Action Recognition In Videos On Ava V21
Metrics
mAP (Val)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | mAP (Val) |
|---|---|
| a-better-baseline-for-ava | 22.8 |
| slowfast-networks-for-video-recognition | 26.3 |
| long-term-feature-banks-for-detailed-video | 27.7 |
| ava-a-video-dataset-of-spatio-temporally | 22.0 |
| a-better-baseline-for-ava | 21.9 |
| slowfast-networks-for-video-recognition | 28.3 |
| slowfast-networks-for-video-recognition | 27.3 |
| video-action-transformer-network | 27.6 |
| video-action-transformer-network | 23.4 |
| slowfast-networks-for-video-recognition | 26.8 |
| actor-centric-relation-network | 17.4 |
| end-to-end-spatio-temporal-action | 41.7 |
| pose-and-joint-aware-action-recognition | 28.4 |
| d3d-distilled-3d-networks-for-video-action | 23 |
| actor-context-actor-relation-network-for | 30.0 |