Hugging Face's logo

ICML2022
/
TimeIsMattEr

video-action-recognition
Model card Files Community
sm3199 commited on
Commit
e71f549
•
1 Parent(s): 51a245d

Upload XViT_TIME.pyth

Browse files

X-ViT+TIME model trained on the paper "Time Is MattEr: Temporal Self-supervision for Video Transformers" (https://arxiv.org/abs/2207.09067)

Files changed (2) hide show
  1. .gitattributes +1 -0
  2. XViT_TIME.pyth +3 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ TimeSformer_TIME.pyth filter=lfs diff=lfs merge=lfs -text
34
  Motionformer.pyth filter=lfs diff=lfs merge=lfs -text
35
  Motionformer_TIME.pyth filter=lfs diff=lfs merge=lfs -text
36
  XViT.pyth filter=lfs diff=lfs merge=lfs -text
 
 
34
  Motionformer.pyth filter=lfs diff=lfs merge=lfs -text
35
  Motionformer_TIME.pyth filter=lfs diff=lfs merge=lfs -text
36
  XViT.pyth filter=lfs diff=lfs merge=lfs -text
37
+ XViT_TIME.pyth filter=lfs diff=lfs merge=lfs -text
XViT_TIME.pyth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84120d9cf020821adf19ba5d692f26c3717cf12492648bfac4c3dabf512d5a3b
3
+ size 384049361