Difference between revisions of "COCO"
From Security Vision
m (Text replacement - "--- By citebot ---" to "<div class="citebot" style="display:none;">") |
|||
| Line 29: | Line 29: | ||
[[CiteRef::linMicrosoftCOCOCommon2015]] | [[CiteRef::linMicrosoftCOCOCommon2015]] | ||
| − | + | <div class="citebot" style="display:none;"> | |
This page uses the following references: | This page uses the following references: | ||
Revision as of 17:19, 20 April 2024
Technical information:
| Full name | Microsoft COCO: Common Objects in Context |
|---|---|
| Country | |
| Contents | Uncontrolled |
| Images | 330,000 |
| Individuals | 250,000 |
| Runs database software | |
| URL"URL" is a type and predefined property provided by Semantic MediaWiki to represent URI/URL values. | https://cocodataset.org/ |
| Related Technology |
Developers and Users:
Description[edit | ]
COCO is a large-scale object detection, segmentation, and captioning dataset. COCO has several features:
Object segmentation Recognition in context Superpixel stuff segmentation 330K images (>200K labeled) 1.5 million object instances 80 object categories 91 stuff categories 5 captions per image 250,000 people with keypoints
References
- ^ | Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Bourdev, Lubomir and Girshick, Ross and Hays, James and Perona, Pietro and Ramanan, Deva and Zitnick, C. Lawrence and Dollár, Piotr. Microsoft COCO: Common Objects in Context. , 2015.