Action Recognition on DailyDVS-200 (test)
54.65Top-1 AccSMV-EAR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SMV-EARInput Type=Multi-view, Backbone=ResNet18, Data Augmentation=Standard, MACs=1.8G, Params=23.5M2026.01 | 54.65 | 78.28 | |
| SMV-EAR*Input Type=Multi-view, Backbone=ResNet18, Data Augmentation=None, MACs=1.8G, Params=23.5M2026.01 | 50.06 | 76.47 | |
| MVFNetInput Type=Multi-view, Backbone=ResNet50, MACs=16.4G, Params=23.6M2026.01 | 48.3 | 75.91 | |
| Swin-TInput Type=Token, Backbone=Transformer, MACs=17.5G, Params=27.8M2026.01 | 48.06 | 74.47 | |
| TimeSformerInput Type=Token, Backbone=Transformer, MACs=107.3G, Params=121.2M2026.01 | 44.25 | 74.03 | |
| MVF-NetInput Type=Multi-view, Backbone=ResNet34&18, MACs=2.8G, Params=33.6M2026.01 | 43.98 | 70.39 | |
| ACTION-NetInput Type=Frame, Backbone=ResNet50, MACs=34.7G, Params=27.9M2026.01 | 42.61 | 71.24 | |
| SlowFastInput Type=Frame, Backbone=ResNet50, MACs=0.7G, Params=33.6M2026.01 | 41.49 | 68.19 | |
| TSMInput Type=Frame, Backbone=ResNet50, MACs=0.7G, Params=24.3M2026.01 | 40.87 | 71.46 | |
| GETInput Type=Token, Backbone=Transformer, MACs=0.9G, Params=4.5M2026.01 | 37.28 | 61.59 | |
| SpikeformerInput Type=Spike, Backbone=Transformer, Params=29.7M2026.01 | 36.94 | 62.37 | |
| CoSTInput Type=Multi-view, Backbone=ResNet50, MACs=9.6G, Params=25.4M2026.01 | 36.09 | 64.45 | |
| R2Plus1DInput Type=Frame, Backbone=ResNet34, MACs=40.7G, Params=63.5M2026.01 | 36.06 | 63.67 | |
| SDTInput Type=Spike, Backbone=Transformer, Params=29.3M2026.01 | 35.43 | 58.81 | |
| ESTInput Type=Learned, Backbone=ResNet34, MACs=2.1G, Params=21.5M2026.01 | 32.23 | 59.66 | |
| ESTFInput Type=Token, Backbone=ResNet18, MACs=17.6G, Params=46.1M2026.01 | 24.68 | 50.18 | |
| C3DInput Type=Frame, Backbone=3D CNN, MACs=0.2G, Params=147.2M2026.01 | 21.99 | 45.81 |