VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Paper
• 2203.12602 • Published
• 1
VideoMAE
VideoMAE Pre-trained Models
-
-
MCG-NJU/videomae-base
Video Classification • 94.2M • Updated • 45.8k • 50 -
MCG-NJU/videomae-base-finetuned-kinetics
Video Classification • 86.5M • Updated • 23.4k • 45 -
MCG-NJU/videomae-base-finetuned-ssv2
Video Classification • Updated • 1.92k • 7 -
MCG-NJU/videomae-large
Video Classification • 0.3B • Updated • 3.64k • 37 -
MCG-NJU/videomae-large-finetuned-kinetics
Video Classification • 0.3B • Updated • 1.76k • 13 -
MCG-NJU/videomae-small-finetuned-kinetics
Video Classification • Updated • 1.64k • 1 -
MCG-NJU/videomae-small-finetuned-ssv2
Video Classification • Updated • 839 -
MCG-NJU/videomae-huge-finetuned-kinetics
Video Classification • Updated • 1.17k • 4