Few Shot Action Recognition On Hmdb51
Metrics
1:1 Accuracy
Results
Performance results of various models on this benchmark
Model Name | 1:1 Accuracy | Paper Title | Repository |
|---|---|---|---|
| Learn2Aug + TRX | 76.4 | Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition | - |
| ARN | 60.6 | Few-shot Action Recognition with Permutation-invariant Attention | |
| STRM | 77.3 | Spatio-temporal Relation Modeling for Few-shot Action Recognition | |
| TRX | 75.6 | Temporal-Relational CrossTransformers for Few-Shot Action Recognition | |
| HyRSM | 76.0 | Hybrid Relation Guided Set Matching for Few-shot Action Recognition | |
| AMeFu-Net | 75.5 | Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition | - |
| HF-AR | 62.2 | - | - |
0 of 7 row(s) selected.