alisalam commited on
Commit
d191b8e
·
verified ·
1 Parent(s): 660dbcd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ Pre-trained checkpoint for **"LookWhen? Fast Video Recognition by Learning When,
15
  and What to Compute"** ([arXiv:2605.06809](https://arxiv.org/abs/2605.06809)).
16
 
17
  LookWhen splits video recognition in two: a shallow **selector** scores every patch of a
18
- 2x-downscaled clip, and a deep **extractor** processes only the top-K of them while still
19
  predicting features of the whole video.
20
 
21
  This is the model used throughout the paper: ViT-B/16, pre-trained for 20 epochs on
 
15
  and What to Compute"** ([arXiv:2605.06809](https://arxiv.org/abs/2605.06809)).
16
 
17
  LookWhen splits video recognition in two: a shallow **selector** scores every patch of a
18
+ 2x-downscaled (2x in each dimension) clip, and a deep **extractor** processes only the top-K of them while still
19
  predicting features of the whole video.
20
 
21
  This is the model used throughout the paper: ViT-B/16, pre-trained for 20 epochs on