Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,9 @@ license: apache-2.0
|
|
| 3 |
---
|
| 4 |
# Model Details
|
| 5 |
|
|
|
|
|
|
|
|
|
|
| 6 |
Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "[Perception Encoder: The best visual embeddings
|
| 7 |
are not at the output of the network](https://ai.meta.com/research/publications/perception-encoder-the-best-visual-embeddings-are-not-at-the-output-of-the-network/)".
|
| 8 |
|
|
|
|
| 3 |
---
|
| 4 |
# Model Details
|
| 5 |
|
| 6 |
+
[\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181)
|
| 7 |
+
[\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
|
| 8 |
+
|
| 9 |
Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "[Perception Encoder: The best visual embeddings
|
| 10 |
are not at the output of the network](https://ai.meta.com/research/publications/perception-encoder-the-best-visual-embeddings-are-not-at-the-output-of-the-network/)".
|
| 11 |
|