Commit
·
d95a7dc
1
Parent(s):
c48dad0
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ Like it's image-only counterpart, CLIP, VideoCLIP enables you to compute a singl
|
|
| 8 |
VideoCLIP uses a Video Q-Former to aggregate frame-level embeddings temporally into a single embedding, maintaining relevance of the underlying content. The resulting embedding is then trained with contrastive loss + captioning loss to match it's corresponding text.
|
| 9 |
|
| 10 |
# Usage
|
| 11 |
-
|
| 12 |
```
|
| 13 |
# Load model.
|
| 14 |
import video_clip
|
|
|
|
| 8 |
VideoCLIP uses a Video Q-Former to aggregate frame-level embeddings temporally into a single embedding, maintaining relevance of the underlying content. The resulting embedding is then trained with contrastive loss + captioning loss to match it's corresponding text.
|
| 9 |
|
| 10 |
# Usage
|
| 11 |
+
Link to github to run the model: [link](https://github.com/AskYoutubeAI/AskVideos-VideoCLIP).
|
| 12 |
```
|
| 13 |
# Load model.
|
| 14 |
import video_clip
|