Commit
•
3946810
1
Parent(s):
19be54f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
|
| 2 |
# Visual semantic with BERT-CNN
|
| 3 |
To take advantage of the overlapping between the visual context and the caption, and to extract global information from each visual, we use BERT as an embedding layer followed by a shallow CNN (tri-gram kernel) (Kim,204).
|
|
|
|
|
|
|
| 4 |
|
| 5 |
|
| 6 |
This model can be used to assign an object-to-caption relatedness score, which is valuable for
|
|
|
|
| 1 |
|
| 2 |
# Visual semantic with BERT-CNN
|
| 3 |
To take advantage of the overlapping between the visual context and the caption, and to extract global information from each visual, we use BERT as an embedding layer followed by a shallow CNN (tri-gram kernel) (Kim,204).
|
| 4 |
+
|
| 5 |
+
For datasets that are less than 100K please have look at our [shallow model](https://github.com/ahmedssabir/Semantic-Relatedness-Based-Reranker-for-Text-Spotting)
|
| 6 |
|
| 7 |
|
| 8 |
This model can be used to assign an object-to-caption relatedness score, which is valuable for
|