Invention Grant
- Patent Title: Forecasting multiple poses based on a graphical image
-
Application No.: US16057161Application Date: 2018-08-07
-
Publication No.: US10475207B2Publication Date: 2019-11-12
- Inventor: Jimei Yang , Yu-Wei Chao , Scott Cohen , Brian Price
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Kilpatrick Townsend & Stockton LLP
- Main IPC: G06T7/73
- IPC: G06T7/73 ; G06T7/246 ; G06N3/04 ; G06K9/00 ; G06K9/46 ; G06K9/62 ; G06N3/08

Abstract:
A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.
Public/Granted literature
- US20180357789A1 Forecasting Multiple Poses Based on a Graphical Image Public/Granted day:2018-12-13
Information query