Commit
•
4cf68d4
1
Parent(s):
6ce6524
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,11 @@ preserve 90%+ of the full embedding quality.
|
|
| 20 |
|
| 21 |
The full embedding model sets new state-of-the-art for multilingual image and text retrieval on both XTD10 and Crossmodal-3600.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## How to use
|
| 24 |
|
| 25 |
### Variable resolutions
|
|
|
|
| 20 |
|
| 21 |
The full embedding model sets new state-of-the-art for multilingual image and text retrieval on both XTD10 and Crossmodal-3600.
|
| 22 |
|
| 23 |
+
| Dataset | image retrieval R@1, avg | text retrieval R@1, avg | image retrieval R@5, avg | text retrieval R@5, avg | image retrieval R@10, avg | text retrieval R@10, avg |
|
| 24 |
+
|-----------------|:------------------------:|:------------------:|:-------------------:|:------------------:|:--------------------:|:-------------------:|
|
| 25 |
+
| Crossmodal-3600 | 0.6079 | 0.5741 | 0.8333 | 0.8174 | 0.8922 | 0.8816 |
|
| 26 |
+
| XTD10 | 0.6997 | 0.6433 | 0.8988 | 0.8848 | 0.9503 | 0.9449 |
|
| 27 |
+
|
| 28 |
## How to use
|
| 29 |
|
| 30 |
### Variable resolutions
|