VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Paper • 2203.12602 • Published • 3
VideoMAE
VideoMAE Pre-trained Models
-
-
MCG-NJU/videomae-base
Video Classification • 94.2M • Updated • 63.7k • 51 -
MCG-NJU/videomae-base-finetuned-kinetics
Video Classification • 86.5M • Updated • 34.7k • 48 -
MCG-NJU/videomae-base-finetuned-ssv2
Video Classification • Updated • 1.37k • 7 -
MCG-NJU/videomae-large
Video Classification • 0.3B • Updated • 59.4k • 37 -
MCG-NJU/videomae-large-finetuned-kinetics
Video Classification • 0.3B • Updated • 7.88k • 14 -
MCG-NJU/videomae-small-finetuned-kinetics
Video Classification • Updated • 9.2k • 1 -
MCG-NJU/videomae-small-finetuned-ssv2
Video Classification • Updated • 767 -
MCG-NJU/videomae-huge-finetuned-kinetics
Video Classification • Updated • 302 • 4