Patent · US Active

Temporal contrastive learning for semi-supervised video action recognition

US12067082B2 · kind B2 · utility

0Cited by
4References
20Claims
0Family size

Assignees

Inventors

Key dates

Filing dateOct 29, 2021
Grant dateAug 20, 2024
Priority date
Expiry dateJul 21, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A base pathway of a computerized two-pathway video action recognition model is trained using a plurality of labeled video samples. The base pathway is trained using a plurality of unlabeled video samples at a first framerate. An auxiliary pathway of the computerized two-pathway video action recognition model is trained using a plurality of the unlabeled video samples at a second framerate, the second framerate being slower than the first framerate, wherein the training of the base pathway and the training of the auxiliary pathway result in a trained computerized two-pathway video action recognition model. A candidate video is categorized using the trained computerized two-pathway video action recognition model and the categorized candidate video is stored in a computer-accessible video database system for information retrieval.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.