Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Video
/
Kinetics-400
Video on Kinetics-400
Metric: Parameters (M) (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide extra data
Export CSV
Sort:
Parameters (M) (best first)
Parameters (M) (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Parameters (M)
▼
Extra Data
Paper
Date
↕
Code
1
TubeViT-H (ImageNet-1k)
632
No
Rethinking Video ViTs: Sparse Video Tubes for Jo...
2022-12-06
Code
2
UniFormerV2-L (ViT-L, 336)
354
Yes
-
-
Code
3
TubeVit-L (ImageNet-1k)
307
No
Rethinking Video ViTs: Sparse Video Tubes for Jo...
2022-12-06
Code
4
Unmasked Teacher (ViT-L)
304
No
Unmasked Teacher: Towards Training-Efficient Vid...
2023-03-28
Code
5
TimeSformer-L
121.4
No
Is Space-Time Attention All You Need for Video U...
2021-02-09
Code
6
FluxViT-B
97
Yes
Make Your Training Flexible: Towards Deployment-...
2025-03-18
Code
7
AMD(ViT-B/16)
87
No
Asymmetric Masked Distillation for Pre-Training ...
2023-11-06
-
8
TubeVit-B (ImageNet-1k)
86
No
Rethinking Video ViTs: Sparse Video Tubes for Jo...
2022-12-06
Code
9
SlowFast-8×8-R50
66.25
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
10
SlowFast-4×16-R50
34.48
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
11
Co Slow_64
32.45
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
12
Slow-8x8-R50
32.45
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
13
Co Slow_8
32.45
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
14
R(2+1)D-18_16
31.51
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
15
R(2+1)D-18_8
31.51
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
16
I3D-R50
28.04
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
17
Co I3D_8
28.04
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
18
Co I3D_64
28.04
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
19
FluxViT-S
24
Yes
Make Your Training Flexible: Towards Deployment-...
2025-03-18
Code
20
AMD(ViT-S/16)
22
No
Asymmetric Masked Distillation for Pre-Training ...
2023-11-06
-
21
RCU_8
12.8
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
22
Co X3D-L_64
6.15
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
23
X3D-L
6.15
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
24
Co X3D-L_16
6.15
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
25
Co X3D-M_64
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
26
Co X3D-S_64
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
27
X3D-M
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
28
X3D-S
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
29
Co X3D-M_16
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
30
Co X3D-S_13
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
31
X3D-XS
3.79
No
Continual 3D Convolutional Neural Networks for R...
2021-05-31
Code
#1
TubeViT-H (ImageNet-1k)
SOTA
632
Parameters (M)
· 2022-12-06
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Code
#2
UniFormerV2-L (ViT-L, 336)
354
Parameters (M)
· Extra Data
No paper
Code
#3
TubeVit-L (ImageNet-1k)
307
Parameters (M)
· 2022-12-06
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Code
#4
Unmasked Teacher (ViT-L)
304
Parameters (M)
· 2023-03-28
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Code
#5
TimeSformer-L
SOTA
121.4
Parameters (M)
· 2021-02-09
Is Space-Time Attention All You Need for Video Understanding?
Code
#6
FluxViT-B
97
Parameters (M)
· Extra Data
· 2025-03-18
Make Your Training Flexible: Towards Deployment-Efficient Video Models
Code
#7
AMD(ViT-B/16)
87
Parameters (M)
· 2023-11-06
Asymmetric Masked Distillation for Pre-Training Small Foundation Models
#8
TubeVit-B (ImageNet-1k)
86
Parameters (M)
· 2022-12-06
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Code
#9
SlowFast-8×8-R50
66.25
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#10
SlowFast-4×16-R50
34.48
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#11
Co Slow_64
32.45
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#12
Slow-8x8-R50
32.45
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#13
Co Slow_8
32.45
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#14
R(2+1)D-18_16
31.51
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#15
R(2+1)D-18_8
31.51
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#16
I3D-R50
28.04
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#17
Co I3D_8
28.04
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#18
Co I3D_64
28.04
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#19
FluxViT-S
24
Parameters (M)
· Extra Data
· 2025-03-18
Make Your Training Flexible: Towards Deployment-Efficient Video Models
Code
#20
AMD(ViT-S/16)
22
Parameters (M)
· 2023-11-06
Asymmetric Masked Distillation for Pre-Training Small Foundation Models
#21
RCU_8
12.8
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#22
Co X3D-L_64
6.15
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#23
X3D-L
6.15
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#24
Co X3D-L_16
6.15
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#25
Co X3D-M_64
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#26
Co X3D-S_64
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#27
X3D-M
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#28
X3D-S
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#29
Co X3D-M_16
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#30
Co X3D-S_13
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code
#31
X3D-XS
3.79
Parameters (M)
· 2021-05-31
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
Code