Update README.md
Browse files
README.md
CHANGED
@@ -83,7 +83,7 @@ print(results)
|
|
83 |
|
84 |
The BridgeTower model was pretrained on four public image-caption datasets:
|
85 |
- [Conceptual Captions (CC3M)](https://ai.google.com/research/ConceptualCaptions/)
|
86 |
-
- [Conceptual 12M (CC12M](https://github.com/google-research-datasets/conceptual-12m)
|
87 |
- [SBU Captions](https://www.cs.rice.edu/~vo9/sbucaptions/)
|
88 |
- [MSCOCO Captions](https://arxiv.org/pdf/1504.00325.pdf)
|
89 |
- [Visual Genome](https://visualgenome.org/)
|
|
|
83 |
|
84 |
The BridgeTower model was pretrained on four public image-caption datasets:
|
85 |
- [Conceptual Captions (CC3M)](https://ai.google.com/research/ConceptualCaptions/)
|
86 |
+
- [Conceptual 12M (CC12M)](https://github.com/google-research-datasets/conceptual-12m)
|
87 |
- [SBU Captions](https://www.cs.rice.edu/~vo9/sbucaptions/)
|
88 |
- [MSCOCO Captions](https://arxiv.org/pdf/1504.00325.pdf)
|
89 |
- [Visual Genome](https://visualgenome.org/)
|