Action Recognition In Videos On Thumos14
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | [email protected] | [email protected] |
|---|---|---|
| temporal-context-network-for-activity | 33.3 | 25.6 |
| temporal-action-detection-with-structured | 41.0 | 29.8 |
| bsn-boundary-sensitive-network-for-temporal | 45.0 | 36.9 |
| multi-granularity-generator-for-temporal | 46.8 | 37.4 |
| end-to-end-learning-of-action-detection-from | 26.4 | 17.1 |
| bmn-boundary-matching-network-for-temporal | 47.4 | 38.8 |
| two-stream-region-convolutional-3d-network | 43.1 | 35.8 |
| two-stream-region-convolutional-3d-network | 43.0 | 36.1 |
| temporal-action-localization-in-untrimmed | 28.7 | 19.0 |
| turn-tap-temporal-unit-regression-network-for | 35.3 | 24.5 |