Patent · US Active

Weakly supervised natural language localization networks for video proposal prediction based on a text query

US11687588B2 · kind B2 · utility

0Cited by
7References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 5, 2019
Grant dateJun 27, 2023
Priority date
Expiry dateSep 14, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V20/46
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods are provided for weakly supervised natural language localization (WSNLL), for example, as implemented in a neural network or model. The WSNLL network is trained with long, untrimmed videos, i.e., videos that have not been temporally segmented or annotated. The WSNLL network or model defines or generates a video-sentence pair, which corresponds to a pairing of an untrimmed video with an input text sentence. According to some embodiments, the WSNLL network or model is implemented with a two-branch architecture, where one branch performs segment sentence alignment and the other one conducts segment selection. These methods and systems are specifically used to predict how a video proposal matches a text query using respective visual and text features.

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