| X3D-L |
- Acc@1
- 69.29
- FLOPs (G) x views
- 19.17x1
- Parameters (M)
- 6.15
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| MARS+RGB+Flow (16 frames) |
- Acc@1
- 68.9
|
MARS: Motion-Augmented RGB Stream for Action Recognition 2019-06-01 |
코드 1 |
| SlowFast-8×8-R50 |
- Acc@1
- 68.45
- FLOPs (G) x views
- 66.25x1
- Parameters (M)
- 66.25
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| S3D-G (Flow, ImageNet pretrained) |
- Acc@1
- 68
- Acc@5
- 87.6
|
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification 2017-12-13 |
코드 1 · 코드 2 |
| R[2+1]D-Flow |
- Acc@1
- 67.5
- Acc@5
- 87.2
|
A Closer Look at Spatiotemporal Convolutions for Action Recognition 2017-11-30 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 |
| Slow-8x8-R50 |
- Acc@1
- 67.42
- FLOPs (G) x views
- 54.87x1
- Parameters (M)
- 32.45
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co X3D-S_64 |
- Acc@1
- 67.33
- FLOPs (G) x views
- 0.17x1
- Parameters (M)
- 3.79
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| X3D-M |
- Acc@1
- 67.24
- FLOPs (G) x views
- 4.97x1
- Parameters (M)
- 3.79
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| SlowFast-4×16-R50 |
- Acc@1
- 67.06
- FLOPs (G) x views
- 36.46x1
- Parameters (M)
- 34.48
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co Slow_8 |
- Acc@1
- 65.90
- FLOPs (G) x views
- 6.90x1
- Parameters (M)
- 32.45
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| MoViNet-A0 |
- Acc@1
- 65.8
- Acc@5
- 87.4
- FLOPs (G) x views
- 2.7x1
|
MoViNets: Mobile Video Networks for Efficient Video Recognition 2021-03-21 |
코드 1 · 코드 2 · 코드 3 |
| X3D-S |
- Acc@1
- 64.71
- FLOPs (G) x views
- 2.06x1
- Parameters (M)
- 3.79
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| I3D-R50 |
- Acc@1
- 63.98
- FLOPs (G) x views
- 28.61x1
- Parameters (M)
- 28.04
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co X3D-L_16 |
- Acc@1
- 63.03
- FLOPs (G) x views
- 1.25x1
- Parameters (M)
- 6.15
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co X3D-M_16 |
- Acc@1
- 62.80
- FLOPs (G) x views
- 0.33x1
- Parameters (M)
- 3.79
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co X3D-S_13 |
- Acc@1
- 60.18
- FLOPs (G) x views
- 0.17x1
- Parameters (M)
- 3.79
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co I3D_8 |
- Acc@1
- 59.58
- FLOPs (G) x views
- 5.68x1
- Parameters (M)
- 28.04
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| R(2+1)D-18_16 |
- Acc@1
- 59.52
- FLOPs (G) x views
- 40.71x1
- Parameters (M)
- 31.51
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| X3D-XS |
- Acc@1
- 59.37
- FLOPs (G) x views
- 0.64x1
- Parameters (M)
- 3.79
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| Co I3D_64 |
- Acc@1
- 56.86
- FLOPs (G) x views
- 5.68x1
- Parameters (M)
- 28.04
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| R(2+1)D-18_8 |
- Acc@1
- 53.52
- FLOPs (G) x views
- 20.35x1
- Parameters (M)
- 31.51
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| RCU_8 |
- Acc@1
- 53.40
- FLOPs (G) x views
- 4.71x1
- Parameters (M)
- 12.80
|
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos 2021-05-31 |
코드 1 |
| ViViT-L/16x2 320 |
- Acc@5
- 94.7
|
ViViT: A Video Vision Transformer 2021-03-29 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 |
| ViT-B-VTN (1 layer, ImageNet pretrain) |
- Acc@5
- 93.4
|
Video Transformer Network 2021-02-01 |
코드 1 |
| MViT-B (train from scratch) |
- FLOPs (G) x views
- 225x5
|
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection 2021-12-02 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 |