On-line action detection using recurrent neural network
US10789482B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 28, 2017 |
| Grant date | Sep 29, 2020 |
| Priority date | — |
| Expiry date | Aug 10, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V40/23
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In implementations of the subject matter described herein, an action detection scheme using a recurrent neural network (RNN) is proposed. Representation information of an incoming frame of a video and a predefined action label for the frame are obtained to train a learning network including RNN elements and a classification element. The representation information represents an observed entity in the frame. Specifically, parameters for the RNN elements are determined based on the representation information and the predefined action label. With the determined parameters, the RNN elements are caused to extract features for the frame based on the representation information and features for a preceding frame. Parameters for the classification element are determined based on the extracted features and the predefined action label. The classification element with the determined parameters generates a probability of the frame being associated with the predefined action label. The parameters for the RNN elements are updated according to the probability.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.