List your company

Action Classification on Kinetics-400 (test)

87.2AccuracyVideoMAE V2
54.33662.86871.479.932Mar 29, 2023Mar 31, 2023Apr 3, 2023Apr 5, 2023Apr 8, 2023Apr 10, 2023Apr 13, 2023

Evaluation results

MethodLinks
VideoMAE V2Backbone=ViT-g, pre-train data=UnlabeledHybrid, data size=1.35M, epoch=1200, Input Resolution=16x224x224, Sampling Stride=42023.0387.283.9
VideoMAE V2Backbone=ViT-H, pre-train data=UnlabeledHybrid, data size=1.35M, epoch=1200, Input Resolution=16x224x224, Sampling Stride=42023.0386.983.2
VideoMAE V1Backbone=ViT-H, pre-train data=Kinetics400, data size=0.24M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0386.6—
VideoMAE V2Backbone=ViT-L, pre-train data=UnlabeledHybrid, data size=1.35M, epoch=1200, Input Resolution=16x224x224, Sampling Stride=42023.0385.481.3
VideoMAE V1Backbone=ViT-L, pre-train data=Kinetics400, data size=0.24M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0385.2—
MAE-STBackbone=ViT-H, pre-train data=Kinetics400, data size=0.24M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0385.1—
MAE-STBackbone=ViT-L, pre-train data=Kinetics400, data size=0.24M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0384.8—
MAE-STBackbone=ViT-L, pre-train data=IG-uncurated, data size=1M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0384.4—
VideoMAE V1Backbone=ViT-B, pre-train data=Kinetics400, data size=0.24M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0381.5—
VideoMAE V2Backbone=ViT-B, pre-train data=UnlabeledHybrid, data size=1.35M, epoch=1200, Input Resolution=16x224x224, Sampling Stride=42023.0381.577
MAE-STBackbone=ViT-B, pre-train data=Kinetics400, data size=0.24M, epoch=1600, Input Resolution=16x224x224, Sampling Stride=42023.0381.3—
VFCZero-shot=true2023.0458.8—
BaselineZero-shot=true2023.0455.6—