Hugging Face's logo

KBlueLeaf
/
TTVidT

Video Classification
Transformers
Safetensors
ttvidt
feature-extraction
video
video-representation-learning
self-supervised-learning
motion
temporal-modeling
dinov3
vision-transformer
custom_code
Eval Results (legacy)
Model card Files
xet
 Community
KBlueLeaf commited on
Commit
3c7a789
·
verified ·
1 Parent(s): 930b76b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -89,7 +89,10 @@ model-index:
89
 
90
  </div>
91
 
92
- ![TT-VidT overview](assets/overview.png)
 
 
 
93
 
94
  **TT-VidT** is a self-supervised video encoder built for *motion*. A DINOv3 ViT-B/16
95
  processes every frame independently (the appearance path), while a compact
 
89
 
90
  </div>
91
 
92
+ <!-- ![TT-VidT overview](assets/overview.png) -->
93
+
94
+
95
+ ![image](https://cdn-uploads.huggingface.co/production/uploads/630593e2fca1d8d92b81d2a1/JKhgNd-K2wnoaAp1fYwR2.png)
96
 
97
  **TT-VidT** is a self-supervised video encoder built for *motion*. A DINOv3 ViT-B/16
98
  processes every frame independently (the appearance path), while a compact