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:
Mar. 11, 2025

Filed:

Mar. 11, 2021
Applicant:

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

Inventors:

Rameswar Panda, Medford, MA (US);

Richard Chen, Baldwin Place, NY (US);

Quanfu Fan, Lexington, MA (US);

Rogerio Schmidt Feris, West Hartford, CT (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 20/40 (2022.01); G06F 18/214 (2023.01); G06F 18/25 (2023.01); G06N 20/00 (2019.01);
U.S. Cl.
CPC ...
G06V 20/46 (2022.01); G06F 18/214 (2023.01); G06F 18/256 (2023.01); G06N 20/00 (2019.01); G06V 20/49 (2022.01);
Abstract

One embodiment of the invention provides a method for video recognition. The method comprises receiving an input video comprising a sequence of video segments over a plurality of data modalities. The method further comprises, for a video segment of the sequence, selecting one or more data modalities based on data representing the video segment. Each data modality selected is optimal for video recognition of the video segment. The method further comprises, for each data modality selected, providing at least one data input representing the video segment over the data modality selected to a machine learning model corresponding to the data modality selected, and generating a first type of prediction representative of the video segment via the machine learning model. The method further comprises determining a second type of prediction representative of the entire input video by aggregating all first type of predictions generated.


Find Patent Forward Citations

Loading…