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:
Apr. 14, 2025

Filed:

Mar. 06, 2023
Applicant:

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

Inventors:

Xiao Xia Mao, Shanghai, CN;

Wei Jun Zheng, Shanghai, CN;

Shi Hui Gui, Shanghai, CN;

Xiao Feng Ji, Shanghai, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 20/70 (2021.12); G06F 16/78 (2018.12); G06F 40/30 (2019.12); G06V 10/74 (2021.12); G06V 10/774 (2021.12); G06V 10/82 (2021.12); G06V 30/19 (2021.12);
U.S. Cl.
CPC ...
G06F 16/78 (2018.12); G06F 40/30 (2019.12); G06V 10/761 (2021.12); G06V 10/774 (2021.12); G06V 10/82 (2021.12); G06V 20/70 (2021.12); G06V 30/19093 (2021.12);
Abstract

A method, computer system, and a computer program product are provided for training a neural network for finding queried videos. Two pairs of video clips and associated text are obtained from a first dataset and a second dataset. The first dataset is used to train two video encoders by providing the video clips to the encoders as input and providing the outputs to a cosine similarity calculator. The second dataset is used to train a multi-mentor paradigm with two mentors. A first mentor and a second mentor are each provided the pair of textual data inputs. The first mentor provides a similarity value comparison, and the second mentor provides a word mover distance. Using the output from the multi-mentor paradigm and the encoders, a contrastive loss is calculated and used to provide contrastive learning of video features by differentiating similarity and dissimilarity of the video clips.


Find Patent Forward Citations

Loading…