Add pipeline tag and project URL (#1)
Browse files- Add pipeline tag and project URL (f1ebc681f0cd27604bb96b2d8f48dbc72ae7b05d)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
|
@@ -1,11 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
library_name: perception-encoder
|
|
|
|
|
|
|
| 4 |
---
|
|
|
|
| 5 |
# Model Details
|
| 6 |
|
| 7 |
-
[
|
| 8 |
-
[
|
| 9 |
|
| 10 |
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
|
| 11 |
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/)".
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: perception-encoder
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
pipeline_tag: image-feature-extraction
|
| 5 |
---
|
| 6 |
+
|
| 7 |
# Model Details
|
| 8 |
|
| 9 |
+
[\\[📃 Tech Report\\]](https://arxiv.org/abs/2504.13181)
|
| 10 |
+
[\\[📂 Github\\]](https://github.com/facebookresearch/perception_models/)
|
| 11 |
|
| 12 |
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
|
| 13 |
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/)".
|