Patent · US Active

Self-attention deep neural network for action recognition in surveillance videos

US10089556B1 · kind B1 · utility

34Cited by
3References
8Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJun 12, 2017
Grant dateOct 2, 2018
Priority date
Expiry dateJun 12, 2037

Classification

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

Abstract

An artificial neural network for analyzing input data, the input data being a 3D tensor having D channels, such as D frames of a video snippet, to recognize an action therein, including: D spatial transformer modules, each generating first and second spatial transformations and corresponding first and second attention windows using only one of the D channels, and transforming first and second regions of each of the D channels corresponding to the first and second attention windows to generate first and second patch sequences; first and second CNNs, respectively processing a concatenation of the D first patch sequences and a concatenation of the D second patch sequences; and a classification network receiving a concatenation of the outputs of the first and second CNNs and the D sets of transformation parameters of the first transformation outputted by the D spatial transformer modules, to generate a predicted action class.

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