Self-attention deep neural network for action recognition in surveillance videos
US10089556B1 · kind B1 · utility
Assignee
Inventor
Key dates
| Filing date | Jun 12, 2017 |
| Grant date | Oct 2, 2018 |
| Priority date | — |
| Expiry date | Jun 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.