Temporal Action Localization On Multithumos 1
Metrics
Average mAP
Results
Performance results of various models on this benchmark
Model Name | Average mAP | Paper Title | Repository | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PointTAD | 23.5 | 42.3 | 39.7 | 35.8 | 30.9 | 24.9 | 18.5 | 12.0 | 5.6 | 1.4 | PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points | - |
| MS-TCT | 16.2 | - | - | - | - | - | - | - | - | - | MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection | - |
| DualDETR (I3D-rgb) | 32.64 | 53.42 | - | 47.41 | - | 35.18 | - | 20.18 | - | 4.02 | Dual DETRs for Multi-Label Temporal Action Detection | - |
| TriDet (VideoMAEv2) | 37.5 | - | 57.7 | - | - | 42.7 | - | 24.3 | - | - | Temporal Action Localization with Enhanced Instant Discriminability | - |
| TriDet (I3D-rgb) | 30.7 | - | 49.1 | - | - | 34.3 | - | 17.8 | - | - | Temporal Action Localization with Enhanced Instant Discriminability | - |
| PDAN | 17.3 | - | - | - | - | - | - | - | - | - | PDAN: Pyramid Dilated Attention Network for Action Detection | |
| TemporalMaxer | 29.9 | 49.1 | 47.5 | 44.3 | 39.4 | 33.4 | 26.5 | 17.4 | 9.1 | 2.24 | TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization | - |
| MLAD | 14.2 | - | - | - | - | - | - | - | - | - | Modeling Multi-Label Action Dependencies for Temporal Action Localization | - |
0 of 8 row(s) selected.