Hugging Face's logo

Sense-X
/
uniformer_video

Video Classification
vision
Model card Files
xet
 Community
Andy1621 commited on
Commit
0bc4e4e
·
1 Parent(s): b312635

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ It also achieves **53.8** box AP and **46.4** mask AP on COCO object detection t
31
  **50.8** mIoU on ADE20K semantic segmentation task,
32
  and **77.4** AP on COCO pose estimation task.
33
 
34
- ![model image](https://huggingface.co/Sense-X/uniformer_video/blob/main/framework.png)
35
 
36
  [Source](https://paperswithcode.com/paper/uniformer-unifying-convolution-and-self)
37
 
 
31
  **50.8** mIoU on ADE20K semantic segmentation task,
32
  and **77.4** AP on COCO pose estimation task.
33
 
34
+ ![teaser](framework.png)
35
 
36
  [Source](https://paperswithcode.com/paper/uniformer-unifying-convolution-and-self)
37