Patent · US Active

Systems and methods for classifying activities captured within images

US10185895B1 · kind B1 · utility

4Cited by
27References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 23, 2017
Grant dateJan 22, 2019
Priority date
Expiry dateJun 3, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An image including a visual capture of a scene may be accessed. The image may be processed through a convolutional neural network. The convolutional neural network may generate a set of two-dimensional feature maps based on the image. The set of two-dimensional feature maps may be processed through a contextual long short-term memory unit. The contextual long short-term memory unit may generate a set of two-dimensional outputs based on the set of two-dimensional feature maps. A set of attention-masks for the image may be generated based on the set of two-dimensional outputs and the set of two-dimensional feature maps. The set of attention-masks may define dimensional portions of the image. The scene may be classified based on the two-dimensional outputs.

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