| Paper | Code | mAP | ModelName | ReleaseDate |
|---|---|---|---|---|
| Modeling Multi-Label Action Dependencies for Temporal Action Localization | ✓ Link | 51.5 | MLAD | 2021-03-04 |
| CTRN: Class-Temporal Relational Network for Action Detection | 51.2 | CTRN | 2021-10-26 | |
| PDAN: Pyramid Dilated Attention Network for Action Detection | ✓ Link | 47.6 | PDAN | 2021-01-05 |
| Temporal Gaussian Mixture Layer for Videos | ✓ Link | 46.4 | TGM | 2018-03-16 |
| MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection | ✓ Link | 43.1 | MS-TCT (RGB only) | 2021-12-07 |
| Learning Latent Super-Events to Detect Multiple Activities in Videos | ✓ Link | 36.4 | I3D + our super-event | 2017-12-05 |
| Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos | ✓ Link | 28.1 | Two-stream + LSTM | 2015-07-21 |
| Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos | ✓ Link | 27.6 | Two-stream | 2015-07-21 |