VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Paper • 2203.12602 • Published • 6
VideoMAE
VideoMAE Pre-trained Models
-
-
MCG-NJU/videomae-base
Video Classification • 94.2M • Updated • 331k • 55 -
MCG-NJU/videomae-base-finetuned-kinetics
Video Classification • 86.5M • Updated • 55.3k • 52 -
MCG-NJU/videomae-base-finetuned-ssv2
Video Classification • Updated • 1.32k • 7 -
MCG-NJU/videomae-large
Video Classification • 0.3B • Updated • 5.42k • 37 -
MCG-NJU/videomae-large-finetuned-kinetics
Video Classification • 0.3B • Updated • 10.7k • 14 -
MCG-NJU/videomae-small-finetuned-kinetics
Video Classification • Updated • 2.67k • 2 -
MCG-NJU/videomae-small-finetuned-ssv2
Video Classification • Updated • 817 -
MCG-NJU/videomae-huge-finetuned-kinetics
Video Classification • Updated • 326 • 4