Add pipeline tag, add link to paper
Browse filesThis PR ensures the model can be found at https://huggingface.co/papers/2412.00927 as well as https://huggingface.co/models?pipeline_tag=video-text-to-text&sort=trending
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
---
|
| 4 |
-
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
pipeline_tag: video-text-to-text
|
| 4 |
---
|
| 5 |
+
|
| 6 |
+
This repository contains the model described in [VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation](https://huggingface.co/papers/2412.00927).
|