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. 03, 2024

Filed:

Aug. 30, 2021
Applicant:

Meta Platforms, Inc., Menlo Park, CA (US);

Inventors:

Gediminas Bertasius, Boston, MA (US);

Heng Wang, Mountain View, CA (US);

Lorenzo Torresani, Norwich, VT (US);

Assignee:

Meta Platforms, Inc., Menlo Park, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06V 10/50 (2022.01); G06F 18/21 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/56 (2022.01); G06V 10/75 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01);
U.S. Cl.
CPC ...
G06V 20/41 (2022.01); G06F 18/21 (2023.01); G06N 20/00 (2019.01); G06V 10/56 (2022.01); G06V 10/751 (2022.01); G06V 20/48 (2022.01); G06V 10/759 (2022.01);
Abstract

In one embodiment, a method includes accessing a stream of F video frames, where each of the F video frames includes N patches that are non-overlapping, generating an initial embedding vector for each of the N×F patches in the F video frames, generating a classification embedding by processing the generated N×F initial embedding vectors using a self-attention-based machine-learning model that computes a temporal attention and a spatial attention for each of the N×F patches, and determining a class of the stream of video frames based on the generated classification embedding.


Find Patent Forward Citations

Loading…