Cl.

CPC ...

G06V 20/41 (2022.01); G06V 10/82 (2022.01); G06V 20/46 (2022.01); G06V 20/49 (2022.01); G06V 40/20 (2022.01);

Abstract

A computer vision temporal action localization (TAL) computing tool and operations are provided. The TAL computing tool receives a coarse temporal bounding box, having a first start point and a first end point, for an action in the input video data, and a first set of logits, where each logit corresponds to a potential classification of the action in the input video data. The TAL computing tool executes a first engine on the coarse temporal bounding box to generate a second set of logits, and a second engine on the first set of logits to generate a refined temporal bounding box having a second start point and a second end point. The TAL computing tool performs the computer vision temporal action localization operation based on the second set of logits and the refined temporal bounding box to specify a temporal segment of the input video data corresponding to an action represented in the input video data, and a corresponding classification of the action represented in the temporal segment.

Find Patent Forward Citations

Wu, Bo. (2026). Temporal action localization with mutual task guidance (U.S. Patent No. 12555375). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12555375

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