Visual reference resolution using attention memory for visual dialog
US10726206B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 30, 2018 |
| Grant date | Jul 28, 2020 |
| Priority date | — |
| Expiry date | Apr 2, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/041
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A dialog engine configured to answer a sequence of questions related to an image. An attention module residing in the dialog engine includes an attention retrieval process and a tentative attention process. The attention retrieval process retrieves a relevant attention map that may have previously been used to answer a previous query. The tentative attention process generates a tentative attention map based on an image and other input parameters. The attention module combines the relevant attention map and the tentative attention map to generate a fused attention map. Based on the fused attention map, the dialog engine generates a response to the query. Finally, the dialog engine stores the fused attention map in an attention memory for use in answering future queries.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.