Dense captioning with joint interference and visual context
US10198671B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 10, 2016 |
| Grant date | Feb 5, 2019 |
| Priority date | — |
| Expiry date | Feb 9, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2210/12
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A dense captioning system and method is provided for processing an image to produce a feature map of the image, analyzing the feature map to generate proposed bounding boxes for a plurality of visual concepts within the image, analyzing the feature map to determine a plurality of region features of the image, and analyzing the feature map to determine a context feature for the image. For each region feature of the plurality of region features of the image, the dense captioning system further provides for analyzing the region feature to determine a detection score for the region feature, calculating a caption for a bounding box for a visual concept in the image using the region feature and the context feature, and localizing the visual concept by adjusting the bounding box around the visual concept based on the caption to generate an adjusted bounding box for the visual concept.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.