List your company
ResearchFormerly WizWand

Video Action Recognition on Kinetics-400 (test)

85.3Top-1 AccuracyCAST
75.73278.21680.783.184Jul 13, 2023Aug 5, 2023Aug 28, 2023Sep 21, 2023Oct 14, 2023Nov 6, 2023Nov 30, 2023
Updated 8mo ago

Evaluation results

MethodLinks
CASTBackbone=CAST-B, Frames=16, Views=5x3, TFLOPs=5.87, Learnable Param (M)=45, Pre-training=VideoMAE pretrained on Kinetics-4002023.1185.3
AIMBackbone=ViT-B, Frames=32, Views=3x1, TFLOPs=2.43, Learnable Param (M)=112023.1184.7
X-CLIPBackbone=ViT-B, Frames=16, Views=4x3, TFLOPs=3.442023.1184.7
EVLBackbone=ViT-B, Frames=32, Views=3x1, TFLOPs=1.78, Learnable Param (M)=292023.1184.2
OMNIVOREBackbone=Swin-B, Frames=322023.1184
Video-FocalNet-BPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=1492023.0783.6
Text4VisBackbone=ViT-B, Frames=16, Views=4x32023.1183.6
Video SwinBackbone=Swin-L, Frames=32, Views=4x3, TFLOPs=7.25, Learnable Param (M)=1972023.1183.1
Uniformer-BPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=2592023.0783
UniFormerBackbone=Hybrid-B, Frames=32, Views=4x3, TFLOPs=3.12, Learnable Param (M)=502023.1183
MViTv2-BViews=5 x 1, FLOPs (G/view)=2262023.0782.9
Video-Swin-BPre-training=ImageNet-21K, Views=4 x 3, FLOPs (G/view)=2822023.0782.7
ST-AdapterBackbone=ViT-B, Frames=32, Views=3x1, TFLOPs=1.822023.1182.7
MTV-B (320p)Pre-training=ImageNet-21K, Views=4 x 3, FLOPs (G/view)=9672023.0782.4
MTV-HRBackbone=MTV-B, Frames=32, Views=4x3, TFLOPs=11.16, Learnable Param (M)=3102023.1182.4
MTV-BPre-training=ImageNet-21K, Views=4 x 3, FLOPs (G/view)=3992023.0781.8
ViViT-L FEPre-training=ImageNet-21K, Views=1 x 3, FLOPs (G/view)=39802023.0781.7
VIVIT FEBackbone=ViT-L, Frames=128, Views=1x3, TFLOPs=11.94, Learnable Param (M)=3112023.1181.7
MoViNet-A6Pre-training=ImageNet-21K, Views=1 x 1, FLOPs (G/view)=3902023.0781.5
MoViNetBackbone=MoViNet-A6, Frames=120, Views=1x1, TFLOPs=0.392023.1181.5
VideoMAEBackbone=ViT-B, Frames=16, Views=5x3, TFLOPs=2.7, Learnable Param (M)=872023.1181.5
Video-FocalNet-SPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=1242023.0781.4
MViTv1-BViews=3 x 3, FLOPs (G/view)=4552023.0781.2
MFormer-HRPre-training=ImageNet-21K, Views=10 x 3, FLOPs (G/view)=9592023.0781.1
TimeSformer-LPre-training=ImageNet-21K, Views=1 x 3, FLOPs (G/view)=23802023.0780.7
TimeSformerBackbone=ViT-L, Frames=96, Views=1x3, TFLOPs=25.06, Learnable Param (M)=4302023.1180.7
Video-Swin-SPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=1662023.0780.6
Video-Swin-BPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=2822023.0780.6
BEVTBackbone=Swin-B, Frames=32, Views=4x3, TFLOPs=3.38, Learnable Param (M)=882023.1180.6
OmniSourcePre-training=ImageNet-21K2023.0780.5
X3D-XXLPre-training=ImageNet-21K, Views=10 x 3, FLOPs (G/view)=1942023.0780.4
MVITBackbone=ViT-B, Frames=32, Views=5x1, TFLOPs=0.85, Learnable Param (M)=372023.1180.2
MFormerBackbone=ViT-L, Frames=32, Views=10x3, TFLOPs=35.552023.1180.2
SlowFast R101-NLPre-training=ImageNet-21K, Views=10 x 3, FLOPs (G/view)=2342023.0779.8
Video-FocalNet-TPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=632023.0779.8
SlowFastBackbone=ResNet101, Frames=80, Views=10x3, TFLOPs=7.022023.1179.8
LGD-3D R101Pre-training=ImageNet-21K2023.0779.4
VidTR-LPre-training=ImageNet-21K, Views=10 x 3, FLOPs (G/view)=3512023.0779.1
X3DBackbone=X3D-XL, Frames=16, Views=10x3, TFLOPs=1.452023.1179.1
Video-Swin-TPre-training=ImageNet-1K, Views=4 x 3, FLOPs (G/view)=882023.0778.8
I3D NLPre-training=ImageNet-21K, Views=10 x 3, FLOPs (G/view)=3592023.0777.7
CLIP*Backbone=ViT-B, Frames=8, Views=5x3, TFLOPs=2.2, Learnable Param (M)=862023.1177.3
TSM-ResNeXt-101Pre-training=ImageNet-21K2023.0776.3
TEAPre-training=ImageNet-21K, Views=10 x 3, FLOPs (G/view)=702023.0776.1